@agent-native/core 0.84.1 → 0.84.2

package/corpus/README.md

@@ -28,4 +28,4 @@ rg -n "defineAction|useActionQuery" node_modules/@agent-native/core/corpus
 ## Generated Counts
 
 - core files: 2043
-- template files: 4895
+- template files: 4902

package/corpus/core/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @agent-native/core
 
+## 0.84.2
+
+### Patch Changes
+
+- 3ff4f55: Extend Builder gateway timeouts for local and background agent-chat runs, and surface recoverable gateway timeout failures instead of silently retrying activity-only tool preparation loops.
+- 3ff4f55: Allow scoped chat surfaces to hide the composer scope badge while keeping thread context attached.
+
 ## 0.84.1
 
 ### Patch Changes

package/corpus/core/docs/design/durable-agent-runs.md

@@ -83,10 +83,11 @@ terminate with an untruthful "done" state.
 not buy more time — it just converts a graceful hand-off into a hard kill. The
 walls, in order:
 
-1. **Builder model gateway hard cap — ~45s.**
-   `MAX_BUILDER_GATEWAY_TIMEOUT_MS = 45_000` in
-   `packages/core/src/agent/engine/builder-engine.ts`. A single model call is
-   killed at the gateway after 45s. **Not raisable** by the framework.
+1. **Builder model gateway foreground cap — ~45s.**
+   Hosted foreground calls keep a 45s cap in
+   `packages/core/src/agent/engine/builder-engine.ts`. Local/non-hosted and
+   proven background-function calls use the longer background-style cap because
+   they are not constrained by the synchronous function wall.
 2. **Serverless function kill — ~60–65s.** The hosting function is terminated
    shortly after; the heartbeat then reaps the run row as `stale_run`.
 
@@ -366,8 +367,8 @@ The whole `auto_continue` / 40s soft-timeout dance exists to stay under the
 **serverless function wall** (~60–65s synchronous on Netlify), not under any
 model limit. Evidence:
 
-- `builder-engine.ts:62` `MAX_LOCAL_BUILDER_GATEWAY_TIMEOUT_MS = 180_000`
-  (3 min) is allowed locally; the run loop has no inherent reason to stop at 40s.
+- `builder-engine.ts` allows the long background gateway cap in local/non-hosted
+  runs; the run loop has no inherent reason to stop at 40s.
 - `run-manager.ts:58,68` `DEFAULT_HOSTED_RUN_SOFT_TIMEOUT_MS` /
   `HOSTED_SOFT_TIMEOUT_CEILING_MS = 40_000` are pinned just under the function
   wall, and `templates/brain/netlify.toml` sets `[functions."*"] timeout = 75`.
@@ -379,10 +380,9 @@ function there is no ~60s wall, so:
 
 - The agent loop can run for minutes in a single invocation with **few or no
   `auto_continue` continuations**.
-- The per-model-call gateway cap (`MAX_BUILDER_GATEWAY_TIMEOUT_MS = 45_000`,
-  `builder-engine.ts:60`) still applies per call — see
-  [Per-model-call gateway cap](#per-model-call-gateway-cap) — but the _run_ is no
-  longer chopped into 40s chunks.
+- The foreground hosted per-model-call gateway cap still applies per call — see
+  [Per-model-call gateway cap](#per-model-call-gateway-cap) — but the _run_ is
+  no longer chopped into 40s chunks.
 
 This is exactly the Layer 1 worker with a concrete long-lived host: Netlify is
 the durable worker, reached through the existing self-dispatch primitive — the
@@ -527,29 +527,27 @@ Minimal client change, because the reconnect machinery already exists:
 
 ## Per-model-call gateway cap
 
-Even in a 15-min function, a _single_ model call is still capped by the Builder
-gateway: `MAX_BUILDER_GATEWAY_TIMEOUT_MS = 45_000` (`builder-engine.ts:60`),
-resolved by `getBuilderGatewayTimeoutMs()` (`:770`) /
-`resolveMaxBuilderGatewayTimeoutMs()` (`:758`). Locally the cap is already
-`180_000` (`:62`) when the gateway base URL is localhost.
+Builder gateway calls now use a runtime-aware cap. Hosted foreground calls keep
+the 45s cap so the synchronous function can still checkpoint before its hard
+wall. Local/non-hosted runs use a longer local cap, and proven Netlify
+background-function runs may use a background cap below the 15-minute function
+wall. The run-manager's 13-minute background soft-timeout should fire before
+the gateway cap in normal durable background operation.
 
