EntityProcess · christso · Jul 3, 2026 · Jul 3, 2026 · Jul 3, 2026 · Jul 3, 2026
diff --git a/apps/web/astro.config.mjs b/apps/web/astro.config.mjs
@@ -1,11 +1,27 @@
+import { readFileSync } from 'node:fs';
+import { fileURLToPath } from 'node:url';
 import starlight from '@astrojs/starlight';
 import { defineConfig } from 'astro/config';
 
+// Static builds can't redirect an open-ended `/docs/[...slug]` wildcard to
+// v4.42.4 (that requires enumerable paths), so generate one concrete
+// redirect per known v4.42.4 route from its route manifest instead.
+const v4RoutesPath = fileURLToPath(new URL('./src/data/docs-v4.42.4-routes.json', import.meta.url));
+const v4Routes = JSON.parse(readFileSync(v4RoutesPath, 'utf8'));
+const v4Redirects = Object.fromEntries(
+  v4Routes.map((route) => {
+    const bareRoute = route.replace('/docs/v4.42.4/', '/docs/');
+    const from = bareRoute === '/docs/' ? '/docs' : bareRoute.replace(/\/$/, '');
+    return [from, route];
+  }),
+);
+
 export default defineConfig({
   site: 'https://agentv.dev',
   image: { service: { entrypoint: 'astro/assets/services/noop' } },
   redirects: {
     '/docs/v4': '/docs/v4.42.4/',
+    ...v4Redirects,
   },
   integrations: [
     starlight({
@@ -48,14 +64,14 @@ export default defineConfig({
         { icon: 'github', label: 'GitHub', href: 'https://github.com/EntityProcess/agentv' },
       ],
       sidebar: [
-        { label: 'Getting Started', autogenerate: { directory: 'docs/getting-started' } },
-        { label: 'Evaluation', autogenerate: { directory: 'docs/evaluation' } },
-        { label: 'Graders', autogenerate: { directory: 'docs/graders' } },
-        { label: 'Targets', autogenerate: { directory: 'docs/targets' } },
-        { label: 'Tools', autogenerate: { directory: 'docs/tools' } },
-        { label: 'Guides', autogenerate: { directory: 'docs/guides' } },
-        { label: 'Integrations', autogenerate: { directory: 'docs/integrations' } },
-        { label: 'Reference', autogenerate: { directory: 'docs/reference' } },
+        { label: 'Getting Started', autogenerate: { directory: 'docs/next/getting-started' } },
+        { label: 'Evaluation', autogenerate: { directory: 'docs/next/evaluation' } },
+        { label: 'Graders', autogenerate: { directory: 'docs/next/graders' } },
+        { label: 'Targets', autogenerate: { directory: 'docs/next/targets' } },
+        { label: 'Tools', autogenerate: { directory: 'docs/next/tools' } },
+        { label: 'Guides', autogenerate: { directory: 'docs/next/guides' } },
+        { label: 'Integrations', autogenerate: { directory: 'docs/next/integrations' } },
+        { label: 'Reference', autogenerate: { directory: 'docs/next/reference' } },
       ],
       editLink: {
         baseUrl: 'https://github.com/EntityProcess/agentv/edit/main/apps/web/',

diff --git a/apps/web/src/components/VersionSelect.astro b/apps/web/src/components/VersionSelect.astro
@@ -1,21 +1,25 @@
 ---
 const versions = [
-  { label: 'Canary', base: '/docs' },
+  { label: 'Next', base: '/docs/next' },
   { label: 'v4.42.4', base: '/docs/v4.42.4' },
 ];
 
+// Longest base first so more specific versions match before shorter prefixes.
+const versionsByBaseLength = [...versions].sort((a, b) => b.base.length - a.base.length);
+
 const pathname = Astro.url.pathname.replace(/\/$/, '') || '/';
 
 function getCurrentVersion(path) {
-  if (path === '/docs/v4.42.4' || path.startsWith('/docs/v4.42.4/')) return versions[1];
-  return versions[0];
+  return (
+    versionsByBaseLength.find(
+      (version) => path === version.base || path.startsWith(`${version.base}/`),
+    ) ?? versions[0]
+  );
 }
 
 function getVersionSuffix(path) {
-  if (path === '/docs' || path === '/docs/v4.42.4') return '';
-  if (path.startsWith('/docs/v4.42.4/')) return path.slice('/docs/v4.42.4'.length);
-  if (path.startsWith('/docs/')) return path.slice('/docs'.length);
-  return '';
+  const current = getCurrentVersion(path);
+  return path === current.base ? '' : path.slice(current.base.length);
 }
 
