@agent-native/core 0.152.0 → 0.153.0

package/corpus/templates/design/.agents/skills/turn-into-app/references/spreadsheet-source.md

@@ -0,0 +1,148 @@
+# Spreadsheet source review
+
+Use this reference after a workbook upload or Google Sheets link is supplied to
+`/turn-into-app`. It defines the bounded review contract before app creation.
+
+## 1. Establish the source boundary
+
+Record the source before interpreting it:
+
+| Field        | Record                                                                            |
+| ------------ | --------------------------------------------------------------------------------- |
+| Source kind  | `xlsx`, `xls`, `csv`, or Google Sheets URL                                        |
+| Provenance   | Original file name or spreadsheet ID and URL; never credentials or workbook bytes |
+| Access       | Upload preview, authenticated provider read, or unavailable                       |
+| Coverage     | Worksheet names, selected range(s), row/column bounds, and sample counts          |
+| Completeness | Complete within the requested bound, partial, truncated, unreadable, or empty     |
+| Refresh      | One-time snapshot or live refreshable source                                      |
+
+For an uploaded XLS/XLSX file, the framework preview contains worksheet names,
+dimensions, and representative displayed values within bounds. It does not
+currently preserve cell fills or font colors in that text preview. Treat the
+original workbook as the formatting authority only when a tool actually returns
+cell formatting metadata. Never describe a text-only upload as style-verified.
+
+For a Google Sheets URL:
+
+1. Parse the spreadsheet ID and preserve the original URL as provenance.
+2. Use the authenticated `google_drive` provider path. Inspect
+   `provider-api-catalog` first, use `provider-api-docs` if the endpoint or
+   fields are uncertain, and then call `provider-api-request`.
+3. Read spreadsheet metadata and only bounded worksheet/range data. Request
+   formatting metadata when the I/O decision depends on colors, including
+   `userEnteredFormat.backgroundColor` and
+   `userEnteredFormat.textFormat.foregroundColor` where the provider supports
+   it. Do not use a public export URL to bypass access.
+4. Preserve the spreadsheet ID, worksheet title, A1 range, account/connection
+   choice without secrets, row limits, and refresh behavior in the brief.
+
+Keep provider responses bounded. For large sheets, stage or save the response
+and reduce it with the available dataset/code tools. A failed page, truncated
+response, or unavailable connection is not an empty sheet.
+
+## 2. Infer cells and ranges, then show the evidence
+
+Classify source material into three separate buckets. Include representative
+cell addresses or ranges and the evidence behind each classification.
+
+| Bucket             | Default signal                                                                                                     | App treatment                                                          |
+| ------------------ | ------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------- |
+| Inputs             | Yellow cell background, editable assumptions, user-entered constants, or labels such as `assumption` / `driver`    | Editable controls or bounded source parameters                         |
+| Outputs            | Blue text, formula-derived result cells, summary blocks, or labels such as `forecast` / `recommendation`           | Read-only results, charts, recommendations, exports, or review actions |
+| Static historicals | Black text used intentionally for prior-period/source records, raw rows, or labels such as `actual` / `historical` | Read-only context; never turn into editable inputs by default          |
+
+These are conventions, not permission to guess. A default black font with no
+explicit style metadata is not enough to label a range as historical. Resolve
+conflicts using labels, formulas, neighboring headers, repeated patterns, and
+the user's stated goal. If the evidence still conflicts, lower confidence and
+ask the user to confirm the proposed mapping.
+
+Keep source cells and app behavior distinct:
+
+- `Source inputs` are the workbook cells or ranges the user is expected to
+  change or refresh.
+- `Source outputs` are the workbook cells or ranges the source already derives
