fix: keep mac gateway attached (#982) (thanks @wes-davis)

Co-authored-by: Wes <wesleydavis@me.com>

CHANGELOG.md

@@ -26,6 +26,7 @@
 - Fix: guard model fallback against undefined provider/model values. (#954) — thanks @roshanasingh4.
 - Fix: refactor session store updates, add chat.inject, and harden subagent cleanup flow. (#944) — thanks @tyler6204.
 - Fix: clean up suspended CLI processes across backends. (#978) — thanks @Nachx639.
+- Fix: macOS gateway stays attached across restarts (no port flapping) and status probes pick the right auth. (#982) — thanks @wes-davis.
 - CLI: add `--json` output for `clawdbot daemon` lifecycle/install commands.
 - Memory: make `node-llama-cpp` an optional dependency (avoid Node 25 install failures) and improve local-embeddings fallback/errors.
 - Browser: add `snapshot refs=aria` (Playwright aria-ref ids) for self-resolving refs across `snapshot` → `act`.

apps/macos/Sources/Clawdbot/GatewayEnvironment.swift

@@ -178,7 +178,7 @@ enum GatewayEnvironment {
         let port = self.gatewayPort()
         if let gatewayBin {
             let bind = self.preferredGatewayBind() ?? "loopback"
-            let cmd = [gatewayBin, "gateway-daemon", "--port", "\(port)", "--bind", bind]
+            let cmd = [gatewayBin, "gateway", "--port", "\(port)", "--bind", bind]
             return GatewayCommandResolution(status: status, command: cmd)
         }
 
@@ -186,7 +186,7 @@ enum GatewayEnvironment {
            case let .success(resolvedRuntime) = runtime
         {
             let bind = self.preferredGatewayBind() ?? "loopback"
-            let cmd = [resolvedRuntime.path, entry, "gateway-daemon", "--port", "\(port)", "--bind", bind]
+            let cmd = [resolvedRuntime.path, entry, "gateway", "--port", "\(port)", "--bind", bind]
             return GatewayCommandResolution(status: status, command: cmd)
         }
 

apps/macos/Sources/Clawdbot/GatewayProcessManager.swift

@@ -87,6 +87,14 @@ final class GatewayProcessManager {
             self.status = .stopped
             return
         }
+        // Many surfaces can call `setActive(true)` in quick succession (startup, Canvas, health checks).
+        // Avoid spawning multiple concurrent "start" tasks that can thrash launchd and flap the port.
+        switch self.status {
+        case .starting, .running, .attachedExisting:
+            return
+        case .stopped, .failed:
+            break
+        }
         self.status = .starting
         self.logger.debug("gateway start requested")
 

apps/macos/Sources/Clawdbot/PortGuardian.swift

@@ -351,10 +351,14 @@ actor PortGuardian {
             if port == GatewayEnvironment.gatewayPort() { return cmd.contains("ssh") }
             return false
         case .local:
-            if !cmd.contains("clawdbot") { return false }
-            if full.contains("gateway-daemon") { return true }
+            // The gateway may listen as `clawdbot` or via its runtime (e.g. node).
+            let hasGatewayArgs =
+                full.contains(" gateway ") &&
+                full.contains(" --port \(port)")
+            if hasGatewayArgs { return true }
             // If args are unavailable, treat a clawdbot listener as expected.
-            return full == cmd
+            if cmd.contains("clawdbot"), full == cmd { return true }
+            return false
         case .unconfigured:
             return false
         }

apps/macos/Tests/ClawdbotIPCTests/GatewayLaunchAgentManagerTests.swift

@@ -7,7 +7,7 @@ import Testing
         let url = FileManager.default.temporaryDirectory
             .appendingPathComponent("clawdbot-launchd-\(UUID().uuidString).plist")
         let plist: [String: Any] = [
-            "ProgramArguments": ["clawdbot", "gateway-daemon", "--port", "18789", "--bind", "loopback"],
+            "ProgramArguments": ["clawdbot", "gateway", "--port", "18789", "--bind", "loopback"],
             "EnvironmentVariables": [
                 "CLAWDBOT_GATEWAY_TOKEN": " secret ",
                 "CLAWDBOT_GATEWAY_PASSWORD": "pw",
@@ -28,7 +28,7 @@ import Testing
         let url = FileManager.default.temporaryDirectory
             .appendingPathComponent("clawdbot-launchd-\(UUID().uuidString).plist")
         let plist: [String: Any] = [
-            "ProgramArguments": ["clawdbot", "gateway-daemon", "--port", "18789"],
+            "ProgramArguments": ["clawdbot", "gateway", "--port", "18789"],
         ]
         let data = try PropertyListSerialization.data(fromPropertyList: plist, format: .xml, options: 0)
         try data.write(to: url, options: [.atomic])

