feat(gui): show and filter intercepted helper requests in Logs

.github/workflows/ci.yml

@@ -516,7 +516,7 @@ jobs:
             if [ "$suite_status" -eq 0 ]; then
               exit 0
             fi
-            if ! grep -Eqi 'oh no: Bun has crashed|Segmentation fault at address|Illegal instruction|Bus error|Aborted \(core dumped\)' "$suite_log"; then
+            if ! grep -Eqi 'oh no: Bun has crashed|Internal assertion failure|Segmentation fault at address|Illegal instruction|Bus error|Aborted \(core dumped\)' "$suite_log"; then
               echo "::error::macOS suite failed on attempt ${attempt} (exit ${suite_status}); assertion failures are not retried."
               exit "$suite_status"
             fi
@@ -611,7 +611,31 @@ jobs:
         # the only one left on Bun's 5s default, and it is the slowest hardware on the board.
         # Three of its failures were the default firing on tests that had not hung — the
         # composed-acceptance cases spawn a real `ocx start` and were still working at 41s.
-        run: bun test --isolate --timeout 60000 tests --shard=${{ matrix.shard }}/4
+        #
+        # The retry is the same one the macOS leg already carries, for the same reason: a Bun
+        # runtime panic is a crash in the interpreter, not a test result, and failing the shard
+        # on it reports a defect this repository does not have (#2152). An ordinary assertion
+        # failure returns its status immediately — only the crash signatures below are retried,
+        # and only once, so a genuinely broken build cannot be retried into green.
+        shell: bash
+        run: |
+          set +e
+          set -uo pipefail
+          suite_log="$(mktemp -t ocx-windows-suite.XXXXXX)"
+          for attempt in 1 2; do
+            bun test --isolate --timeout 60000 tests --shard=${{ matrix.shard }}/4 2>&1 | tee "$suite_log"
+            suite_status="${PIPESTATUS[0]}"
+            if [ "$suite_status" -eq 0 ]; then
+              exit 0
+            fi
+            if ! grep -Eqi 'oh no: Bun has crashed|Internal assertion failure|Segmentation fault at address|Illegal instruction|Bus error|Aborted \(core dumped\)' "$suite_log"; then
+              echo "::error::Windows shard ${{ matrix.shard }}/4 failed on attempt ${attempt} (exit ${suite_status}); assertion failures are not retried."
+              exit "$suite_status"
+            fi
+            echo "::warning::Bun runtime crash in Windows shard ${{ matrix.shard }}/4 (exit ${suite_status}, attempt ${attempt})."
+          done
+          echo "::error::Bun runtime crash repeated on Windows shard ${{ matrix.shard }}/4; failing after one retry."
+          exit 1
 
       - name: CLI help smoke
         run: bun run src/cli/index.ts help

gui/src/i18n/de.ts

@@ -638,6 +638,9 @@ export const de: Record<TKey, string> = {
   "logs.filter.surface.claude": "Claude",
   "logs.filter.surface.codex": "Codex",
   "logs.filter.surface.grok": "Grok",
+  "logs.filter.interceptedHelpersOnly": "Nur abgefangene Helfer",
+  "logs.badge.interceptedHelper": "I · {model}",
+  "logs.badge.interceptedHelperTitle": "Abgefangene Helfer-Anfrage",
   "logs.filter.conversation.label": "Konversation",
   "logs.filter.conversation.placeholder": "Konversations-ID einfügen",
   "logs.filter.conversation.clear": "Löschen",

gui/src/i18n/en.ts

@@ -671,6 +671,9 @@ export const en = {
   "logs.filter.surface.claude": "Claude",
   "logs.filter.surface.codex": "Codex",
   "logs.filter.surface.grok": "Grok",
+  "logs.filter.interceptedHelpersOnly": "Intercepted helpers only",
+  "logs.badge.interceptedHelper": "I · {model}",
+  "logs.badge.interceptedHelperTitle": "Intercepted helper request",
   "logs.filter.conversation.label": "Conversation",
   "logs.filter.conversation.placeholder": "Paste conversation id",
   "logs.filter.conversation.clear": "Clear",