 Options, in scope-order:
 
-1. **In scope / safe now:** keep the 45s per-call cap. A 15-min function makes
-   _many_ 45s calls; the cap bounds one call, not the run. This alone delivers
-   the goal (long multi-step runs finish) with **zero gateway changes**.
-2. **Flag, out of scope until confirmed:** raise the per-call cap toward 180s in
-   the background context. `getBuilderGatewayTimeoutMs()` already honors
-   `AGENT_NATIVE_BUILDER_GATEWAY_TIMEOUT_MS`, but it is hard-clamped to
-   `resolveMaxBuilderGatewayTimeoutMs()` = 45s for non-localhost gateways. Raising
-   it requires the **hosted Builder gateway to actually allow >45s upstream** —
-   unverified, and not the framework's call. Until confirmed, do not raise it.
-3. **Escape hatch:** a direct Anthropic engine (no Builder gateway) has no 45s
-   cap, so a single very long call could use it. Out of scope for this change;
-   note it as the lever if a single model call truly needs >45s.
-
-**Recommendation:** ship with option 1. The win is removing the _run-level_
-ceiling; the per-call cap is orthogonal and rarely the binding constraint.
+1. **Foreground hosted:** keep the 45s cap. The synchronous function wall is the
+   constraint, and a larger cap would turn graceful checkpointing into a hard
+   platform kill.
+2. **Local/non-hosted:** allow longer calls by default. Local development should
+   not inherit a serverless wall it does not have.
+3. **Durable background:** allow longer calls only when the runtime proves it is
+   inside the emitted background function. Keep the cap below 15 minutes and
+   above the 13-minute run soft-timeout so background checkpointing still owns
+   logical-turn continuation.
+
+**Recommendation:** preserve this split. Do not raise the foreground cap; use
+durable background for long-running tool-input generation.
 
 ## Idempotency / dedup
 
@@ -626,7 +624,8 @@ only): foreground handler inserts the run row, dispatches, returns the SSE
 stream from `subscribeToRun`. The background `_process-run` claims the run and
 calls the same `startRun` + `runAgentLoop` the inline path uses, with
 `softTimeoutMs ≈ 13min` (new `backgroundFunction` option in
-`resolveRunSoftTimeoutMs`). Per-call gateway cap stays at 45s (option 1).
+`resolveRunSoftTimeoutMs`). Builder gateway calls use the background cap only
+when the worker proves it is inside the emitted background function.
 **Done when:** a long multi-step turn that thrashes today completes in one
 background invocation with zero `auto_continue`, events streaming to the client
 via the SQL-poll path, terminal `done` persisted.
@@ -645,10 +644,10 @@ dispatches, and background→background `auto_continue` chaining for the rare
 > 13-min turn (mirror `agent-teams.ts:1886`). Internal checkpointing (Option A)
 > for monotonic progress across any continuation.
 
-**Slice 4 (optional, separate decision) — raise the per-call gateway cap.**
-Only after confirming the hosted Builder gateway accepts >45s upstream; wire
-`AGENT_NATIVE_BUILDER_GATEWAY_TIMEOUT_MS` through with a background-context max.
-Out of scope until that confirmation exists.
+**Slice 4 — foreground remains capped.**
+Do not raise the hosted foreground per-call gateway cap. Any future tuning
+should stay in the local/background timeout regime unless the synchronous
+platform wall changes.
 
 ## Open risks / unknowns
 

package/corpus/core/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@agent-native/core",
-  "version": "0.84.1",
+  "version": "0.84.2",
   "description": "Framework for agent-native application development — where AI agents and UI share SQL state, actions, and context",
   "homepage": "https://github.com/BuilderIO/agent-native#readme",
   "bugs": {

package/corpus/core/src/agent/engine/builder-engine.ts

@@ -24,6 +24,7 @@ import {
   normalizeReasoningEffortForModel,
   type ReasoningEffort,
 } from "../../shared/reasoning-effort.js";
+import { isInBackgroundFunctionRuntime } from "../durable-background.js";
 import { BUILDER_MODEL_CONFIG } from "../model-config.js";
 import { getBuilderGatewayRequestHeaders } from "./builder-gateway-headers.js";
 import {
@@ -53,13 +54,20 @@ export const BUILDER_CAPABILITIES: EngineCapabilities = {
 
 export const BUILDER_SUPPORTED_MODELS = BUILDER_MODEL_CONFIG.supportedModels;
 