docs/platforms/hetzner.md

@@ -187,7 +187,7 @@ services:
       [
         "node",
         "dist/index.js",
-        "gateway-daemon",
+        "gateway",
         "--bind",
         "${CLAWDBOT_GATEWAY_BIND}",
         "--port",

scripts/restart-mac.sh

@@ -206,6 +206,31 @@ if [[ "$NO_SIGN" -ne 1 && -f "${LAUNCHAGENT_DISABLE_MARKER}" ]]; then
   run_step "clear launchagent disable marker" /bin/rm -f "${LAUNCHAGENT_DISABLE_MARKER}"
 fi
 
+# When unsigned, ensure the gateway LaunchAgent targets the repo CLI (before the app launches).
+# This reduces noisy "could not connect" errors during app startup.
+if [ "$NO_SIGN" -eq 1 ]; then
+  run_step "install gateway launch agent (unsigned)" bash -lc "cd '${ROOT_DIR}' && node dist/entry.js daemon install --force --runtime node"
+  run_step "restart gateway daemon (unsigned)" bash -lc "cd '${ROOT_DIR}' && node dist/entry.js daemon restart"
+  if [[ "${GATEWAY_WAIT_SECONDS}" -gt 0 ]]; then
+    run_step "wait for gateway (unsigned)" sleep "${GATEWAY_WAIT_SECONDS}"
+  fi
+  GATEWAY_PORT="$(
+    node -e '
+      const fs = require("node:fs");
+      const path = require("node:path");
+      try {
+        const raw = fs.readFileSync(path.join(process.env.HOME, ".clawdbot", "clawdbot.json"), "utf8");
+        const cfg = JSON.parse(raw);
+        const port = cfg && cfg.gateway && typeof cfg.gateway.port === "number" ? cfg.gateway.port : 18789;
+        process.stdout.write(String(port));
+      } catch {
+        process.stdout.write("18789");
+      }
+    '
+  )"
+  run_step "verify gateway port ${GATEWAY_PORT} (unsigned)" bash -lc "lsof -iTCP:${GATEWAY_PORT} -sTCP:LISTEN | head -n 5 || true"
+fi
+
 # 4) Launch the installed app in the foreground so the menu bar extra appears.
 # LaunchServices can inherit a huge environment from this shell (secrets, prompt vars, etc.).
 # That can cause launchd spawn failures and is undesirable for a GUI app anyway.
@@ -226,13 +251,6 @@ else
   fail "App exited immediately. Check ${LOG_PATH} or Console.app (User Reports)."
 fi
 
-# When unsigned, ensure the gateway LaunchAgent targets the repo CLI (after the app launches).
 if [ "$NO_SIGN" -eq 1 ]; then
-  run_step "install gateway launch agent (unsigned)" bash -lc "cd '${ROOT_DIR}' && node dist/entry.js daemon install --force --runtime node"
-  run_step "restart gateway daemon (unsigned)" bash -lc "cd '${ROOT_DIR}' && node dist/entry.js daemon restart"
-  if [[ "${GATEWAY_WAIT_SECONDS}" -gt 0 ]]; then
-    run_step "wait for gateway (unsigned)" sleep "${GATEWAY_WAIT_SECONDS}"
-  fi
-  run_step "verify gateway port 18789 (unsigned)" bash -lc "lsof -iTCP:18789 -sTCP:LISTEN | head -n 5 || true"
   run_step "show gateway launch agent args (unsigned)" bash -lc "/usr/bin/plutil -p '${HOME}/Library/LaunchAgents/com.clawdbot.gateway.plist' | head -n 40 || true"
 fi