 function withTrailingSlash(path) {

diff --git a/apps/web/src/components/VersionedSidebar.astro b/apps/web/src/components/VersionedSidebar.astro
@@ -3,18 +3,28 @@ import MobileMenuFooter from 'virtual:starlight/components/MobileMenuFooter';
 import SidebarPersister from '@astrojs/starlight/components/SidebarPersister.astro';
 import SidebarSublist from '@astrojs/starlight/components/SidebarSublist.astro';
 import type { SidebarEntry } from '@astrojs/starlight/utils/routing/types';
-import archiveRoutes from '../data/docs-v4.42.4-routes.json';
+import v4Routes from '../data/docs-v4.42.4-routes.json';
+
+// The Starlight sidebar config autogenerates from docs/next/*, so the base
+// sidebar's hrefs already point at the live /docs/next/ tree unmodified.
+// Only genuinely archived versions below need their hrefs remapped.
+const LIVE_PREFIX = '/docs/next/';
+const ARCHIVED_VERSIONS = [{ slug: 'v4.42.4', routes: v4Routes }];
 
-const ARCHIVE_PREFIX = '/docs/v4.42.4/';
 const { sidebar } = Astro.locals.starlightRoute;
 const pathname = withTrailingSlash(Astro.url.pathname);
-const routeSet = new Set(archiveRoutes);
-const renderedSidebar = isArchivePath(pathname) ? toArchiveSidebar(sidebar) : sidebar;
+const archiveVersion = ARCHIVED_VERSIONS.find((version) => isArchivePath(pathname, version.slug));
+const renderedSidebar = archiveVersion ? toArchiveSidebar(sidebar, archiveVersion) : sidebar;
+
+function toArchiveSidebar(
+  entries: SidebarEntry[],
+  archiveVersion: (typeof ARCHIVED_VERSIONS)[number],
+): SidebarEntry[] {
+  const routeSet = new Set(archiveVersion.routes);
 
-function toArchiveSidebar(entries: SidebarEntry[]): SidebarEntry[] {
   return entries.flatMap((entry) => {
     if (entry.type === 'link') {
-      const archiveHref = toArchiveHref(entry.href);
+      const archiveHref = toArchiveHref(entry.href, archiveVersion.slug);
       if (!routeSet.has(stripHash(archiveHref))) return [];
 
       return [
@@ -26,7 +36,7 @@ function toArchiveSidebar(entries: SidebarEntry[]): SidebarEntry[] {
       ];
     }
 
-    const childEntries = toArchiveSidebar(entry.entries);
+    const childEntries = toArchiveSidebar(entry.entries, archiveVersion);
     if (!childEntries.length) return [];
 
     return [
@@ -38,17 +48,19 @@ function toArchiveSidebar(entries: SidebarEntry[]): SidebarEntry[] {
   });
 }
 
-function toArchiveHref(href: string) {
-  if (!href.startsWith('/docs/') || href.startsWith(ARCHIVE_PREFIX)) return href;
-  return href.replace('/docs/', ARCHIVE_PREFIX);
+function toArchiveHref(href: string, slug: string) {
+  const archivePrefix = `/docs/${slug}/`;
+  if (!href.startsWith(LIVE_PREFIX) || href.startsWith(archivePrefix)) return href;
+  return href.replace(LIVE_PREFIX, archivePrefix);
 }
 
 function withTrailingSlash(path: string) {
   return path.endsWith('/') ? path : `${path}/`;
 }
 
-function isArchivePath(path: string) {
-  return path === ARCHIVE_PREFIX || path.startsWith(ARCHIVE_PREFIX);
+function isArchivePath(path: string, slug: string) {
+  const archivePrefix = `/docs/${slug}/`;
+  return path === archivePrefix || path.startsWith(archivePrefix);
 }
 