gui/src/i18n/fr.ts

@@ -652,6 +652,9 @@ export const fr: Record<TKey, string> = {
   "logs.filter.surface.claude": "Claude",
   "logs.filter.surface.codex": "Codex",
   "logs.filter.surface.grok": "Grok",
+  "logs.filter.interceptedHelpersOnly": "Assistants interceptés uniquement",
+  "logs.badge.interceptedHelper": "I · {model}",
+  "logs.badge.interceptedHelperTitle": "Requête d'assistant interceptée",
   "logs.filter.conversation.label": "Conversation",
   "logs.filter.conversation.placeholder": "Coller l’ID de conversation",
   "logs.filter.conversation.clear": "Effacer",

gui/src/i18n/ja.ts

@@ -614,6 +614,9 @@ export const ja: Record<TKey, string> = {
   "logs.filter.surface.claude": "Claude",
   "logs.filter.surface.codex": "Codex",
   "logs.filter.surface.grok": "Grok",
+  "logs.filter.interceptedHelpersOnly": "インターセプトされたヘルパーのみ",
+  "logs.badge.interceptedHelper": "I · {model}",
+  "logs.badge.interceptedHelperTitle": "インターセプトされたヘルパー要求",
   "logs.filter.conversation.label": "会話",
   "logs.filter.conversation.placeholder": "会話 ID を貼り付け",
   "logs.filter.conversation.clear": "クリア",

gui/src/i18n/ko.ts

@@ -657,6 +657,9 @@ export const ko: Record<TKey, string> = {
   "logs.filter.surface.claude": "Claude",
   "logs.filter.surface.codex": "Codex",
   "logs.filter.surface.grok": "Grok",
+  "logs.filter.interceptedHelpersOnly": "가로챈 헬퍼만",
+  "logs.badge.interceptedHelper": "I · {model}",
+  "logs.badge.interceptedHelperTitle": "가로챈 헬퍼 요청",
   "logs.filter.conversation.label": "대화",
   "logs.filter.conversation.placeholder": "대화 ID 붙여넣기",
   "logs.filter.conversation.clear": "지우기",

gui/src/i18n/ru.ts

@@ -655,6 +655,9 @@ export const ru: Record<TKey, string> = {
   "logs.filter.surface.claude": "Claude",
   "logs.filter.surface.codex": "Codex",
   "logs.filter.surface.grok": "Grok",
+  "logs.filter.interceptedHelpersOnly": "Только перехваченные помощники",
+  "logs.badge.interceptedHelper": "I · {model}",
+  "logs.badge.interceptedHelperTitle": "Перехваченный запрос помощника",
   "logs.filter.conversation.label": "Диалог",
   "logs.filter.conversation.placeholder": "Вставьте ID диалога",
   "logs.filter.conversation.clear": "Сбросить",

gui/src/i18n/tr.ts

@@ -662,6 +662,9 @@ export const tr: Record<TKey, string> = {
   "logs.filter.surface.claude": "Claude",
   "logs.filter.surface.codex": "Codex",
   "logs.filter.surface.grok": "Grok",
+  "logs.filter.interceptedHelpersOnly": "Yalnizca yakalanan yardimcilar",
+  "logs.badge.interceptedHelper": "I · {model}",
+  "logs.badge.interceptedHelperTitle": "Yakalanan yardimci istegi",
   "logs.filter.conversation.label": "Sohbet",
   "logs.filter.conversation.placeholder": "Sohbet ID'sini yapıştırın",
   "logs.filter.conversation.clear": "Temizle",

gui/src/i18n/zh-TW.ts

@@ -509,6 +509,9 @@ export const zhTW: Record<TKey, string> = {
   "logs.filter.surface.claude": "Claude",
   "logs.filter.surface.codex": "Codex",
   "logs.filter.surface.grok": "Grok",
+  "logs.filter.interceptedHelpersOnly": "僅已攔截的輔助請求",
+  "logs.badge.interceptedHelper": "I · {model}",
+  "logs.badge.interceptedHelperTitle": "已攔截的輔助請求",
   "logs.filter.conversation.label": "對話",
   "logs.filter.conversation.placeholder": "貼上對話 ID",
   "logs.filter.conversation.clear": "清除",

gui/src/i18n/zh.ts

@@ -650,6 +650,9 @@ export const zh: Record<TKey, string> = {
   "logs.filter.surface.claude": "Claude",
   "logs.filter.surface.codex": "Codex",
   "logs.filter.surface.grok": "Grok",
+  "logs.filter.interceptedHelpersOnly": "仅已拦截的辅助请求",
+  "logs.badge.interceptedHelper": "I · {model}",
+  "logs.badge.interceptedHelperTitle": "已拦截的辅助请求",
   "logs.filter.conversation.label": "会话",
   "logs.filter.conversation.placeholder": "粘贴会话 ID",
   "logs.filter.conversation.clear": "清除",

