feat(evalboard): make analytics surfaces harness-aware and stream tables

evalboard/app/_components/harness-badge.tsx

@@ -1,22 +1,35 @@
 import Image from "next/image";
 
-// Vendor logo for a run's harness (RunConfig). Renders the recognizable
+// Canonical harness constants live in the leaf lib/harness module (shared by
+// the server data layer); re-exported here so existing badge importers are
+// unaffected.
+export { KNOWN_HARNESSES, type KnownHarness } from "@/lib/harness";
+
+// Vendor logo + labels for a run's harness (RunConfig). Renders the recognizable
 // vendor mark instead of raw "claude-code"/"codex"/"antigravity" text,
 // mirroring the Slack rollup's vendor emoji. A missing harness defaults to
 // claude-code (the nightly). This is an internal-only column — the caller
 // gates it behind isInternal (see lib/edition.ts).
-const HARNESS_LOGO: Record<string, { src: string; label: string }> = {
+const HARNESS_LOGO: Record<string, { src: string; label: string; short: string }> = {
     "claude-code": {
         src: "/harness/claude-code.png",
         label: "Claude Code · Anthropic",
+        short: "Claude Code",
     },
-    codex: { src: "/harness/codex.png", label: "Codex · OpenAI" },
+    codex: { src: "/harness/codex.png", label: "Codex · OpenAI", short: "Codex" },
     antigravity: {
         src: "/harness/antigravity.png",
         label: "Antigravity · Google Gemini",
+        short: "Antigravity",
     },
 };
 
+// Short human label for a harness id ("Claude Code"), for selectors and prose.
+// Unknown ids fall through to the raw id.
+export function harnessShortLabel(harness: string): string {
+    return HARNESS_LOGO[harness]?.short ?? harness;
+}
+
 export function HarnessBadge({ harness }: { harness?: string | null }) {
     const key = harness ?? "claude-code";
     const logo = HARNESS_LOGO[key];

evalboard/app/_components/harness-selector.tsx

@@ -0,0 +1,49 @@
+"use client";
+
+import { usePathname, useRouter, useSearchParams } from "next/navigation";
+import { HarnessBadge, harnessShortLabel } from "./harness-badge";
+
+// Segmented control for the trends page's harness scope. Sets `?h=<harness>`
+// while preserving the active q/tag params, mirroring WindowSelector. Each
+// segment shows the vendor logo + short label so it reads like the per-run
+// harness badge on the runs tables.
+export function HarnessSelector({
+    current,
+    harnesses,
+}: {
+    current: string;
+    harnesses: readonly string[];
+}) {
+    const router = useRouter();
+    const pathname = usePathname();
+    const searchParams = useSearchParams();
+    const set = (h: string) => {
+        const p = new URLSearchParams(searchParams.toString());
+        p.set("h", h);
+        router.replace(`${pathname}?${p.toString()}`, { scroll: false });
+    };
+    // Always show the active harness, even if it has aged out of the recent
+    // window (so a deep-linked `?h=` still reads as selected rather than absent).
+    const opts = harnesses.includes(current)
+        ? harnesses
+        : [current, ...harnesses];
+    return (
+        <div className="inline-flex border border-gray-200 rounded-md overflow-hidden text-sm">
+            {opts.map((h) => {
+                const active = h === current;
+                return (
+                    <button
+                        key={h}
+                        type="button"
+                        onClick={() => set(h)}
+                        aria-pressed={active}
+                        className={`flex items-center gap-1.5 px-3 py-1 ${active ? "bg-studio-blue text-white" : "bg-white text-gray-700 hover:bg-gray-50"}`}
+                    >
+                        <HarnessBadge harness={h} />
+                        {harnessShortLabel(h)}
+                    </button>
+                );
+            })}
+        </div>
+    );
+}

evalboard/app/_overview/tag-rail.tsx

@@ -1,5 +1,6 @@
 import Link from "next/link";
 import type { TagCount } from "@/lib/overview";
+import { DEFAULT_HARNESS } from "@/lib/harness";
 import type { Window } from "@/lib/reviews-types";
 