+  or presents.
+- `Static historicals` are context the app may filter, compare, or summarize,
+  but should not edit.
+- `App outputs` are the new app's visible results, saved records, exports,
+  alerts, or downstream handoffs. Do not invent these until the repeatable job
+  or user confirmation makes them clear.
+
+## 3. Offer candidate apps, not a tab dump
+
+Group related worksheets into candidate repeatable jobs. A candidate should
+have a recognizable user, trigger, inputs, transformation or judgment, and
+outputs. Utility tabs such as lookups, raw imports, instructions, pivots, and
+calculation helpers can support a candidate without becoming destinations.
+
+Present a compact Q&A review with multi-select options. In generated app code,
+use `askUserQuestion` from `@agent-native/core/client/agent-chat` with
+`allowMultiple: true`, stable candidate IDs as option values, and
+`allowFreeText: true` for corrections. It renders inline in the agent panel;
+do not build a custom modal. Each option should fit in a scannable row or
+choice card:
+
+```text
+Candidate: Pipeline forecast
+Uses: Assumptions, Historical Pipeline, Forecast
+Inputs: yellow assumptions in Assumptions!B4:B12 (high confidence)
+Outputs: blue forecast summary in Forecast!B3:H10 (medium confidence)
+Historical context: Historical Pipeline!A1:K500
+Question: Confirm that forecast assumptions should be editable?
+```
+
+Mark the strongest recommendation with `recommended: true`, but do not silently
+select it. Let the user select none, one, or several candidates, correct a
+proposed tab/range, or answer the unresolved question. Keep each question to
+2-4 grouped candidate jobs; for a larger workbook, group related tabs into
+jobs rather than showing a tab dump or asking a separate question for every
+worksheet. If there is only one high-confidence candidate, keep the review
+compact and ask for confirmation only when the I/O mapping or source access is
+unclear.
+
+When several candidates are selected, pass a stable candidate ID, display name,
+source worksheet/ranges, I/O mapping, confidence, and confirmation status for
+each. The generated app should expose them as separate named left-navigation
+destinations or tabs, not merge them into an opaque dashboard and not create a
+separate workspace app for every worksheet.
+
+## 4. Confirm before building or publishing
+
+The confirmation view is a source-integrity checkpoint, not a product-design
+questionnaire. Show:
+
+- the source file or spreadsheet ID and snapshot/live choice;
+- selected candidate destinations and their source tabs/ranges;
+- editable inputs, read-only outputs, and static historical context;
+- the evidence and confidence for each mapping;
+- truncation, unreadable, missing-connection, and refresh limitations;
+- the app outputs/actions that will be created.
+
+Use clear actions such as `Confirm and build`, `Edit mapping`, and `Use a
+different source`. If the host has a structured question or multi-select UI,
+use it. Otherwise, ask one concise assistant message that presents the same
+options and requires an explicit confirmation/correction before handoff.
+
+After confirmation, the online host may call
+`start-workspace-app-creation`; the Builder run itself remains autonomous and
+must record any remaining non-blocking assumptions. In a local generated app,
+persist the confirmation state in SQL/application state and keep the user on
+the review surface while the agent builds. Never claim a full import, live
+refresh, or output write until the corresponding source/action has succeeded.
+
+## 5. Failure and recovery states
+
+Keep these states distinct in the review and in the handoff:
+
+- `unreadable` - parser/provider could not read the source;
+- `partial` - only some worksheets, ranges, rows, or pages were read;
+- `truncated` - the bounded preview ended before full coverage;
+- `empty` - the requested readable range contains no values;
+- `not-connected` - authenticated Google access is required but unavailable;
+- `confirmed` - the user approved the candidate and I/O mapping.
+
+For unreadable or not-connected sources, request a CSV/XLSX export or the
+required connection. For partial or truncated sources, continue only with a
+clearly bounded snapshot or ask for a narrower range. Do not coerce any of
+these states into a successful empty source.