gui/src/pages/Logs.tsx

@@ -133,6 +133,15 @@ export interface LogEntry {
   provider: string;
   surface?: LogSurface;
   conversationId?: string;
+  /**
+   * The original helper model, when Shadow Call Intercept rewrote this request.
+   *
+   * Present ONLY for an intercepted request. A helper request that was not intercepted --
+   * interception off, no replacement model, or a slug the matcher does not recognize -- is
+   * indistinguishable here from ordinary traffic, which is why the filter below says
+   * "intercepted" rather than "helper".
+   */
+  shadowCallRewrittenFrom?: string;
   requestedEffort?: string;
   effectiveEffort?: string;
   reasoningWireField?: string;
@@ -174,6 +183,7 @@ function validCachedLogs(cached: LogEntry[] | null): LogEntry[] | null {
       || typeof entry.provider !== "string"
       || typeof entry.status !== "number"
       || typeof entry.durationMs !== "number"
+      || (entry.shadowCallRewrittenFrom !== undefined && typeof entry.shadowCallRewrittenFrom !== "string")
       || !validCachedRouteDecision(entry.routeDecision)
     ) {
       return null;
@@ -355,6 +365,7 @@ export default function Logs({ apiBase }: { apiBase: string }) {
   const [autoRefresh, setAutoRefresh] = useState(true);
   const [detail, setDetail] = useState<LogEntry | null>(null);
   const [surfaceFilter, setSurfaceFilter] = useState<LogSurfaceFilter>("all");
+  const [interceptedHelpersOnly, setInterceptedHelpersOnly] = useState(false);
   const [conversationFilter, setConversationFilter] = useState("");
   const [conversationQueryHash, setConversationQueryHash] = useState<string | undefined>();
   const scrollContainerRef = useRef<HTMLDivElement>(null);
@@ -472,6 +483,7 @@ export default function Logs({ apiBase }: { apiBase: string }) {
 
   const filteredLogs = logs.filter(log => (
     logMatchesSurface(log, surfaceFilter)
+    && (!interceptedHelpersOnly || Boolean(log.shadowCallRewrittenFrom))
     && (!conversationQuery || matchesLogConversationId(log.conversationId, conversationQuery, conversationQueryHash))
   ));
   const conversationTotals = conversationQuery ? summarizeFilteredLogs(filteredLogs) : null;
@@ -566,6 +578,20 @@ export default function Logs({ apiBase }: { apiBase: string }) {
             </button>
           ))}
         </div>
+        {/*
+          "Intercepted", not "helper". The marker only exists when Shadow Call Intercept
+          rewrote the request, so a helper request that was not intercepted looks exactly like
+          ordinary traffic here. A broader label would promise a classification this data
+          cannot support.
+        */}
+        <label className="muted text-control logs-filter-field">
+          <input
+            type="checkbox"
+            checked={interceptedHelpersOnly}
+            onChange={event => setInterceptedHelpersOnly(event.target.checked)}
+          />
+          {t("logs.filter.interceptedHelpersOnly")}
+        </label>
         <label className="muted text-control logs-filter-field">
           {t("logs.filter.conversation.label")}
           <input
@@ -717,8 +743,17 @@ export default function Logs({ apiBase }: { apiBase: string }) {
                     {formatEstimatedUsd(log.displayMetrics?.cost, t, localeTag)}
                   </td>
                  <td className="mono log-col-model" title={modelTitle(log, t)}>
-                   <span className="logs-model-cell">
-                    <span>{modelLabel(log.resolvedModel ?? log.model)}</span>
+                  <span className="logs-model-cell">
+                   <span>{modelLabel(log.resolvedModel ?? log.model)}</span>
+                      {log.shadowCallRewrittenFrom && (
+                        <span
+                          className="badge badge-muted"
+                          style={{ whiteSpace: "nowrap" }}
+                          title={t("logs.badge.interceptedHelperTitle")}
+                        >
+                          {t("logs.badge.interceptedHelper", { model: log.shadowCallRewrittenFrom })}
+                        </span>
+                      )}
                       {(log.surface === "claude" || log.surface === "claude-desktop") && (
                         <span className="badge badge-accent">{t("logs.badge.claude")}</span>
                       )}