 type Variant = "neutral" | "rose" | "indigo";
@@ -35,11 +36,16 @@ function hrefForTag(
     tag: string | null,
     window: Window | null,
     q: string | null,
+    harness: string | null,
 ): string {
     const params = new URLSearchParams();
     if (window) params.set("window", window);
     if (tag) params.set("tag", tag);
     if (q) params.set("q", q);
+    // Preserve the active harness scope across tag clicks (omit the default to
+    // keep URLs clean). Without this, filtering by a tag would silently reset a
+    // codex/antigravity view back to claude-code.
+    if (harness && harness !== DEFAULT_HARNESS) params.set("h", harness);
     const qs = params.toString();
     return qs ? `${basePath}?${qs}` : basePath;
 }
@@ -52,6 +58,7 @@ function TagChip({
     basePath,
     window,
     q,
+    harness,
 }: {
     tag: string;
     count: number;
@@ -60,11 +67,12 @@ function TagChip({
     basePath: string;
     window: Window | null;
     q: string | null;
+    harness: string | null;
 }) {
     const s = STYLES[variant];
     return (
         <Link
-            href={hrefForTag(basePath, active ? null : tag, window, q)}
+            href={hrefForTag(basePath, active ? null : tag, window, q, harness)}
             scroll={false}
             className={`inline-flex items-center gap-1 text-[11px] leading-none px-2 py-1 rounded border transition-colors ${active ? s.chipActive : s.chip}`}
         >
@@ -111,6 +119,7 @@ export function MergedTagRail({
     basePath = "/",
     window = null,
     q = null,
+    harness = null,
     limit = 24,
 }: {
     skills: TagCount[];
@@ -123,6 +132,8 @@ export function MergedTagRail({
     // Null on pages that don't expose a window selector (e.g. /trends).
     window?: Window | null;
     q?: string | null;
+    // Active harness scope to preserve in chip links (null = not harness-scoped).
+    harness?: string | null;
     limit?: number;
 }) {
     const s = pickShown(skills, limit, activeTag);
@@ -146,6 +157,7 @@ export function MergedTagRail({
                     basePath={basePath}
                     window={window}
                     q={q}
+                    harness={harness}
                 />
             ))}
             {r.shown.map((tc) => (
@@ -158,6 +170,7 @@ export function MergedTagRail({
                     basePath={basePath}
                     window={window}
                     q={q}
+                    harness={harness}
                 />
             ))}
             {t.shown.map((tc) => (
@@ -170,6 +183,7 @@ export function MergedTagRail({
                     basePath={basePath}
                     window={window}
                     q={q}
+                    harness={harness}
                 />
             ))}
             {totalRemaining > 0 && (

evalboard/app/page.tsx

@@ -3,8 +3,10 @@ import {
     getAdhocRunListing,
     getOverview,
     getRunListing,
+    listRecentHarnesses,
     type TagCount,
 } from "@/lib/overview";
+import { parseHarnessParam, DEFAULT_HARNESS } from "@/lib/harness";
 import { fmtDuration, fmtRunTime, fmtTimestamp, passClass } from "@/lib/format";
 import { WindowSelector } from "./_components/window-selector";
 import { WINDOWS, type Window } from "@/lib/reviews-types";
@@ -15,7 +17,8 @@ import { ChipLegend, MergedTagRail } from "./_overview/tag-rail";
 import { TableScroll } from "./_components/scroll-table";
 import { CollapsibleRail } from "./_components/collapsible-rail";
 import { isInternal } from "@/lib/edition";
-import { HarnessBadge } from "@/app/_components/harness-badge";
+import { HarnessBadge, harnessShortLabel } from "@/app/_components/harness-badge";
+import { HarnessSelector } from "@/app/_components/harness-selector";
 
 export const dynamic = "force-dynamic";
 
@@ -98,6 +101,7 @@ export default async function Page({
         window?: string;
         tag?: string;
         q?: string;
+        h?: string;
         limit?: string;
         alimit?: string;
     }>;
@@ -106,14 +110,20 @@ export default async function Page({
     const window = parseWindow(params.window);
     const activeTag = parseTag(params.tag);
     const q = parseQ(params.q);
+    const harness = parseHarnessParam(params.h);
     const limit = parseLimit(params.limit);
     const adhocLimit = parseAdhocLimit(params.alimit);
     const isFiltered = activeTag != null || q != null;
 
-    const [overview, listing, adhoc] = await Promise.all([
-        getOverview(window, activeTag, q),
+    // The analytics block (chart + rails) is scoped to one harness so the
+    // success line stops zigzagging across incomparable harnesses. The run
+    // LIST stays all-harness — seeing every recent run is the page's job, and
+    // the Harness column already disambiguates each row.
+    const [overview, listing, adhoc, harnesses] = await Promise.all([
+        getOverview(window, activeTag, q, harness),
         getRunListing(window, activeTag, q, limit),
         getAdhocRunListing(adhocLimit),
+        listRecentHarnesses(),
     ]);
 
     const skills = filterTagsByQuery(overview.skills, q);
@@ -133,10 +143,14 @@ export default async function Page({
     const rawAlimit = Array.isArray(params.alimit)
         ? params.alimit[0]
         : params.alimit;
+    // Omit the default harness from URLs to keep them clean; carry a non-default
+    // scope through every self-link so it isn't reset by pagination/clear.
+    const hParam = harness === DEFAULT_HARNESS ? undefined : harness;
     const base = {
         window,
         tag: activeTag,
         q,
+        h: hParam,
         limit: rawLimit,
         alimit: rawAlimit,
     };
@@ -146,7 +160,7 @@ export default async function Page({
         limit: Math.min(tableTotalLabel, shownCount + DEFAULT_LIMIT),
     });
     const showAllHref = buildHref({ ...base, limit: "all" });
-    const clearAllHref = buildHref({ window });
+    const clearAllHref = buildHref({ window, h: hParam });
 