src/agents/pi-embedded-subscribe.handlers.lifecycle.ts

@@ -14,7 +14,7 @@ export function handleAgentStart(ctx: EmbeddedPiSubscribeContext) {
       startedAt: Date.now(),
     },
   });
-  ctx.params.onAgentEvent?.({
+  void ctx.params.onAgentEvent?.({
     stream: "lifecycle",
     data: { phase: "start" },
   });
@@ -24,7 +24,7 @@ export function handleAutoCompactionStart(ctx: EmbeddedPiSubscribeContext) {
   ctx.state.compactionInFlight = true;
   ctx.ensureCompactionPromise();
   ctx.log.debug(`embedded run compaction start: runId=${ctx.params.runId}`);
-  ctx.params.onAgentEvent?.({
+  void ctx.params.onAgentEvent?.({
     stream: "compaction",
     data: { phase: "start" },
   });
@@ -43,7 +43,7 @@ export function handleAutoCompactionEnd(
   } else {
     ctx.maybeResolveCompactionWait();
   }
-  ctx.params.onAgentEvent?.({
+  void ctx.params.onAgentEvent?.({
     stream: "compaction",
     data: { phase: "end", willRetry },
   });
@@ -59,7 +59,7 @@ export function handleAgentEnd(ctx: EmbeddedPiSubscribeContext) {
       endedAt: Date.now(),
     },
   });
-  ctx.params.onAgentEvent?.({
+  void ctx.params.onAgentEvent?.({
     stream: "lifecycle",
     data: { phase: "end" },
   });

src/agents/pi-embedded-subscribe.handlers.messages.ts

@@ -118,7 +118,7 @@ export function handleMessageUpdate(
         mediaUrls: mediaUrls?.length ? mediaUrls : undefined,
       },
     });
-    ctx.params.onAgentEvent?.({
+    void ctx.params.onAgentEvent?.({
       stream: "assistant",
       data: {
         text: cleanedText,

src/agents/pi-embedded-subscribe.handlers.tools.ts

@@ -11,7 +11,7 @@ import {
 } from "./pi-embedded-subscribe.tools.js";
 import { inferToolMetaFromArgs } from "./pi-embedded-utils.js";
 
-export function handleToolExecutionStart(
+export async function handleToolExecutionStart(
   ctx: EmbeddedPiSubscribeContext,
   evt: AgentEvent & { toolName: string; toolCallId: string; args: unknown },
 ) {
@@ -53,7 +53,8 @@ export function handleToolExecutionStart(
       args: args as Record<string, unknown>,
     },
   });
-  ctx.params.onAgentEvent?.({
+  // Await onAgentEvent to ensure typing indicator starts before tool summaries are emitted.
+  await ctx.params.onAgentEvent?.({
     stream: "tool",
     data: { phase: "start", name: toolName, toolCallId },
   });
@@ -108,7 +109,7 @@ export function handleToolExecutionUpdate(
       partialResult: sanitized,
     },
   });
-  ctx.params.onAgentEvent?.({
+  void ctx.params.onAgentEvent?.({
     stream: "tool",
     data: {
       phase: "update",
@@ -170,7 +171,7 @@ export function handleToolExecutionEnd(
       result: sanitizedResult,
     },
   });
-  ctx.params.onAgentEvent?.({
+  void ctx.params.onAgentEvent?.({
     stream: "tool",
     data: {
       phase: "result",

src/agents/pi-embedded-subscribe.handlers.ts

@@ -32,7 +32,11 @@ export function createEmbeddedPiSessionEventHandler(ctx: EmbeddedPiSubscribeCont
         handleMessageEnd(ctx, evt as never);
         return;
       case "tool_execution_start":
-        handleToolExecutionStart(ctx, evt as never);
+        // Async handler - awaits typing indicator before emitting tool summaries.
+        // Catch rejections to avoid unhandled promise rejection crashes.
+        handleToolExecutionStart(ctx, evt as never).catch((err) => {
+          ctx.log.debug(`tool_execution_start handler failed: ${String(err)}`);
+        });
         return;
       case "tool_execution_update":
         handleToolExecutionUpdate(ctx, evt as never);

src/agents/pi-embedded-subscribe.subscribe-embedded-pi-session.includes-canvas-action-metadata-tool-summaries.test.ts

@@ -13,7 +13,7 @@ describe("subscribeEmbeddedPiSession", () => {
     { tag: "antthinking", open: "<antthinking>", close: "</antthinking>" },
   ] as const;
 