gui/tests/fr-localization.test.ts

@@ -47,6 +47,9 @@ const INTENTIONAL_ENGLISH = new Set<TKey>([
   "dash.updateVersionTransition",
   "prov.accountId",
   "models.shadowCallOriginal",
+  // One-glyph marker plus a model id in a narrow column; the meaning lives in the translated
+  // tooltip (`logs.badge.interceptedHelperTitle`), not in the glyph.
+  "logs.badge.interceptedHelper",
   "models.v2Mode_v1",
   "models.v2Mode_default",
   "models.v2Mode_v2",

gui/tests/locale-parity.test.ts

@@ -124,6 +124,12 @@ const ZH_TW_KEEP_ENGLISH: ReadonlySet<string> = new Set([
   "routing.analyticsP99",
   // Format template with placeholder only; other locales (zh/ja/ko) keep it identical to en
   "models.shadowCallOriginal",
+  // A one-glyph marker plus the model id, sitting inside a narrow table column. The glyph is
+  // an icon-shaped affordance rather than a word, and its meaning is carried by the tooltip
+  // (`logs.badge.interceptedHelperTitle`), which IS translated. Localizing the glyph per
+  // locale would make the same badge unrecognizable across a screenshot or a bug report for
+  // no gain in comprehension.
+  "logs.badge.interceptedHelper",
   "models.v2Mode_default",
   "models.v2Mode_v1",
   "models.v2Mode_v2",

gui/tests/logs-auto-refresh.test.tsx

@@ -481,3 +481,56 @@ test("Logs: inside-card clicks keep the detail dialog open; backdrop dismiss clo
 
   await act(async () => { root.unmount(); });
 });
+
+// #2157: the Codex App sends helper requests on every message and turn completion. That
+// traffic is the App's, not ours -- what is ours is making an INTERCEPTED one identifiable, so
+// the reporter can tell recurring helper spend from their own work.
+//
+// "Intercepted", deliberately. A helper request that was not intercepted carries no marker and
+// is indistinguishable from ordinary traffic here, so the filter must not promise more.
+test("Logs: an intercepted helper row is badged and filterable", async () => {
+  const interceptedLog = {
+    ...sampleLog,
+    requestId: "req-shadow",
+    model: "grok-4.6",
+    shadowCallRewrittenFrom: "gpt-5.6-luna",
+  };
+  globalThis.fetch = (async (input) => {
+    const url = String(input);
+    if (!url.includes("/api/logs")) return new Response(null, { status: 404 });
+    return jsonResponse([interceptedLog, sampleLog]);
+  }) as typeof fetch;
+
+  const { root, container } = await mountLogs();
+  await flushMicrotasks();
+
+  // The badge names the ORIGINAL helper model, which is the attribution that was being lost.
+  expect(container.textContent).toContain("I · gpt-5.6-luna");
+  expect(container.textContent).toContain("gpt-test");
+
+  const toggle = [...container.querySelectorAll("input[type=checkbox]")].find(
+    input => input.closest("label")?.textContent?.includes("Intercepted helpers only"),
+  ) as HTMLInputElement | undefined;
+  expect(toggle).toBeDefined();
+
+  await act(async () => { toggle!.click(); });
+  await act(async () => {
+    jest.advanceTimersByTime(0);
+    await Promise.resolve();
+  });
+
+  // Filtered: the marked row stays, the ordinary one goes.
+  expect(container.textContent).toContain("I · gpt-5.6-luna");
+  expect(container.textContent).not.toContain("gpt-test");
+
+  await act(async () => { toggle!.click(); });
+  await act(async () => {
+    jest.advanceTimersByTime(0);
+    await Promise.resolve();
+  });
+
+  expect(container.textContent).toContain("gpt-test");
+
+  await act(async () => { root.unmount(); });
+});
+

scripts/ci/run-bun-test-batches.sh

@@ -78,7 +78,7 @@ is_bun_runtime_crash() {
   fi
 
   grep -Eqi \
-    'oh no: Bun has crashed|Segmentation fault at address|Illegal instruction|Bus error|Aborted \(core dumped\)' \
+    'oh no: Bun has crashed|Internal assertion failure|Segmentation fault at address|Illegal instruction|Bus error|Aborted \(core dumped\)' \
     "$log_file"
 }
 

tests/ci-workflows.test.ts

@@ -48,6 +48,21 @@ function hasExactShellCommand(run: string | undefined, expected: string): boolea
     .includes(expected);
 }
 