-// Keep the gateway timeout below the hosted run soft timeout so the agent loop
-// can append a continuation and persist terminal state before serverless hosts
-// (Netlify synchronous Functions are 60s) hard-kill the invocation.
+// Keep the foreground hosted gateway timeout below the synchronous serverless
+// wall so the agent loop can append a continuation and persist terminal state
+// before the host hard-kills the invocation.
 const DEFAULT_BUILDER_GATEWAY_TIMEOUT_MS = 45_000;
-const MAX_BUILDER_GATEWAY_TIMEOUT_MS = 45_000;
-/** Local ai-services has no serverless wall; allow longer streams in dev. */
-const MAX_LOCAL_BUILDER_GATEWAY_TIMEOUT_MS = 180_000;
+const MAX_HOSTED_FOREGROUND_BUILDER_GATEWAY_TIMEOUT_MS = 45_000;
+/**
+ * Netlify background functions have a 15-minute wall. Keep the Builder gateway
+ * ceiling below that, but above the run-manager's 13-minute soft-timeout so
+ * durable background runs checkpoint before this timer wins.
+ */
+const MAX_BACKGROUND_BUILDER_GATEWAY_TIMEOUT_MS = 14 * 60_000;
+/** Local and non-hosted runtimes have no synchronous serverless wall. */
+const MAX_LOCAL_BUILDER_GATEWAY_TIMEOUT_MS =
+  MAX_BACKGROUND_BUILDER_GATEWAY_TIMEOUT_MS;
 const BUILDER_GATEWAY_NETWORK_ERROR_CODE = "builder_gateway_network_error";
 
 export const BUILDER_DEFAULT_MODEL = BUILDER_MODEL_CONFIG.defaultModel;
@@ -315,6 +323,7 @@ class BuilderEngine implements AgentEngine {
       }
 
       yield* parseJsonlStream(reader, opts.model, {
+        abortSignal: gatewayAbort.signal,
         didGatewayTimeout: gatewayAbort.didTimeout,
         gatewayTimeoutMs,
         gatewayUrl,
@@ -430,11 +439,12 @@ async function* emitHttpError(response: Response): AsyncIterable<EngineEvent> {
 // a complete line and the client must still process it.
 async function* readJsonlLines(
   reader: ReadableStreamDefaultReader<Uint8Array>,
+  abortSignal?: AbortSignal,
 ): AsyncIterable<string> {
   const decoder = new TextDecoder();
   let buffer = "";
   while (true) {
-    const { done, value } = await reader.read();
+    const { done, value } = await readStreamChunk(reader, abortSignal);
     if (done) break;
     buffer += decoder.decode(value, { stream: true });
     let newlineIdx = buffer.indexOf("\n");
@@ -457,6 +467,7 @@ async function* parseJsonlStream(
   reader: ReadableStreamDefaultReader<Uint8Array>,
   model: string,
   captureContext: {
+    abortSignal?: AbortSignal;
     didGatewayTimeout?: () => boolean;
     gatewayTimeoutMs?: number;
     gatewayUrl?: URL;
@@ -487,7 +498,10 @@ async function* parseJsonlStream(
   };
 
   try {
-    for await (const line of readJsonlLines(reader)) {
+    for await (const line of readJsonlLines(
+      reader,
+      captureContext.abortSignal,
+    )) {
       let event: any;
       try {
         event = JSON.parse(line);
@@ -722,6 +736,32 @@ async function* parseJsonlStream(
   }
 }
 
+function readStreamChunk(
+  reader: ReadableStreamDefaultReader<Uint8Array>,
+  abortSignal?: AbortSignal,
+): Promise<ReadableStreamReadResult<Uint8Array>> {
+  if (!abortSignal) return reader.read();
+  if (abortSignal.aborted) {
+    return Promise.reject(abortSignal.reason ?? new Error("Stream aborted"));
+  }
+  return new Promise((resolve, reject) => {
+    const onAbort = () => {
+      reject(abortSignal.reason ?? new Error("Stream aborted"));
+    };
+    abortSignal.addEventListener("abort", onAbort, { once: true });
+    reader.read().then(
+      (value) => {
+        abortSignal.removeEventListener("abort", onAbort);
+        resolve(value);
+      },
+      (err) => {
+        abortSignal.removeEventListener("abort", onAbort);
+        reject(err);
+      },
+    );
+  });
+}
+
 function normalizeGatewayErrorText(raw: string, status: number): string {
   const text = raw.trim();
   const looksHtml = /<html[\s>]|<body[\s>]|<head[\s>]/i.test(text);
@@ -761,6 +801,14 @@ export function createBuilderEngine(
 }
 