 function stripHash(href: string) {

diff --git a/...ontent/docs/docs/evaluation/batch-cli.mdx → ...t/docs/docs/next/evaluation/batch-cli.mdx b/...ontent/docs/docs/evaluation/batch-cli.mdx → ...t/docs/docs/next/evaluation/batch-cli.mdx
diff --git a/...ntent/docs/docs/evaluation/eval-cases.mdx → .../docs/docs/next/evaluation/eval-cases.mdx b/...ntent/docs/docs/evaluation/eval-cases.mdx → .../docs/docs/next/evaluation/eval-cases.mdx
diff --git a/...ntent/docs/docs/evaluation/eval-files.mdx → .../docs/docs/next/evaluation/eval-files.mdx b/...ntent/docs/docs/evaluation/eval-files.mdx → .../docs/docs/next/evaluation/eval-files.mdx
diff --git a/...content/docs/docs/evaluation/examples.mdx → ...nt/docs/docs/next/evaluation/examples.mdx b/...content/docs/docs/evaluation/examples.mdx → ...nt/docs/docs/next/evaluation/examples.mdx
@@ -121,7 +121,7 @@ tests:
       - Output contains the transformed spreadsheet text including the revenue rows
 ```
 
-See [`examples/features/preprocessors/`](../../../../examples/features/preprocessors/) for a runnable end-to-end example with a file-producing target and custom grader target.
+See [`examples/features/preprocessors/`](../../../../../examples/features/preprocessors/) for a runnable end-to-end example with a file-producing target and custom grader target.
 
 ## Tool Trajectory
 
@@ -189,7 +189,7 @@ assert:
         prompt: ../prompts/grader-pass-fail-v1.md
 ```
 
-See [`examples/showcase/offline-grader-benchmark/`](../../../../examples/showcase/offline-grader-benchmark/) for the full workflow, replay target, export contract, scoring script, and A/B compare commands.
+See [`examples/showcase/offline-grader-benchmark/`](../../../../../examples/showcase/offline-grader-benchmark/) for the full workflow, replay target, export contract, scoring script, and A/B compare commands.
 
 ## Static Trace
 

diff --git a/...tent/docs/docs/evaluation/experiments.mdx → ...docs/docs/next/evaluation/experiments.mdx b/...tent/docs/docs/evaluation/experiments.mdx → ...docs/docs/next/evaluation/experiments.mdx
diff --git a/.../content/docs/docs/evaluation/rubrics.mdx → ...ent/docs/docs/next/evaluation/rubrics.mdx b/.../content/docs/docs/evaluation/rubrics.mdx → ...ent/docs/docs/next/evaluation/rubrics.mdx
diff --git a/...nt/docs/docs/evaluation/running-evals.mdx → ...cs/docs/next/evaluation/running-evals.mdx b/...nt/docs/docs/evaluation/running-evals.mdx → ...cs/docs/next/evaluation/running-evals.mdx
diff --git a/.../src/content/docs/docs/evaluation/sdk.mdx → ...content/docs/docs/next/evaluation/sdk.mdx b/.../src/content/docs/docs/evaluation/sdk.mdx → ...content/docs/docs/next/evaluation/sdk.mdx
diff --git a/...ocs/docs/getting-started/installation.mdx → ...ocs/next/getting-started/installation.mdx b/...ocs/docs/getting-started/installation.mdx → ...ocs/next/getting-started/installation.mdx
diff --git a/.../docs/docs/getting-started/quickstart.mdx → .../docs/next/getting-started/quickstart.mdx b/.../docs/docs/getting-started/quickstart.mdx → .../docs/next/getting-started/quickstart.mdx
diff --git a/...ontent/docs/docs/graders/code-graders.mdx → ...t/docs/docs/next/graders/code-graders.mdx b/...ontent/docs/docs/graders/code-graders.mdx → ...t/docs/docs/next/graders/code-graders.mdx
diff --git a/...c/content/docs/docs/graders/composite.mdx → ...tent/docs/docs/next/graders/composite.mdx b/...c/content/docs/docs/graders/composite.mdx → ...tent/docs/docs/next/graders/composite.mdx
diff --git a/...t/docs/docs/graders/custom-assertions.mdx → ...s/docs/next/graders/custom-assertions.mdx b/...t/docs/docs/graders/custom-assertions.mdx → ...s/docs/next/graders/custom-assertions.mdx
diff --git a/...tent/docs/docs/graders/custom-graders.mdx → ...docs/docs/next/graders/custom-graders.mdx b/...tent/docs/docs/graders/custom-graders.mdx → ...docs/docs/next/graders/custom-graders.mdx
diff --git a/...t/docs/docs/graders/execution-metrics.mdx → ...s/docs/next/graders/execution-metrics.mdx b/...t/docs/docs/graders/execution-metrics.mdx → ...s/docs/next/graders/execution-metrics.mdx
diff --git a/...content/docs/docs/graders/llm-graders.mdx → ...nt/docs/docs/next/graders/llm-graders.mdx b/...content/docs/docs/graders/llm-graders.mdx → ...nt/docs/docs/next/graders/llm-graders.mdx
@@ -221,7 +221,7 @@ Resolution order:
 - if no preprocessor matches, AgentV falls back to a UTF-8 text read
 - if the fallback read looks binary or invalid, the grader receives a warning note instead of failing the test run
 
-See [`examples/features/preprocessors/`](../../../../examples/features/preprocessors/) for a runnable example with a file-producing target and a custom preprocessor script.
+See [`examples/features/preprocessors/`](../../../../../examples/features/preprocessors/) for a runnable example with a file-producing target and a custom preprocessor script.
 