-  it("includes canvas action metadata in tool summaries", () => {
+  it("includes canvas action metadata in tool summaries", async () => {
     let handler: ((evt: unknown) => void) | undefined;
     const session: StubSession = {
       subscribe: (fn) => {
@@ -38,6 +38,9 @@ describe("subscribeEmbeddedPiSession", () => {
       args: { action: "a2ui_push", jsonlPath: "/tmp/a2ui.jsonl" },
     });
 
+    // Wait for async handler to complete
+    await Promise.resolve();
+
     expect(onToolResult).toHaveBeenCalledTimes(1);
     const payload = onToolResult.mock.calls[0][0];
     expect(payload.text).toContain("🖼️");
@@ -72,7 +75,7 @@ describe("subscribeEmbeddedPiSession", () => {
 
     expect(onToolResult).not.toHaveBeenCalled();
   });
-  it("emits tool summaries when shouldEmitToolResult overrides verbose", () => {
+  it("emits tool summaries when shouldEmitToolResult overrides verbose", async () => {
     let handler: ((evt: unknown) => void) | undefined;
     const session: StubSession = {
       subscribe: (fn) => {
@@ -98,6 +101,9 @@ describe("subscribeEmbeddedPiSession", () => {
       args: { path: "/tmp/c.txt" },
     });
 
+    // Wait for async handler to complete
+    await Promise.resolve();
+
     expect(onToolResult).toHaveBeenCalledTimes(1);
   });
 });

src/agents/pi-embedded-subscribe.subscribe-embedded-pi-session.suppresses-message-end-block-replies-message-tool.test.ts

@@ -14,7 +14,7 @@ describe("subscribeEmbeddedPiSession", () => {
     { tag: "antthinking", open: "<antthinking>", close: "</antthinking>" },
   ] as const;
 
-  it("suppresses message_end block replies when the message tool already sent", () => {
+  it("suppresses message_end block replies when the message tool already sent", async () => {
     let handler: ((evt: unknown) => void) | undefined;
     const session: StubSession = {
       subscribe: (fn) => {
@@ -41,6 +41,9 @@ describe("subscribeEmbeddedPiSession", () => {
       args: { action: "send", to: "+1555", message: messageText },
     });
 
+    // Wait for async handler to complete
+    await Promise.resolve();
+
     handler?.({
       type: "tool_execution_end",
       toolName: "message",
@@ -58,7 +61,7 @@ describe("subscribeEmbeddedPiSession", () => {
 
     expect(onBlockReply).not.toHaveBeenCalled();
   });
-  it("does not suppress message_end replies when message tool reports error", () => {
+  it("does not suppress message_end replies when message tool reports error", async () => {
     let handler: ((evt: unknown) => void) | undefined;
     const session: StubSession = {
       subscribe: (fn) => {
@@ -85,6 +88,9 @@ describe("subscribeEmbeddedPiSession", () => {
       args: { action: "send", to: "+1555", message: messageText },
     });
 
+    // Wait for async handler to complete
+    await Promise.resolve();
+
     handler?.({
       type: "tool_execution_end",
       toolName: "message",

src/agents/pi-embedded-subscribe.subscribe-embedded-pi-session.waits-multiple-compaction-retries-before-resolving.test.ts

@@ -54,7 +54,7 @@ describe("subscribeEmbeddedPiSession", () => {
     await waitPromise;
     expect(resolved).toBe(true);
   });
-  it("emits tool summaries at tool start when verbose is on", () => {
+  it("emits tool summaries at tool start when verbose is on", async () => {
     let handler: ((evt: unknown) => void) | undefined;
     const session: StubSession = {
       subscribe: (fn) => {
@@ -79,6 +79,9 @@ describe("subscribeEmbeddedPiSession", () => {
       args: { path: "/tmp/a.txt" },
     });
 