 function resolveMaxBuilderGatewayTimeoutMs(): number {
+  if (isInBackgroundFunctionRuntime()) {
+    return MAX_BACKGROUND_BUILDER_GATEWAY_TIMEOUT_MS;
+  }
+
+  if (!isHostedBuilderRuntime()) {
+    return MAX_LOCAL_BUILDER_GATEWAY_TIMEOUT_MS;
+  }
+
   try {
     const base = getBuilderGatewayBaseUrl();
     if (/^https?:\/\/(localhost|127\.0\.0\.1)([:/]|$)/i.test(base)) {
@@ -769,7 +817,31 @@ function resolveMaxBuilderGatewayTimeoutMs(): number {
   } catch {
     // ignore malformed override
   }
-  return MAX_BUILDER_GATEWAY_TIMEOUT_MS;
+  return MAX_HOSTED_FOREGROUND_BUILDER_GATEWAY_TIMEOUT_MS;
+}
+
+function isHostedBuilderRuntime(): boolean {
+  if (
+    process.env.NETLIFY &&
+    process.env.NETLIFY !== "false" &&
+    process.env.NETLIFY_LOCAL !== "true"
+  ) {
+    return true;
+  }
+  if (
+    process.env.AWS_LAMBDA_FUNCTION_NAME &&
+    process.env.NETLIFY_LOCAL !== "true"
+  ) {
+    return true;
+  }
+  return Boolean(
+    process.env.CF_PAGES ||
+    process.env.VERCEL ||
+    process.env.VERCEL_ENV ||
+    process.env.RENDER ||
+    process.env.FLY_APP_NAME ||
+    process.env.K_SERVICE,
+  );
 }
 
 function getBuilderGatewayTimeoutMs(): number {

package/corpus/core/src/agent/run-manager.ts

@@ -46,8 +46,8 @@ const CLEANUP_DELAY_MS = 5 * 60 * 1000;
  *
  * This MUST fire before the two upstream hard walls that otherwise kill a run
  * mid-turn with no chance to hand off:
- *   1. The Builder model gateway hard-caps a single model call at 45s
- *      (builder-engine.ts MAX_BUILDER_GATEWAY_TIMEOUT_MS) — not raisable.
+ *   1. The Builder model gateway keeps a 45s cap only for hosted foreground
+ *      runs; local and proven background-function runs use longer caps.
  *   2. Serverless functions are hard-killed around 60-65s (the heartbeat then
  *      reaps the row as a stale_run).
  * Production data showed every cutoff landing in the 44-70s window with ZERO
@@ -61,11 +61,12 @@ export const DEFAULT_HOSTED_RUN_SOFT_TIMEOUT_MS = 40_000;
 
 /**
  * Hard ceiling for the hosted soft timeout. On a hosted runtime the
- * auto_continue soft timeout can never usefully exceed this — the gateway
- * (45s) / function (~60s) walls kill the run first, so a larger configured or
- * env value just guarantees the cutoff is a hard error instead of a graceful
- * hand-off. Any resolved value above this is clamped down when hosted. Local
- * dev (non-hosted) is left alone so long-running local turns aren't chunked.
+ * foreground auto_continue soft timeout can never usefully exceed this — the
+ * synchronous function (~60s) wall kills the run first, so a larger configured
+ * or env value just guarantees the cutoff is a hard error instead of a graceful
+ * hand-off. Any resolved value above this is clamped down for hosted foreground
+ * runs. Local dev (non-hosted) is left alone so long-running local turns aren't
+ * chunked.
  *
  * IMPORTANT: this clamp is for the INTERACTIVE / foreground path and must NOT
  * be raised. The foreground POST still rides a synchronous serverless function

package/corpus/core/src/cli/design-connect.ts

@@ -1,3 +1,4 @@
+import { spawn } from "node:child_process";
 import crypto from "node:crypto";
 import fsSync from "node:fs";
 import fs from "node:fs/promises";
@@ -44,6 +45,7 @@ export interface DesignConnectArgs {
   json: boolean;
   once: boolean;
   dryRun: boolean;
+  daemon: boolean;
   help: boolean;
 }
 