package/corpus/templates/design/.agents/skills/workspace-conventions/SKILL.md

@@ -0,0 +1,93 @@
+---
+name: workspace-conventions
+description: >-
+  Shared conventions for a multi-app Agent Native workspace: finding
+  version-matched framework docs and source, shared vs app-owned code, file and
+  blob storage, env and secrets, agent scratch files, and Dispatch Resources.
+  Use when working across workspace apps, storing files or credentials, or
+  looking up framework APIs.
+scope: dev
+---
+
+# Workspace Conventions
+
+The long-form detail behind the workspace `AGENTS.md` core rules. Read this
+before adding shared code, storing files or secrets, creating workspace
+resources, or looking up framework APIs.
+
+## Framework Docs Lookup
+
+Read `agent-native-docs` for the lookup workflow (`framework-search` first, then
+the focused `docs-search` / `source-search` readers, and the `rg` fallback).
+
+The workspace-specific slugs it does not list are `workspace` and
+`multi-app-workspace`. Feature flags and other specialized workflows are
+optional; read their skill only when the app uses them. Use package docs for framework APIs,
+the package corpus for reusable framework/template patterns, and this
+`AGENTS.md` plus `.agents/skills/` for workspace-specific conventions.
+
+Before building common workspace or agent UI, read `agent-native-toolkit` to
+inventory existing public kits and installed package seams. Read
+`customizing-agent-native` before adapting shared UI. Use the supported
+ladder: configure → compose → eject the smallest unit → propose a shared seam.
+Preview before `--apply`, commit `agent-native.ejections.json`, and never edit
+`node_modules` or eject protected runtime contracts.
+
+## Shared Conventions
+
+- All AI/LLM behavior goes through the app's agent chat. UI and server code
+  must not call model providers, AI SDK `generateText()` / `streamText()`, or
+  other inline LLM APIs directly. Use `sendToAgentChat()` for local app-agent
+  work, including hidden `context` and `submit: false` prefill/review flows.
+  Keep actions deterministic and focused. If a workflow is framed as research,
+  analysis, generation, recommendation, or synthesis, let the agent
+  orchestrate provider/data actions in the open AgentSidebar instead of hiding
+  the work in one opaque action or a separate follow-up textbox.
+  Only use `useAgentChatContext`, `setAgentChatContextItem`,
+  `listAgentChatContext`, `removeAgentChatContextItem`, and
+  `clearAgentChatContext` when UI needs two-way sync with staged context chips.
+  Read `.agents/skills/delegate-to-agent/SKILL.md` before building agent-driven
+  UI or "AI" features.
+- Put shared code in `packages/shared` only when multiple apps need it.
+- Keep app-specific screens, actions, state, and skills inside `apps/<app>`.
+- SQL is for structured records, metadata, references, and searchable text. Store
+  large files/blob payloads (base64, `data:` URLs, images, video/audio, PDFs,
+  ZIPs, screenshots, thumbnails, session replay chunks) in configured file/blob
+  storage and persist only URLs, ids, or handles.
+- Store shared runtime configuration in the workspace root `.env`; use
+  `apps/<app>/.env` only for app-specific overrides. Never hardcode API keys,
+  tokens, webhook URLs, signing secrets, private Builder/internal data, customer
+  data, or credential-looking literals in source, docs, prompts, fixtures,
+  application state, action responses, or generated app content. Use
+  secrets/OAuth/runtime configuration and obvious placeholders in examples.
+- Each app deploys its own `/*` page function, and that function ships whatever
+  the app's server bundle depends on — including a dependency only a background
+  job uses. Before an app takes on a heavy runtime (headless browser, ffmpeg,
+  media processing, ML), read `.agents/skills/performance/SKILL.md` §9 and keep
+  that work in a background function or job. A dependency belonging to one app
+  does not belong in `packages/shared`.
+- Prefer framework defaults until the workspace has a real custom rule,
+  component, plugin, action, or skill to share.
+- Keep the Workspace files view for user-authored or user-requested resources.
+  Agents may create hidden `agent_scratch` resources for temporary working
+  notes, scripts, task plans, or intermediate outputs, but should promote them
+  to normal workspace visibility only when the user explicitly asks to keep or
+  manage the file.
+- Runtime-editable global resources can be managed from Dispatch Resources.
+  Use `AGENTS.md` or `instructions/<slug>.md` for always-on guardrails,
+  `skills/<slug>/SKILL.md` for workspace skills, `context/<slug>.md` for
+  personas/positioning/messaging/company facts/brand guidelines, and
+  `agents/<slug>.md` for custom agent profiles. Scope them to All apps when
+  every workspace app should inherit them. All-app resources are inherited at
+  runtime; do not copy or sync them into individual apps.
+
+## Related Skills
+
+- **adding-workspace-apps** — Creating and mounting a new app under `apps/`.
+- **agent-native-docs** — The full docs and source-corpus lookup workflow.
+- **agent-native-toolkit** — Inventory of shared workspace and agent UI.
+- **customizing-agent-native** — The configure → compose → eject ladder.
+- **delegate-to-agent** — Routing every AI feature through the agent chat.
+- **performance** — Load cost, and (§9) cold-start artifact size per app.
+- **secrets** — Registering API keys and service credentials.
+- **storing-data** — Where structured data and large payloads belong.