 ## Available Context Fields
 

diff --git a/...tent/docs/docs/graders/python-helpers.mdx → ...docs/docs/next/graders/python-helpers.mdx b/...tent/docs/docs/graders/python-helpers.mdx → ...docs/docs/next/graders/python-helpers.mdx
diff --git a/...ent/docs/docs/graders/structured-data.mdx → ...ocs/docs/next/graders/structured-data.mdx b/...ent/docs/docs/graders/structured-data.mdx → ...ocs/docs/next/graders/structured-data.mdx
diff --git a/...ent/docs/docs/graders/tool-trajectory.mdx → ...ocs/docs/next/graders/tool-trajectory.mdx b/...ent/docs/docs/graders/tool-trajectory.mdx → ...ocs/docs/next/graders/tool-trajectory.mdx
diff --git a/...nt/docs/docs/guides/agent-eval-layers.mdx → ...cs/docs/next/guides/agent-eval-layers.mdx b/...nt/docs/docs/guides/agent-eval-layers.mdx → ...cs/docs/next/guides/agent-eval-layers.mdx
diff --git a/...content/docs/docs/guides/autoresearch.mdx → ...nt/docs/docs/next/guides/autoresearch.mdx b/...content/docs/docs/guides/autoresearch.mdx → ...nt/docs/docs/next/guides/autoresearch.mdx
@@ -6,7 +6,7 @@ sidebar:
 ---
 
 import { Image } from 'astro:assets';
-import trajectoryChart from '../../../../assets/screenshots/autoresearch-trajectory.png';
+import trajectoryChart from '../../../../../assets/screenshots/autoresearch-trajectory.png';
 
 Autoresearch is an unattended optimization loop that **automatically improves your agent skills** through repeated eval cycles. It runs the same evaluate → analyze → improve loop described in the [Skill Improvement Workflow](/docs/guides/skill-improvement-workflow/), but does it hands-free — no human review between cycles.
 