@@ -115,6 +117,7 @@ export function parseDesignConnectArgs(argv: string[]): DesignConnectArgs {
     json: false,
     once: false,
     dryRun: false,
+    daemon: false,
     help: false,
   };
 
@@ -155,6 +158,8 @@ export function parseDesignConnectArgs(argv: string[]): DesignConnectArgs {
     } else if (arg === "--dry-run") {
       parsed.dryRun = true;
       parsed.once = true;
+    } else if (arg === "--daemon") {
+      parsed.daemon = true;
     } else if (arg.startsWith("-")) {
       throw new Error(`Unknown option: ${arg}`);
     } else {
@@ -165,6 +170,11 @@ export function parseDesignConnectArgs(argv: string[]): DesignConnectArgs {
   if (!Number.isInteger(parsed.port) || parsed.port <= 0) {
     throw new Error("--port must be a positive integer");
   }
+  if (parsed.daemon && (parsed.json || parsed.once || parsed.dryRun)) {
+    throw new Error(
+      "--daemon cannot be combined with --json, --once, or --dry-run",
+    );
+  }
   parsed.root = path.resolve(parsed.root);
   parsed.url = parsed.url ? normalizeHttpUrl(parsed.url) : undefined;
   return parsed;
@@ -298,6 +308,86 @@ async function probeDevServer(url: string): Promise<boolean> {
   }
 }
 
+async function waitForBridgeHealth(
+  bridgeUrl: string,
+  timeoutMs = 5_000,
+): Promise<boolean> {
+  const healthUrl = new URL("/health", bridgeUrl).toString();
+  const deadline = Date.now() + timeoutMs;
+  while (Date.now() < deadline) {
+    const controller = new AbortController();
+    const timeout = setTimeout(() => controller.abort(), 400);
+    try {
+      const response = await fetch(healthUrl, {
+        method: "GET",
+        signal: controller.signal,
+      });
+      if (response.ok) return true;
+    } catch {
+      // Keep polling until the detached process finishes binding the port.
+    } finally {
+      clearTimeout(timeout);
+    }
+    await new Promise((resolve) => setTimeout(resolve, 150));
+  }
+  return false;
+}
+
+function isDesignConnectManifest(
+  value: unknown,
+): value is DesignConnectManifest {
+  if (!value || typeof value !== "object") return false;
+  const manifest = value as Partial<DesignConnectManifest>;
+  return (
+    manifest.version === 1 &&
+    manifest.source === "agent-native-design-connect" &&
+    manifest.sourceType === "localhost" &&
+    manifest.localOnly === true &&
+    typeof manifest.devServerUrl === "string" &&
+    typeof manifest.bridgeUrl === "string" &&
+    typeof manifest.rootPath === "string"
+  );
+}
+
+async function fetchRunningBridgeManifest(
+  bridgeUrl: string,
+): Promise<DesignConnectManifest | null> {
+  const manifestUrl = new URL("/manifest.json", bridgeUrl).toString();
+  const controller = new AbortController();
+  const timeout = setTimeout(() => controller.abort(), 800);
+  try {
+    const response = await fetch(manifestUrl, {
+      method: "GET",
+      signal: controller.signal,
+    });
+    if (!response.ok) return null;
+    const body = (await response.json()) as unknown;
+    return isDesignConnectManifest(body) ? body : null;
+  } catch {
+    return null;
+  } finally {
+    clearTimeout(timeout);
+  }
+}
+
+export function designConnectManifestsTargetSameApp(
+  running: Pick<DesignConnectManifest, "devServerUrl" | "rootPath">,
+  requested: Pick<DesignConnectManifest, "devServerUrl" | "rootPath">,
+): boolean {
+  let runningUrl = running.devServerUrl;
+  let requestedUrl = requested.devServerUrl;
+  try {
+    runningUrl = normalizeHttpUrl(runningUrl);
+    requestedUrl = normalizeHttpUrl(requestedUrl);
+  } catch {
+    // Fall through to direct string comparison for malformed legacy manifests.
+  }
+  return (
+    runningUrl === requestedUrl &&
+    path.resolve(running.rootPath) === path.resolve(requested.rootPath)
+  );
+}
+
 async function resolveDevServerUrl(url?: string): Promise<string> {
   if (url) return normalizeHttpUrl(url);
   for (const candidate of DEFAULT_DEV_SERVER_CANDIDATES) {
@@ -942,6 +1032,7 @@ Options:
   --route-manifest <path> Non-destructive route manifest output path
   --app-url <url>         Deployed design app URL for self-registration
                           (also reads AGENT_NATIVE_URL / DESIGN_APP_URL env)
+  --daemon                Start the bridge detached, wait for /health, then exit
   --json                  Print the manifest JSON and exit
   --once                  Prepare/scaffold the manifest and exit
   --dry-run               Print what would be exposed without writing files
@@ -966,6 +1057,87 @@ Element provenance (resolveNodeToFile):
   Cross-origin localhost iframes cannot be read regardless of attributes (CSP).`);
 }
 