package/corpus/templates/design/actions/index-design-system-with-builder.ts

@@ -10,6 +10,7 @@ import {
 import { z } from "zod";
 
 import { upsertBuilderProxyDesignSystem } from "../server/lib/builder-design-system-proxy.js";
+import importGithub from "./import-github.js";
 
 const codeFileSchema = z.object({
   filename: z.string().trim().min(1).describe("File name or relative path"),
@@ -36,6 +37,7 @@ export default defineAction({
   description:
     "Start Builder DSI design-system indexing from connected code, a GitHub repository, code/design files, and optional design.md guidance. " +
     "Use this instead of local import-code/import-github when the user wants a reusable brand kit or design system. " +
+    "Private GitHub repositories use the saved GITHUB_TOKEN server-side; the token is never sent to Builder or exposed to the client. " +
     "Requires Builder.io to be connected (free tier available); Builder owns the indexed design-system docs, generated guidance, token/component extraction, and job state.",
   schema: z.object({
     projectName: z
@@ -73,8 +75,17 @@ export default defineAction({
     codeFiles,
     designMd,
   }) => {
+    const githubImport = githubRepoUrl
+      ? await importGithub.run({ repoUrl: githubRepoUrl })
+      : null;
+    const githubFiles = githubImport?.rawFiles
+      ? Object.entries(githubImport.rawFiles).map(([filename, content]) => ({
+          filename,
+          content,
+        }))
+      : [];
     const files = buildBuilderDesignSystemIndexFiles({
-      codeFiles,
+      codeFiles: [...(codeFiles ?? []), ...githubFiles],
       designMd,
       // Agent action payloads intentionally stay at the core 2 MB inline
       // budget. Fail loudly instead of silently dropping a larger `.fig`;
@@ -84,7 +95,10 @@ export default defineAction({
     const result = await startBuilderDesignSystemIndex({
       projectName,
       description,
-      githubRepoUrl,
+      // Upload token-authenticated GitHub files as Builder file sources. If
+      // there was nothing relevant to upload, retain the public-repo source
+      // so public repositories still work without a saved token.
+      githubRepoUrl: githubFiles.length > 0 ? undefined : githubRepoUrl,
       connectedProjectId,
       files,
     });

package/corpus/templates/design/app/components/design-system/ProductionDesignSystemShowcase.tsx

@@ -14,12 +14,6 @@ import {
   type ProductionDesignSystemTemplate,
 } from "../../../shared/design-system-templates";
 
-const descriptionKeys: Record<DesignSystemTemplateId, string> = {
-  "material-3": "designSystems.showcase.descriptions.material3",
-  "carbon-white": "designSystems.showcase.descriptions.carbon",
-  "primer-light": "designSystems.showcase.descriptions.primer",
-};
-
 export function ProductionDesignSystemShowcase({
   pendingTemplateId,
   onAdd,
@@ -31,7 +25,7 @@ export function ProductionDesignSystemShowcase({
 
   return (
     <section aria-labelledby="production-design-systems-heading">
-      <div className="mb-4 flex max-w-2xl items-start gap-3">
+      <div className="mb-4 flex items-center gap-3">
         <div className="mt-0.5 flex size-8 shrink-0 items-center justify-center rounded-lg border border-border bg-muted/40">
           <IconRosetteDiscountCheck className="size-4 text-muted-foreground" />
         </div>
@@ -42,13 +36,10 @@ export function ProductionDesignSystemShowcase({
           >
             {t("designSystems.showcase.title")}
           </h2>
-          <p className="mt-1 text-sm leading-relaxed text-muted-foreground">
-            {t("designSystems.showcase.description")}
-          </p>
         </div>
       </div>
 