+    // Wait for async handler to complete
+    await Promise.resolve();
+
     expect(onToolResult).toHaveBeenCalledTimes(1);
     const payload = onToolResult.mock.calls[0][0];
     expect(payload.text).toContain("/tmp/a.txt");
@@ -93,7 +96,7 @@ describe("subscribeEmbeddedPiSession", () => {
 
     expect(onToolResult).toHaveBeenCalledTimes(1);
   });
-  it("includes browser action metadata in tool summaries", () => {
+  it("includes browser action metadata in tool summaries", async () => {
     let handler: ((evt: unknown) => void) | undefined;
     const session: StubSession = {
       subscribe: (fn) => {
@@ -118,6 +121,9 @@ describe("subscribeEmbeddedPiSession", () => {
       args: { action: "snapshot", targetUrl: "https://example.com" },
     });
 
+    // Wait for async handler to complete
+    await Promise.resolve();
+
     expect(onToolResult).toHaveBeenCalledTimes(1);
     const payload = onToolResult.mock.calls[0][0];
     expect(payload.text).toContain("🌐");

src/agents/pi-embedded-subscribe.types.ts

@@ -22,7 +22,10 @@ export type SubscribeEmbeddedPiSessionParams = {
   blockReplyChunking?: BlockReplyChunking;
   onPartialReply?: (payload: { text?: string; mediaUrls?: string[] }) => void | Promise<void>;
   onAssistantMessageStart?: () => void | Promise<void>;
-  onAgentEvent?: (evt: { stream: string; data: Record<string, unknown> }) => void;
+  onAgentEvent?: (evt: {
+    stream: string;
+    data: Record<string, unknown>;
+  }) => void | Promise<void>;
   enforceFinalTag?: boolean;
 };
 

src/auto-reply/reply/agent-runner-execution.ts

@@ -26,7 +26,7 @@ import type { VerboseLevel } from "../thinking.js";
 import { isSilentReplyText, SILENT_REPLY_TOKEN } from "../tokens.js";
 import type { GetReplyOptions, ReplyPayload } from "../types.js";
 import { buildThreadingToolContext, resolveEnforceFinalTag } from "./agent-runner-utils.js";
-import type { BlockReplyPipeline } from "./block-reply-pipeline.js";
+import { createBlockReplyPayloadKey, type BlockReplyPipeline } from "./block-reply-pipeline.js";
 import type { FollowupRun } from "./queue.js";
 import { parseReplyDirectives } from "./reply-directives.js";
 import { applyReplyTagsToPayload, isRenderablePayload } from "./reply-payloads.js";
@@ -40,6 +40,8 @@ export type AgentRunLoopResult =
       fallbackModel?: string;
       didLogHeartbeatStrip: boolean;
       autoCompactionCompleted: boolean;
+      /** Payload keys sent directly (not via pipeline) during tool flush. */
+      directlySentBlockKeys?: Set<string>;
     }
   | { kind: "final"; payload: ReplyPayload };
 
@@ -70,6 +72,8 @@ export async function runAgentTurnWithFallback(params: {
 }): Promise<AgentRunLoopResult> {
   let didLogHeartbeatStrip = false;
   let autoCompactionCompleted = false;
+  // Track payloads sent directly (not via pipeline) during tool flush to avoid duplicates.
+  const directlySentBlockKeys = new Set<string>();
 