+function removeDaemonFlag(argv: string[]): string[] {
+  return argv.filter((arg) => arg !== "--daemon");
+}
+
+function resolveCurrentCliInvocation(argv: string[]): {
+  command: string;
+  args: string[];
+} {
+  const suffixLength = argv.length + 1; // leading "design" command + runDesign argv
+  const prefixEnd = Math.max(1, process.argv.length - suffixLength);
+  const cliPrefix = process.argv.slice(1, prefixEnd);
+  const entry = cliPrefix[0] ?? process.argv[1];
+  if (!entry) {
+    throw new Error("Could not resolve current CLI entrypoint for --daemon");
+  }
+  if (entry.endsWith(".ts") || entry.endsWith(".tsx")) {
+    return {
+      command: "tsx",
+      args: [...cliPrefix, "design", ...removeDaemonFlag(argv)],
+    };
+  }
+  return {
+    command: process.execPath,
+    args: [...cliPrefix, "design", ...removeDaemonFlag(argv)],
+  };
+}
+
+async function startDetachedDesignBridge(
+  argv: string[],
+  manifest: DesignConnectManifest,
+): Promise<number> {
+  if (await waitForBridgeHealth(manifest.bridgeUrl, 800)) {
+    const runningManifest = await fetchRunningBridgeManifest(
+      manifest.bridgeUrl,
+    );
+    if (
+      runningManifest &&
+      designConnectManifestsTargetSameApp(runningManifest, manifest)
+    ) {
+      console.error(
+        `Design localhost bridge already running at ${manifest.bridgeUrl}`,
+      );
+      console.log(JSON.stringify(runningManifest, null, 2));
+      return 0;
+    }
+
+    console.error(
+      [
+        `Design localhost bridge already running at ${manifest.bridgeUrl} for a different app.`,
+        runningManifest
+          ? `Running app: ${runningManifest.devServerUrl} (${runningManifest.rootPath})`
+          : "Running bridge did not expose a compatible manifest.",
+        `Requested app: ${manifest.devServerUrl} (${manifest.rootPath})`,
+        "Stop the existing bridge or choose a different --port.",
+      ].join("\n"),
+    );
+    return 1;
+  }
+
+  const invocation = resolveCurrentCliInvocation(argv);
+  const child = spawn(invocation.command, invocation.args, {
+    cwd: process.cwd(),
+    detached: true,
+    env: process.env,
+    stdio: "ignore",
+    shell: process.platform === "win32",
+  });
+  child.unref();
+
+  if (await waitForBridgeHealth(manifest.bridgeUrl)) {
+    console.error(`Design localhost bridge running at ${manifest.bridgeUrl}`);
+    console.log(JSON.stringify(manifest, null, 2));
+    return 0;
+  }
+
+  console.error(
+    `Timed out waiting for detached Design bridge at ${manifest.bridgeUrl}`,
+  );
+  return 1;
+}
+
 export async function runDesign(argv: string[]) {
   const subcommand = argv[0];
   if (subcommand !== "connect") {
@@ -988,6 +1160,9 @@ export async function runDesign(argv: string[]) {
   }
 
   const manifest = await prepareDesignConnectManifest(parsed);
+  if (parsed.daemon) {
+    return startDetachedDesignBridge(argv, manifest);
+  }
   if (parsed.json || parsed.once || parsed.dryRun) {
     console.log(JSON.stringify(manifest, null, 2));
     return 0;

package/corpus/core/src/cli/skills.ts

@@ -464,18 +464,16 @@ iframe-backed screens on the infinite canvas.
 From the target app repo, make sure its dev server is running, then run:
 