-      <div className="grid grid-cols-1 gap-4 md:grid-cols-3">
+      <div className="grid grid-cols-[repeat(auto-fit,minmax(230px,1fr))] gap-3">
         {PRODUCTION_DESIGN_SYSTEM_TEMPLATES.map((template) => {
           const isPending = pendingTemplateId === template.id;
           return (
@@ -57,7 +48,7 @@ export function ProductionDesignSystemShowcase({
               className="overflow-hidden rounded-xl border border-border bg-card"
             >
               <ProductionSystemPreview template={template} />
-              <div className="p-4">
+              <div className="p-3">
                 <div className="flex items-center justify-between gap-3">
                   <span className="text-[11px] font-medium uppercase tracking-[0.12em] text-muted-foreground">
                     {template.organization}
@@ -66,13 +57,10 @@ export function ProductionDesignSystemShowcase({
                     {template.version}
                   </span>
                 </div>
-                <h3 className="mt-3 text-sm font-semibold text-foreground">
+                <h3 className="mt-2 text-sm font-semibold text-foreground">
                   {template.title}
                 </h3>
-                <p className="mt-1 min-h-16 text-xs leading-relaxed text-muted-foreground">
-                  {t(descriptionKeys[template.id])}
-                </p>
-                <div className="mt-4 flex items-center gap-2">
+                <div className="mt-3 flex items-center gap-2">
                   <Button
                     type="button"
                     size="sm"
@@ -108,7 +96,7 @@ export function ProductionDesignSystemShowcase({
                     </a>
                   </Button>
                 </div>
-                <p className="mt-3 text-[10px] text-muted-foreground/70">
+                <p className="mt-2 text-[10px] text-muted-foreground/70">
                   {t("designSystems.showcase.license", {
                     license: template.license,
                   })}

package/corpus/templates/design/app/i18n/en-US.ts

@@ -46,7 +46,7 @@ const messages = {
     applyFeedbackFailed: "Could not apply review feedback",
     sendToAgentFailed: "Could not send this thread to the agent",
     shareLinkDescription:
-      "Anyone with this link can view the design. Signed-in reviewers can comment.",
+      "Anyone with this link can view the design. Signed-in commenters can comment.",
     presentComments: "Comments",
     presentCommentMode: "Comment mode",
     closeComments: "Close comments",