diff --git a/...docs/docs/guides/benchmark-provenance.mdx → ...docs/next/guides/benchmark-provenance.mdx b/...docs/docs/guides/benchmark-provenance.mdx → ...docs/next/guides/benchmark-provenance.mdx
diff --git a/...ocs/docs/guides/enterprise-governance.mdx → ...ocs/next/guides/enterprise-governance.mdx b/...ocs/docs/guides/enterprise-governance.mdx → ...ocs/next/guides/enterprise-governance.mdx
diff --git a/...ntent/docs/docs/guides/eval-authoring.mdx → .../docs/docs/next/guides/eval-authoring.mdx b/...ntent/docs/docs/guides/eval-authoring.mdx → .../docs/docs/next/guides/eval-authoring.mdx
diff --git a/...ent/docs/docs/guides/evaluation-types.mdx → ...ocs/docs/next/guides/evaluation-types.mdx b/...ent/docs/docs/guides/evaluation-types.mdx → ...ocs/docs/next/guides/evaluation-types.mdx
diff --git a/...ocs/guides/skill-improvement-workflow.mdx → ...ext/guides/skill-improvement-workflow.mdx b/...ocs/guides/skill-improvement-workflow.mdx → ...ext/guides/skill-improvement-workflow.mdx
diff --git a/...cs/docs/guides/workspace-architecture.mdx → ...cs/next/guides/workspace-architecture.mdx b/...cs/docs/guides/workspace-architecture.mdx → ...cs/next/guides/workspace-architecture.mdx
diff --git a/apps/web/src/content/docs/docs/index.mdx → .../web/src/content/docs/docs/next/index.mdx b/apps/web/src/content/docs/docs/index.mdx → .../web/src/content/docs/docs/next/index.mdx
diff --git a/.../docs/integrations/agent-skills-evals.mdx → .../next/integrations/agent-skills-evals.mdx b/.../docs/integrations/agent-skills-evals.mdx → .../next/integrations/agent-skills-evals.mdx
diff --git a/...cs/integrations/autoevals-integration.mdx → ...xt/integrations/autoevals-integration.mdx b/...cs/integrations/autoevals-integration.mdx → ...xt/integrations/autoevals-integration.mdx
diff --git a/...ntent/docs/docs/integrations/langfuse.mdx → .../docs/docs/next/integrations/langfuse.mdx b/...ntent/docs/docs/integrations/langfuse.mdx → .../docs/docs/next/integrations/langfuse.mdx
diff --git a/...ontent/docs/docs/integrations/phoenix.mdx → ...t/docs/docs/next/integrations/phoenix.mdx b/...ontent/docs/docs/integrations/phoenix.mdx → ...t/docs/docs/next/integrations/phoenix.mdx
diff --git a/...ontent/docs/docs/reference/comparison.mdx → ...t/docs/docs/next/reference/comparison.mdx b/...ontent/docs/docs/reference/comparison.mdx → ...t/docs/docs/next/reference/comparison.mdx
diff --git a/.../docs/docs/reference/result-artifacts.mdx → .../docs/next/reference/result-artifacts.mdx b/.../docs/docs/reference/result-artifacts.mdx → .../docs/next/reference/result-artifacts.mdx
diff --git a/...ontent/docs/docs/targets/cli-provider.mdx → ...t/docs/docs/next/targets/cli-provider.mdx b/...ontent/docs/docs/targets/cli-provider.mdx → ...t/docs/docs/next/targets/cli-provider.mdx
diff --git a/...ntent/docs/docs/targets/coding-agents.mdx → .../docs/docs/next/targets/coding-agents.mdx b/...ntent/docs/docs/targets/coding-agents.mdx → .../docs/docs/next/targets/coding-agents.mdx
diff --git a/...ntent/docs/docs/targets/configuration.mdx → .../docs/docs/next/targets/configuration.mdx b/...ntent/docs/docs/targets/configuration.mdx → .../docs/docs/next/targets/configuration.mdx
diff --git a/...nt/docs/docs/targets/custom-providers.mdx → ...cs/docs/next/targets/custom-providers.mdx b/...nt/docs/docs/targets/custom-providers.mdx → ...cs/docs/next/targets/custom-providers.mdx
diff --git a/...ntent/docs/docs/targets/llm-providers.mdx → .../docs/docs/next/targets/llm-providers.mdx b/...ntent/docs/docs/targets/llm-providers.mdx → .../docs/docs/next/targets/llm-providers.mdx
diff --git a/...b/src/content/docs/docs/targets/retry.mdx → .../content/docs/docs/next/targets/retry.mdx b/...b/src/content/docs/docs/targets/retry.mdx → .../content/docs/docs/next/targets/retry.mdx
diff --git a/...b/src/content/docs/docs/tools/compare.mdx → .../content/docs/docs/next/tools/compare.mdx b/...b/src/content/docs/docs/tools/compare.mdx → .../content/docs/docs/next/tools/compare.mdx
diff --git a/...b/src/content/docs/docs/tools/convert.mdx → .../content/docs/docs/next/tools/convert.mdx b/...b/src/content/docs/docs/tools/convert.mdx → .../content/docs/docs/next/tools/convert.mdx
diff --git a/...src/content/docs/docs/tools/dashboard.mdx → ...ontent/docs/docs/next/tools/dashboard.mdx b/...src/content/docs/docs/tools/dashboard.mdx → ...ontent/docs/docs/next/tools/dashboard.mdx
@@ -6,20 +6,20 @@ sidebar:
 ---
 