 \`\`\`bash
-npx @agent-native/core@latest design connect --url http://localhost:5173 --root .
+npx @agent-native/core@latest design connect --url http://localhost:5173 --root . --daemon
 \`\`\`
 
-Use the app's real port. The command starts a local bridge on
-\`http://127.0.0.1:7331\` by default and exposes \`/manifest.json\`,
-\`/routes.json\`, and \`/health\`.
+Use the app's real port. The command starts a detached local bridge on
+\`http://127.0.0.1:7331\` by default, waits for \`/health\`, prints the
+manifest JSON, and keeps the bridge alive after the agent command exits.
 
-For one-shot agent setup, ask for JSON and keep the long-running bridge open in
-a second terminal if the user needs live updates:
+For a manual health/manifest check:
 
 \`\`\`bash
-npx @agent-native/core@latest design connect --url http://localhost:5173 --root .
 curl http://127.0.0.1:7331/manifest.json
 \`\`\`
 

package/corpus/core/src/client/AgentPanel.tsx

@@ -548,6 +548,8 @@ export interface AgentPanelProps extends Omit<
    * see the `Layout` files for each template.
    */
   scope?: import("./use-chat-threads.js").ChatThreadScope | null;
+  /** Show the compact scope chip above the composer. Default: true. */
+  showScopeBadge?: MultiTabAssistantChatProps["showScopeBadge"];
   /** Stable browser tab id used for tab-scoped app-state context. */
   browserTabId?: string;
   /** Keep chat thread selection in URL state. */
@@ -673,6 +675,7 @@ function AgentPanelInner({
   storageKey,
   restoreActiveThread = true,
   scope,
+  showScopeBadge,
   browserTabId,
   threadUrlSync,
   chatNotice,
@@ -1710,6 +1713,7 @@ function AgentPanelInner({
               storageKey={storageKey}
               restoreActiveThread={restoreActiveThread}
               scope={scope}
+              showScopeBadge={showScopeBadge}
               browserTabId={browserTabId}
               threadUrlSync={threadUrlSync}
             />
@@ -2393,6 +2397,8 @@ export interface AgentSidebarProps {
    * Templates compute this from the active route (see template layouts).
    */
   scope?: import("./use-chat-threads.js").ChatThreadScope | null;
+  /** Show the compact scope chip above the composer. Default: true. */
+  showScopeBadge?: MultiTabAssistantChatProps["showScopeBadge"];
   /** Stable browser tab id used for tab-scoped app-state context. */
   browserTabId?: string;
   /** Keep chat thread selection in URL state. */
@@ -2422,6 +2428,7 @@ export function AgentSidebar({
   openOnChatRunning = false,
   onFullscreenRequest,
   scope,
+  showScopeBadge,
   browserTabId,
   threadUrlSync,
 }: AgentSidebarProps) {
@@ -2955,6 +2962,7 @@ export function AgentSidebar({
             }
             storageKey={storageKey}
             scope={scope}
+            showScopeBadge={showScopeBadge}
             browserTabId={browserTabId}
             threadUrlSync={threadUrlSync}
           />

package/corpus/core/src/client/MultiTabAssistantChat.tsx

@@ -929,6 +929,8 @@ export type MultiTabAssistantChatProps = Omit<
    * the composer.
    */
   scope?: ChatThreadScope | null;
+  /** Show the compact scope chip above the composer. Default: true. */
+  showScopeBadge?: boolean;
 };
 
 export function MultiTabAssistantChat({
@@ -942,6 +944,7 @@ export function MultiTabAssistantChat({
   browserTabId,
   threadUrlSync = false,
   scope = null,
+  showScopeBadge = true,
   ...props
 }: MultiTabAssistantChatProps) {
   const {
@@ -2625,7 +2628,7 @@ export function MultiTabAssistantChat({
                 ? props.dynamicSuggestions
                 : false;
             const scopeComposerSlot =
-              tabId === activeThreadId && !contentHidden ? (
+              showScopeBadge && tabId === activeThreadId && !contentHidden ? (
                 tabScope && activeThreadId ? (
                   <ScopeBadge
                     scope={tabScope}