package/corpus/templates/design/app/i18n-data.ts

@@ -1472,6 +1472,8 @@ const enUS = {
       "Connect from a website, code, files, or an existing design system.",
     chooseSourcePrompt: "Choose one source to configure",
     continue: "Continue to generation",
+    starting: "Starting...",
+    githubIndexStarted: "GitHub indexing started",
     title: "Set up your design system",
     description:
       "Connect Figma, code, and optional design.md guidance through Builder DSI. More context gives the agent a more accurate system.",
@@ -1532,6 +1534,8 @@ const enUS = {
       enterGithub: "Enter a GitHub repository URL before adding it.",
       githubUrl:
         "Use a full GitHub repository URL, like https://github.com/org/repo.",
+      githubIndex:
+        "Could not start GitHub indexing. Check your Builder connection and repository access.",
       noSources: "Add at least one source before generating a design system.",
     },
     sections: {
@@ -1947,6 +1951,8 @@ const designLocaleOverrides = {
       otherSourcesDescription: "从网站、代码、文件或现有设计系统连接。",
       chooseSourcePrompt: "选择一个来源进行配置",
       continue: "继续生成",
+      starting: "正在启动…",
+      githubIndexStarted: "GitHub 索引已开始",
       title: "设置您的设计系统",
       description:
         "通过 Builder DSI 连接 Figma、代码和可选的 design.md 指引。上下文越多，代理得到的系统越准确。",
@@ -1999,6 +2005,8 @@ const designLocaleOverrides = {
         enterGithub: "在添加之前输入 GitHub 存储库 URL。",
         githubUrl:
           "使用完整的 GitHub 存储库 URL，例如 https://github.com/org/repo。",
+        githubIndex:
+          "无法启动 GitHub 索引。请检查 Builder 连接和仓库访问权限。",
         noSources: "在生成设计系统之前至少添加一个源。",
       },
       sections: {
@@ -2356,6 +2364,8 @@ const designLocaleOverrides = {
         "Conecta desde un sitio web, código, archivos o un sistema de diseño existente.",
       chooseSourcePrompt: "Elige una fuente para configurar",
       continue: "continuar con la generación",
+      starting: "Iniciando…",
+      githubIndexStarted: "La indexación de GitHub ha comenzado",
       title: "Configure su sistema de diseño",
       description:
         "Conecta Figma, código y guía opcional de design.md mediante Builder DSI. Más contexto le da al agente un sistema más preciso.",
@@ -2418,6 +2428,8 @@ const designLocaleOverrides = {
         enterGithub: "Ingrese un repositorio GitHub URL antes de agregarlo.",
         githubUrl:
           "Utilice un repositorio GitHub completo URL, como https://github.com/org/repo.",
+        githubIndex:
+          "No se pudo iniciar la indexación de GitHub. Comprueba la conexión de Builder y el acceso al repositorio.",
         noSources:
           "Agregue al menos una fuente antes de generar un sistema de diseño.",
       },
@@ -2787,6 +2799,8 @@ const designLocaleOverrides = {
         "Connectez-vous depuis un site web, du code, des fichiers ou un système de conception existant.",
       chooseSourcePrompt: "Choisissez une source à configurer",
       continue: "Continuer jusqu'à la génération",
+      starting: "Démarrage…",
+      githubIndexStarted: "L’indexation GitHub a démarré",
       title: "Configurez votre système de conception",
       description:
         "Connectez Figma, le code et les consignes design.md facultatives via Builder DSI. Plus le contexte est riche, plus le système de l’agent est précis.",
@@ -2849,6 +2863,8 @@ const designLocaleOverrides = {
         enterGithub: "Entrez un référentiel GitHub URL avant de l'ajouter.",
         githubUrl:
           "Utilisez un référentiel GitHub complet URL, comme https://github.com/org/repo.",
+        githubIndex:
+          "Impossible de démarrer l’indexation GitHub. Vérifiez la connexion à Builder et l’accès au dépôt.",
         noSources:
           "Ajoutez au moins une source avant de générer un système de conception.",
       },
@@ -3218,6 +3234,8 @@ const designLocaleOverrides = {
         "Von einer Website, Code, Dateien oder einem vorhandenen Designsystem verbinden.",
       chooseSourcePrompt: "Quelle zum Konfigurieren auswählen",
       continue: "Weiter zur Generation",
+      starting: "Wird gestartet…",
+      githubIndexStarted: "GitHub-Indizierung gestartet",
       title: "Richten Sie Ihr Designsystem ein",
       description:
         "Verbinde Figma, Code und optionale design.md-Anweisungen über Builder DSI. Mehr Kontext gibt dem Agenten ein genaueres System.",
@@ -3282,6 +3300,8 @@ const designLocaleOverrides = {
           "Geben Sie ein GitHub-Repository URL ein, bevor Sie es hinzufügen.",
         githubUrl:
           "Verwenden Sie ein vollständiges GitHub-Repository URL, wie https://github.com/org/repo.",
+        githubIndex:
+          "GitHub-Indizierung konnte nicht gestartet werden. Prüfe die Builder-Verbindung und den Repository-Zugriff.",
         noSources:
           "Fügen Sie mindestens eine Quelle hinzu, bevor Sie ein Designsystem erstellen.",
       },
@@ -3649,6 +3669,8 @@ const designLocaleOverrides = {
         "Webサイト、コード、ファイル、または既存のデザインシステムから接続します。",
       chooseSourcePrompt: "設定するソースを選択",
       continue: "世代を継続する",
+      starting: "開始中…",
+      githubIndexStarted: "GitHub のインデックス作成を開始しました",
       title: "デザインシステムをセットアップする",
       description:
         "Figma、コード、任意の design.md ガイドを Builder DSI で接続します。コンテキストが多いほど、エージェントのシステムは正確になります。",
@@ -3711,6 +3733,8 @@ const designLocaleOverrides = {
         enterGithub: "追加する前に、GitHub リポジトリ URL を入力します。",
         githubUrl:
           "https://github.com/org/repo など、完全な GitHub リポジトリ URL を使用します。",
+        githubIndex:
+          "GitHub のインデックス作成を開始できませんでした。Builder の接続とリポジトリへのアクセスを確認してください。",
         noSources:
           "デザイン システムを生成する前に、少なくとも 1 つのソースを追加します。",
       },
@@ -4075,6 +4099,8 @@ const designLocaleOverrides = {
         "웹사이트, 코드, 파일 또는 기존 디자인 시스템에서 연결합니다.",
       chooseSourcePrompt: "구성할 소스 선택",
       continue: "세대를 이어가다",
+      starting: "시작 중…",
+      githubIndexStarted: "GitHub 인덱싱이 시작되었습니다",
       title: "디자인 시스템 설정",
       description:
         "Figma, 코드, 선택적 design.md 지침을 Builder DSI로 연결하세요. 맥락이 많을수록 에이전트의 시스템이 더 정확해집니다.",
@@ -4133,6 +4159,8 @@ const designLocaleOverrides = {
         enterGithub: "추가하기 전에 GitHub 저장소 URL를 입력하세요.",
         githubUrl:
           "https://github.com/org/repo와 같은 전체 GitHub 저장소 URL를 사용하세요.",
+        githubIndex:
+          "GitHub 인덱싱을 시작할 수 없습니다. Builder 연결과 저장소 접근 권한을 확인하세요.",
         noSources: "디자인 시스템을 생성하기 전에 소스를 하나 이상 추가하세요.",
       },
       sections: {
@@ -4495,6 +4523,8 @@ const designLocaleOverrides = {
         "Conecte-se de um site, código, arquivos ou um sistema de design existente.",
       chooseSourcePrompt: "Escolha uma fonte para configurar",
       continue: "Continuar para a geração",
+      starting: "Iniciando…",
+      githubIndexStarted: "Indexação do GitHub iniciada",
       title: "Configure seu sistema de design",
       description:
         "Conecte Figma, código e orientações opcionais de design.md pelo Builder DSI. Mais contexto dá ao agente um sistema mais preciso.",
@@ -4556,6 +4586,8 @@ const designLocaleOverrides = {
         enterGithub: "Insira um repositório GitHub URL antes de adicioná-lo.",
         githubUrl:
           "Use um repositório GitHub completo URL, como https://github.com/org/repo.",
+        githubIndex:
+          "Não foi possível iniciar a indexação do GitHub. Verifique a conexão do Builder e o acesso ao repositório.",
         noSources:
           "Adicione pelo menos uma fonte antes de gerar um sistema de design.",
       },
@@ -4921,6 +4953,8 @@ const designLocaleOverrides = {
         "वेबसाइट, कोड, फ़ाइलों या मौजूदा डिज़ाइन सिस्टम से कनेक्ट करें।",
       chooseSourcePrompt: "कॉन्फ़िगर करने के लिए एक स्रोत चुनें",
       continue: "पीढ़ी तक जारी रखें",
+      starting: "शुरू हो रहा है…",
+      githubIndexStarted: "GitHub इंडेक्सिंग शुरू हो गई",
       title: "अपना डिज़ाइन सिस्टम सेट करें",
       description:
         "Figma, कोड और वैकल्पिक design.md मार्गदर्शन को Builder DSI से कनेक्ट करें. अधिक संदर्भ एजेंट को अधिक सटीक सिस्टम देता है.",
@@ -4977,6 +5011,8 @@ const designLocaleOverrides = {
         enterGithub: "इसे जोड़ने से पहले एक GitHub रिपॉजिटरी URL दर्ज करें।",
         githubUrl:
           "https://github.com/org/repo जैसे पूर्ण GitHub रिपॉजिटरी URL का उपयोग करें।",
+        githubIndex:
+          "GitHub इंडेक्सिंग शुरू नहीं हो सकी। Builder कनेक्शन और रिपॉजिटरी एक्सेस जाँचें।",
         noSources: "डिज़ाइन सिस्टम तैयार करने से पहले कम से कम एक स्रोत जोड़ें।",
       },
       sections: {
@@ -5337,6 +5373,8 @@ const designLocaleOverrides = {
         "الاتصال من موقع ويب أو رمز أو ملفات أو نظام تصميم موجود.",
       chooseSourcePrompt: "اختر مصدرًا لتهيئته",
       continue: "الاستمرار في الجيل",
+      starting: "جارٍ البدء…",
+      githubIndexStarted: "بدأت فهرسة GitHub",
       title: "قم بإعداد نظام التصميم الخاص بك",
       description:
         "اربط Figma والكود وإرشادات design.md الاختيارية عبر Builder DSI. كلما زاد السياق، حصل الوكيل على نظام أدق.",
@@ -5395,6 +5433,8 @@ const designLocaleOverrides = {
         enterGithub: "أدخل مستودع GitHub URL قبل إضافته.",
         githubUrl:
           "استخدم مستودع GitHub الكامل URL، مثل https://github.com/org/repo.",
+        githubIndex:
+          "تعذر بدء فهرسة GitHub. تحقق من اتصال Builder ومن صلاحية الوصول إلى المستودع.",
         noSources: "أضف مصدرًا واحدًا على الأقل قبل إنشاء نظام التصميم.",
       },
       sections: {