 import { Image } from 'astro:assets';
-import studioRuns from '../../../../assets/screenshots/studio-runs.png';
-import studioRunDetail from '../../../../assets/screenshots/studio-run-detail.png';
-import studioExperiments from '../../../../assets/screenshots/studio-experiments.png';
-import studioProjects from '../../../../assets/screenshots/studio-projects.png';
-import studioProjectsMulti from '../../../../assets/screenshots/studio-projects-multi.png';
-import studioCompareAggregated from '../../../../assets/screenshots/studio-compare-aggregated.png';
-import studioComparePerRun from '../../../../assets/screenshots/studio-compare-per-run.png';
-import studioCompareSideBySide from '../../../../assets/screenshots/studio-compare-side-by-side.png';
-import studioRunsBench from '../../../../assets/screenshots/studio-runs-bench.png';
-import studioAnalyticsAggregated from '../../../../assets/screenshots/studio-analytics-aggregated.png';
-import studioAnalyticsCharts from '../../../../assets/screenshots/studio-analytics-charts.png';
-import studioAnalyticsTrend from '../../../../assets/screenshots/studio-analytics-trend.png';
-import studioRemoteResultsBeforeSync from '../../../../assets/screenshots/studio-remote-results-before-sync.png';
-import studioRemoteResultsAfterSync from '../../../../assets/screenshots/studio-remote-results-after-sync.png';
+import studioRuns from '../../../../../assets/screenshots/studio-runs.png';
+import studioRunDetail from '../../../../../assets/screenshots/studio-run-detail.png';
+import studioExperiments from '../../../../../assets/screenshots/studio-experiments.png';
+import studioProjects from '../../../../../assets/screenshots/studio-projects.png';
+import studioProjectsMulti from '../../../../../assets/screenshots/studio-projects-multi.png';
+import studioCompareAggregated from '../../../../../assets/screenshots/studio-compare-aggregated.png';
+import studioComparePerRun from '../../../../../assets/screenshots/studio-compare-per-run.png';
+import studioCompareSideBySide from '../../../../../assets/screenshots/studio-compare-side-by-side.png';
+import studioRunsBench from '../../../../../assets/screenshots/studio-runs-bench.png';
+import studioAnalyticsAggregated from '../../../../../assets/screenshots/studio-analytics-aggregated.png';
+import studioAnalyticsCharts from '../../../../../assets/screenshots/studio-analytics-charts.png';
+import studioAnalyticsTrend from '../../../../../assets/screenshots/studio-analytics-trend.png';
+import studioRemoteResultsBeforeSync from '../../../../../assets/screenshots/studio-remote-results-before-sync.png';
+import studioRemoteResultsAfterSync from '../../../../../assets/screenshots/studio-remote-results-after-sync.png';
 
 The `dashboard` command launches a web-based dashboard for browsing evaluation runs, inspecting individual test results, and reviewing scores. It shows both local runs and runs synced from a remote results repository.
 

diff --git a/...eb/src/content/docs/docs/tools/import.mdx → ...c/content/docs/docs/next/tools/import.mdx b/...eb/src/content/docs/docs/tools/import.mdx → ...c/content/docs/docs/next/tools/import.mdx
diff --git a/...b/src/content/docs/docs/tools/inspect.mdx → .../content/docs/docs/next/tools/inspect.mdx b/...b/src/content/docs/docs/tools/inspect.mdx → .../content/docs/docs/next/tools/inspect.mdx
diff --git a/...b/src/content/docs/docs/tools/prepare.mdx → .../content/docs/docs/next/tools/prepare.mdx b/...b/src/content/docs/docs/tools/prepare.mdx → .../content/docs/docs/next/tools/prepare.mdx
diff --git a/...b/src/content/docs/docs/tools/results.mdx → .../content/docs/docs/next/tools/results.mdx b/...b/src/content/docs/docs/tools/results.mdx → .../content/docs/docs/next/tools/results.mdx
@@ -6,8 +6,8 @@ sidebar:
 ---
 
 import { Image } from 'astro:assets';
-import resultsReportOverview from '../../../../assets/screenshots/results-report-overview.png';
-import resultsReportDetails from '../../../../assets/screenshots/results-report-details.png';
+import resultsReportOverview from '../../../../../assets/screenshots/results-report-overview.png';
+import resultsReportDetails from '../../../../../assets/screenshots/results-report-details.png';
 
 The `results` command family works on existing local AgentV run workspaces and `index.jsonl` manifests. Use it after an eval run to inspect failures, validate manifests, export artifact layouts, combine/delete local run workspaces, or generate a shareable HTML report.
 

diff --git a/...web/src/content/docs/docs/tools/trend.mdx → ...rc/content/docs/docs/next/tools/trend.mdx b/...web/src/content/docs/docs/tools/trend.mdx → ...rc/content/docs/docs/next/tools/trend.mdx
diff --git a/.../src/content/docs/docs/tools/validate.mdx → ...content/docs/docs/next/tools/validate.mdx b/.../src/content/docs/docs/tools/validate.mdx → ...content/docs/docs/next/tools/validate.mdx
diff --git a/...ntent/docs/docs/tools/wip-checkpoints.mdx → .../docs/docs/next/tools/wip-checkpoints.mdx b/...ntent/docs/docs/tools/wip-checkpoints.mdx → .../docs/docs/next/tools/wip-checkpoints.mdx
diff --git a/apps/web/src/content/docs/docs/v4.42.4/evaluation/batch-cli.mdx b/apps/web/src/content/docs/docs/v4.42.4/evaluation/batch-cli.mdx
@@ -6,10 +6,6 @@ sidebar:
 slug: docs/v4.42.4/evaluation/batch-cli
 editUrl: false
 pagefind: false
-banner:
-  content: |
-    You are viewing the frozen v4.42.4 docs. Use <a href="/docs/">Canary docs</a> for the current development version.
-
 ---
 