     // Ad-hoc section disclosure: rows are filtered (by `q`) then capped to
     // adhocLimit; offer "Show all" while more match than are shown, and a
@@ -212,7 +226,7 @@ export default async function Page({
                                     {overview.runs.length === 1 ? "" : "s"}
                                     {" · "}
                                     <Link
-                                        href={buildHref({ window })}
+                                        href={buildHref({ window, h: hParam })}
                                         scroll={false}
                                         className="text-studio-blue hover:underline"
                                     >
@@ -221,14 +235,21 @@ export default async function Page({
                                 </>
                             ) : (
                                 <>
-                                    Success rate per run across the last{" "}
-                                    {window} · {overview.runs.length} run
+                                    Success rate per{" "}
+                                    {harnessShortLabel(harness)} run across the
+                                    last {window} · {overview.runs.length} run
                                     {overview.runs.length === 1 ? "" : "s"}
                                 </>
                             )}
                         </p>
                     </div>
-                    <WindowSelector current={window} />
+                    <div className="flex items-center gap-3">
+                        <HarnessSelector
+                            current={harness}
+                            harnesses={harnesses}
+                        />
+                        <WindowSelector current={window} />
+                    </div>
                 </div>
                 <DailySuccessChart
                     data={overview.runs}
@@ -261,6 +282,7 @@ export default async function Page({
                             activeTag={activeTag}
                             window={window}
                             q={q}
+                            harness={harness}
                             limit={24}
                         />
                     </CollapsibleRail>

evalboard/app/path-to-ga/page.tsx

@@ -1,7 +1,14 @@
 import Link from "next/link";
-import { getOverview, getTagTaskBreakdown } from "@/lib/overview";
+import {
+    getOverview,
+    getTagTaskBreakdown,
+    listRecentHarnesses,
+} from "@/lib/overview";
+import { parseHarnessParam } from "@/lib/harness";
 import { humanizeTaskId } from "@/lib/format";
 import { WindowSelector } from "../_components/window-selector";
+import { HarnessSelector } from "../_components/harness-selector";
+import { harnessShortLabel } from "../_components/harness-badge";
 import { WINDOWS, type Window } from "@/lib/reviews-types";
 import { DailySuccessChart } from "../_overview/daily-chart";
 import { TableScroll } from "../_components/scroll-table";
@@ -26,14 +33,18 @@ function passClass(pct: number | null): string {
 export default async function PathToGaPage({
     searchParams,
 }: {
-    searchParams: Promise<{ window?: string }>;
+    searchParams: Promise<{ window?: string; h?: string }>;
 }) {
     const params = await searchParams;
     const window = parseWindow(params.window);
+    const harness = parseHarnessParam(params.h);
 
-    const [overview, taskRows] = await Promise.all([
-        getOverview(window, TAG, null),
-        getTagTaskBreakdown(window, TAG),
+    // Scope to one harness — readiness of a task is per-harness, and a blended
+    // chart/pass-rate mixes incomparable regimes.
+    const [overview, taskRows, harnesses] = await Promise.all([
+        getOverview(window, TAG, null, harness),
+        getTagTaskBreakdown(window, TAG, harness),
+        listRecentHarnesses(),
     ]);
 
     const runsInWindow = overview.runs.length;
@@ -52,10 +63,14 @@ export default async function PathToGaPage({
                     </h1>
                     <p className="text-sm text-gray-500">
                         Score for every task tagged{" "}
-                        <span className="font-mono text-gray-700">{TAG}</span>.
+                        <span className="font-mono text-gray-700">{TAG}</span> on{" "}
+                        {harnessShortLabel(harness)}.
                     </p>
                 </div>
-                <WindowSelector current={window} />
+                <div className="flex items-center gap-3">
+                    <HarnessSelector current={harness} harnesses={harnesses} />
+                    <WindowSelector current={window} />
+                </div>
             </div>
 
             <section className="border border-gray-200 rounded-lg bg-white p-4 space-y-4">

evalboard/app/trends/__tests__/trends-view.test.tsx

@@ -1,13 +1,22 @@
 import { describe, expect, test, vi } from "vitest";
 import { render, screen } from "@testing-library/react";
 import type { TaskTrend } from "@/lib/trends";
+import { KNOWN_HARNESSES } from "@/app/_components/harness-badge";
 
 // The view imports the server action for the expandable history rows; stub it
 // so rendering doesn't pull the blob-backed loader into a jsdom test.
 vi.mock("../actions", () => ({
     fetchTaskHistoryAction: vi.fn(async () => []),
 }));
 
+// The header's HarnessSelector reads router/params hooks; stub them so the view
+// renders in jsdom without a router provider.
+vi.mock("next/navigation", () => ({
+    useRouter: () => ({ replace: vi.fn() }),
+    usePathname: () => "/trends",
+    useSearchParams: () => new URLSearchParams(),
+}));
+
 const { TrendsView } = await import("../trends-view");
 
 function trend(overrides: Partial<TaskTrend>): TaskTrend {
@@ -35,6 +44,8 @@ function renderView(tasks: TaskTrend[], runIds: string[]) {
             runIds={runIds}
             q={null}
             activeTag={null}
+            activeHarness="claude-code"
+            harnesses={KNOWN_HARNESSES}
             skills={[]}
             taskTags={[]}
             reviewTags={[]}