+/**
+ * Same intent as {@link hasExactShellCommand}, but for a command that is the HEAD of a
+ * pipeline. The retry loops capture the suite with `… 2>&1 | tee "$suite_log"`, so an exact
+ * whole-line match would reject the very shape the retry requires. Anchoring at the start of
+ * the line still rejects an `echo` of the command or a commented-out copy, which is what the
+ * exact match was protecting against.
+ */
+function hasShellCommandHead(run: string | undefined, expected: string): boolean {
+  return (run ?? "")
+    .split(/\r?\n/)
+    .map(line => line.trim())
+    .filter(line => line.length > 0 && !line.startsWith("#"))
+    .some(line => line === expected || line.startsWith(`${expected} `));
+}
+
 function expectSecureLinuxKeyringBootstrap(workflow: string): void {
   const smokeStep = workflow
     .split("- name: OS keyring create/read/delete smoke")[1]
@@ -224,17 +239,52 @@ describe("GitHub Actions hardening", () => {
     // Three composed-acceptance failures were that default firing on tests still working
     // at 41s. Pin the flag so the leg cannot silently drift back to the default.
     const windowsTestCommand = `bun test --isolate --timeout 60000 tests --shard=\${{ matrix.shard }}/${windowsShards.length}`;
-    expect(hasExactShellCommand(`echo ${windowsTestCommand}`, windowsTestCommand)).toBe(false);
+    expect(hasShellCommandHead(`echo ${windowsTestCommand}`, windowsTestCommand)).toBe(false);
     // Binding the assertion to an executable line is only half the guarantee: a
     // step carrying the exact command still runs nothing under `if: false`, and
     // the suite would stay green against a Windows leg that never tests. Require
     // the matching step to be unconditional.
-    const windowsTestSteps = winSteps.filter(step => hasExactShellCommand(step.run, windowsTestCommand));
+    const windowsTestSteps = winSteps.filter(step => hasShellCommandHead(step.run, windowsTestCommand));
     expect(windowsTestSteps.length).toBeGreaterThan(0);
     expect(windowsTestSteps.every(step => step.if === undefined)).toBe(true);
     expect(winSteps.some(step => step.if === "runner.environment == 'self-hosted'"
       && step.run?.includes("git clean -xffd"))).toBe(true);
 
+    // The three crash-signature lists must stay identical, and they must not key on
+    // `panic(thread`.
+    //
+    // Bun emits BOTH `panic(thread 2852)` and `panic(main thread)` for the same class of
+    // failure, so a grep anchored on the numbered form silently misses half of them and the
+    // shard fails on a crash it was supposed to retry. This repository already learned that
+    // once — `devlog/_fin/260731_pr_issue_triage_round/050_windows_ci_flake_rca.md` names
+    // `Internal assertion failure` as the stable fingerprint — and #2152 reintroduced it.
+    // Three copies of one list is the real hazard, so pin the sync rather than the text.
+    const crashSignatures = [
+      "oh no: Bun has crashed",
+      "Internal assertion failure",
+      "Segmentation fault at address",
+      "Illegal instruction",
+      "Bus error",
+    ];
+    const windowsTestRun = windowsTestSteps[0]?.run ?? "";
+    const batchScript = await readText("scripts/ci/run-bun-test-batches.sh");
+    for (const signature of crashSignatures) {
+      expect(`macos:${signature}:${macosTestRun.includes(signature)}`).toBe(`macos:${signature}:true`);
+      expect(`windows:${signature}:${windowsTestRun.includes(signature)}`).toBe(`windows:${signature}:true`);
+      expect(`script:${signature}:${batchScript.includes(signature)}`).toBe(`script:${signature}:true`);
+    }
+    // The thread-numbered form must not be the anchor anywhere.
+    expect(macosTestRun).not.toContain("panic\\(thread");
+    expect(windowsTestRun).not.toContain("panic\\(thread");
+    expect(batchScript).not.toContain("panic\\(thread");
+
+    // Windows carries the same bounded retry as macOS: one attempt, crash-only.
+    expect(hasExactShellCommand(windowsTestRun, "set +e")).toBe(true);
+    expect(windowsTestRun).toContain("for attempt in 1 2");
+    expect(windowsTestRun).not.toContain("while true");
+    expect(windowsTestRun).toContain("assertion failures are not retried");
+    expect(windowsTestRun).toContain("failing after one retry");
+
     // Every job that runs the root suite must build the GUI first, unconditionally.
     // Tests that fetch the served dashboard read their session bootstrap out of
     // `gui/dist/index.html`; with no build the server has no index to serve and the