 Batch CLI evaluation handles tools that process multiple inputs at once — bulk classifiers, screening engines, or any runner that reads all tests and outputs results in one pass.

diff --git a/apps/web/src/content/docs/docs/v4.42.4/evaluation/eval-cases.mdx b/apps/web/src/content/docs/docs/v4.42.4/evaluation/eval-cases.mdx
@@ -6,10 +6,6 @@ sidebar:
 slug: docs/v4.42.4/evaluation/eval-cases
 editUrl: false
 pagefind: false
-banner:
-  content: |
-    You are viewing the frozen v4.42.4 docs. Use <a href="/docs/">Canary docs</a> for the current development version.
-
 ---
 
 Tests are individual test entries within an evaluation file. Each test defines input messages, expected outcomes, and optional grader overrides.

diff --git a/apps/web/src/content/docs/docs/v4.42.4/evaluation/eval-files.mdx b/apps/web/src/content/docs/docs/v4.42.4/evaluation/eval-files.mdx
@@ -6,10 +6,6 @@ sidebar:
 slug: docs/v4.42.4/evaluation/eval-files
 editUrl: false
 pagefind: false
-banner:
-  content: |
-    You are viewing the frozen v4.42.4 docs. Use <a href="/docs/">Canary docs</a> for the current development version.
-
 ---
 
 Evaluation files define the test cases, targets, and graders for an evaluation run. AgentV supports two formats: YAML and JSONL.

diff --git a/apps/web/src/content/docs/docs/v4.42.4/evaluation/examples.mdx b/apps/web/src/content/docs/docs/v4.42.4/evaluation/examples.mdx
@@ -6,10 +6,6 @@ sidebar:
 slug: docs/v4.42.4/evaluation/examples
 editUrl: false
 pagefind: false
-banner:
-  content: |
-    You are viewing the frozen v4.42.4 docs. Use <a href="/docs/">Canary docs</a> for the current development version.
-
 ---
 
 This page collects complete eval file examples you can copy and adapt. Each demonstrates a different AgentV pattern.

diff --git a/apps/web/src/content/docs/docs/v4.42.4/evaluation/rubrics.mdx b/apps/web/src/content/docs/docs/v4.42.4/evaluation/rubrics.mdx
@@ -6,10 +6,6 @@ sidebar:
 slug: docs/v4.42.4/evaluation/rubrics
 editUrl: false
 pagefind: false
-banner:
-  content: |
-    You are viewing the frozen v4.42.4 docs. Use <a href="/docs/">Canary docs</a> for the current development version.
-
 ---
 
 Rubrics are defined with `assertions` entries and support binary checklist grading and score-range analytic grading.

diff --git a/apps/web/src/content/docs/docs/v4.42.4/evaluation/running-evals.mdx b/apps/web/src/content/docs/docs/v4.42.4/evaluation/running-evals.mdx
@@ -6,10 +6,6 @@ sidebar:
 slug: docs/v4.42.4/evaluation/running-evals
 editUrl: false
 pagefind: false
-banner:
-  content: |
-    You are viewing the frozen v4.42.4 docs. Use <a href="/docs/">Canary docs</a> for the current development version.
-
 ---
 
 ## Run an Evaluation

diff --git a/apps/web/src/content/docs/docs/v4.42.4/evaluation/sdk.mdx b/apps/web/src/content/docs/docs/v4.42.4/evaluation/sdk.mdx
@@ -6,10 +6,6 @@ sidebar:
 slug: docs/v4.42.4/evaluation/sdk
 editUrl: false
 pagefind: false
-banner:
-  content: |
-    You are viewing the frozen v4.42.4 docs. Use <a href="/docs/">Canary docs</a> for the current development version.
-
 ---
 
 YAML remains AgentV's canonical, portable eval format. The SDK surfaces below are for cases where you want to generate YAML-shaped definitions in code, embed eval runs inside another application, or write executable graders and prompt templates. For authoring helpers, `@agentv/sdk` is AgentV's public lightweight SDK package.

diff --git a/apps/web/src/content/docs/docs/v4.42.4/getting-started/installation.mdx b/apps/web/src/content/docs/docs/v4.42.4/getting-started/installation.mdx
@@ -6,10 +6,6 @@ sidebar:
 slug: docs/v4.42.4/getting-started/installation
 editUrl: false
 pagefind: false
-banner:
-  content: |
-    You are viewing the frozen v4.42.4 docs. Use <a href="/docs/">Canary docs</a> for the current development version.
-
 ---
 
 ## Prerequisites

diff --git a/apps/web/src/content/docs/docs/v4.42.4/getting-started/quickstart.mdx b/apps/web/src/content/docs/docs/v4.42.4/getting-started/quickstart.mdx
@@ -6,10 +6,6 @@ sidebar:
 slug: docs/v4.42.4/getting-started/quickstart
 editUrl: false
 pagefind: false
-banner:
-  content: |
-    You are viewing the frozen v4.42.4 docs. Use <a href="/docs/">Canary docs</a> for the current development version.
-
 ---
 
 Follow these steps to create and run your first evaluation.

diff --git a/apps/web/src/content/docs/docs/v4.42.4/graders/code-graders.mdx b/apps/web/src/content/docs/docs/v4.42.4/graders/code-graders.mdx
@@ -6,10 +6,6 @@ sidebar:
 slug: docs/v4.42.4/graders/code-graders
 editUrl: false
 pagefind: false
-banner:
-  content: |
-    You are viewing the frozen v4.42.4 docs. Use <a href="/docs/">Canary docs</a> for the current development version.
-
 ---
 
 Code graders are scripts that evaluate agent responses deterministically. Write them in any language — Python, TypeScript, Node, or any executable.

diff --git a/apps/web/src/content/docs/docs/v4.42.4/graders/composite.mdx b/apps/web/src/content/docs/docs/v4.42.4/graders/composite.mdx
@@ -6,10 +6,6 @@ sidebar:
 slug: docs/v4.42.4/graders/composite
 editUrl: false
 pagefind: false
-banner:
-  content: |
-    You are viewing the frozen v4.42.4 docs. Use <a href="/docs/">Canary docs</a> for the current development version.
-
 ---
 
 Composite graders combine multiple graders and aggregate their results into a single score. This enables sophisticated evaluation patterns like safety gates, weighted scoring, and conflict resolution.

diff --git a/apps/web/src/content/docs/docs/v4.42.4/graders/custom-assertions.mdx b/apps/web/src/content/docs/docs/v4.42.4/graders/custom-assertions.mdx
@@ -6,10 +6,6 @@ sidebar:
 slug: docs/v4.42.4/graders/custom-assertions
 editUrl: false
 pagefind: false
-banner:
-  content: |
-    You are viewing the frozen v4.42.4 docs. Use <a href="/docs/">Canary docs</a> for the current development version.
-
 ---
 
 Custom assertions let you add evaluation logic that goes beyond built-in types. Define a TypeScript function, drop it in `.agentv/assertions/`, and reference it by name in your YAML eval files.

diff --git a/apps/web/src/content/docs/docs/v4.42.4/graders/custom-graders.mdx b/apps/web/src/content/docs/docs/v4.42.4/graders/custom-graders.mdx
@@ -6,10 +6,6 @@ sidebar:
 slug: docs/v4.42.4/graders/custom-graders
 editUrl: false
 pagefind: false
-banner:
-  content: |
-    You are viewing the frozen v4.42.4 docs. Use <a href="/docs/">Canary docs</a> for the current development version.
-
 ---
 
 AgentV supports multiple grader types that can be combined for comprehensive evaluation.

diff --git a/apps/web/src/content/docs/docs/v4.42.4/graders/execution-metrics.mdx b/apps/web/src/content/docs/docs/v4.42.4/graders/execution-metrics.mdx
@@ -6,10 +6,6 @@ sidebar:
 slug: docs/v4.42.4/graders/execution-metrics
 editUrl: false
 pagefind: false
-banner:
-  content: |
-    You are viewing the frozen v4.42.4 docs. Use <a href="/docs/">Canary docs</a> for the current development version.
-
 ---
 
 AgentV provides built-in graders for checking execution metrics against thresholds. These are useful for enforcing efficiency constraints without writing custom code.

diff --git a/apps/web/src/content/docs/docs/v4.42.4/graders/llm-graders.mdx b/apps/web/src/content/docs/docs/v4.42.4/graders/llm-graders.mdx
@@ -6,10 +6,6 @@ sidebar:
 slug: docs/v4.42.4/graders/llm-graders
 editUrl: false
 pagefind: false
-banner:
-  content: |
-    You are viewing the frozen v4.42.4 docs. Use <a href="/docs/">Canary docs</a> for the current development version.
-
 ---
 
 LLM graders use a language model to evaluate agent responses against custom criteria defined in a prompt file.