   const runId = crypto.randomUUID();
   if (params.sessionKey) {
@@ -244,12 +248,13 @@ export async function runAgentTurnWithFallback(params: {
                     });
                   }
                 : undefined,
-            onAgentEvent: (evt) => {
-              // Trigger typing when tools start executing
+            onAgentEvent: async (evt) => {
+              // Trigger typing when tools start executing.
+              // Must await to ensure typing indicator starts before tool summaries are emitted.
               if (evt.stream === "tool") {
                 const phase = typeof evt.data.phase === "string" ? evt.data.phase : "";
                 if (phase === "start" || phase === "update") {
-                  void params.typingSignals.signalToolStart();
+                  await params.typingSignals.signalToolStart();
                 }
               }
               // Track auto-compaction completion
@@ -261,57 +266,67 @@ export async function runAgentTurnWithFallback(params: {
                 }
               }
             },
-            onBlockReply:
-              params.blockStreamingEnabled && params.opts?.onBlockReply
-                ? async (payload) => {
-                    const { text, skip } = normalizeStreamingText(payload);
-                    const hasPayloadMedia = (payload.mediaUrls?.length ?? 0) > 0;
-                    if (skip && !hasPayloadMedia) return;
-                    const taggedPayload = applyReplyTagsToPayload(
-                      {
-                        text,
-                        mediaUrls: payload.mediaUrls,
-                        mediaUrl: payload.mediaUrls?.[0],
-                      },
-                      params.sessionCtx.MessageSid,
-                    );
-                    // Let through payloads with audioAsVoice flag even if empty (need to track it)
-                    if (!isRenderablePayload(taggedPayload) && !payload.audioAsVoice) return;
-                    const parsed = parseReplyDirectives(taggedPayload.text ?? "", {
-                      currentMessageId: params.sessionCtx.MessageSid,
-                      silentToken: SILENT_REPLY_TOKEN,
-                    });
-                    const cleaned = parsed.text || undefined;
-                    const hasRenderableMedia =
-                      Boolean(taggedPayload.mediaUrl) || (taggedPayload.mediaUrls?.length ?? 0) > 0;
-                    // Skip empty payloads unless they have audioAsVoice flag (need to track it)
-                    if (
-                      !cleaned &&
-                      !hasRenderableMedia &&
-                      !payload.audioAsVoice &&
-                      !parsed.audioAsVoice
-                    )
-                      return;
-                    if (parsed.isSilent && !hasRenderableMedia) return;
+            // Always pass onBlockReply so flushBlockReplyBuffer works before tool execution,
+            // even when regular block streaming is disabled. The handler sends directly
+            // via opts.onBlockReply when the pipeline isn't available.
+            onBlockReply: params.opts?.onBlockReply
+              ? async (payload) => {
+                  const { text, skip } = normalizeStreamingText(payload);
+                  const hasPayloadMedia = (payload.mediaUrls?.length ?? 0) > 0;
+                  if (skip && !hasPayloadMedia) return;
+                  const taggedPayload = applyReplyTagsToPayload(
+                    {
+                      text,
+                      mediaUrls: payload.mediaUrls,
+                      mediaUrl: payload.mediaUrls?.[0],
+                    },
+                    params.sessionCtx.MessageSid,
+                  );
+                  // Let through payloads with audioAsVoice flag even if empty (need to track it)
+                  if (!isRenderablePayload(taggedPayload) && !payload.audioAsVoice) return;
+                  const parsed = parseReplyDirectives(taggedPayload.text ?? "", {
+                    currentMessageId: params.sessionCtx.MessageSid,
+                    silentToken: SILENT_REPLY_TOKEN,
+                  });
+                  const cleaned = parsed.text || undefined;
+                  const hasRenderableMedia =
+                    Boolean(taggedPayload.mediaUrl) || (taggedPayload.mediaUrls?.length ?? 0) > 0;
+                  // Skip empty payloads unless they have audioAsVoice flag (need to track it)
+                  if (
+                    !cleaned &&
+                    !hasRenderableMedia &&
+                    !payload.audioAsVoice &&
+                    !parsed.audioAsVoice
+                  )
+                    return;
+                  if (parsed.isSilent && !hasRenderableMedia) return;
 
-                    const blockPayload: ReplyPayload = params.applyReplyToMode({
-                      ...taggedPayload,
-                      text: cleaned,
-                      audioAsVoice: Boolean(parsed.audioAsVoice || payload.audioAsVoice),
-                      replyToId: taggedPayload.replyToId ?? parsed.replyToId,
-                      replyToTag: taggedPayload.replyToTag || parsed.replyToTag,
-                      replyToCurrent: taggedPayload.replyToCurrent || parsed.replyToCurrent,
+                  const blockPayload: ReplyPayload = params.applyReplyToMode({
+                    ...taggedPayload,
+                    text: cleaned,
+                    audioAsVoice: Boolean(parsed.audioAsVoice || payload.audioAsVoice),
+                    replyToId: taggedPayload.replyToId ?? parsed.replyToId,
+                    replyToTag: taggedPayload.replyToTag || parsed.replyToTag,
+                    replyToCurrent: taggedPayload.replyToCurrent || parsed.replyToCurrent,
+                  });
+
+                  void params.typingSignals
+                    .signalTextDelta(cleaned ?? taggedPayload.text)
+                    .catch((err) => {
+                      logVerbose(`block reply typing signal failed: ${String(err)}`);
                     });
 
-                    void params.typingSignals
-                      .signalTextDelta(cleaned ?? taggedPayload.text)
-                      .catch((err) => {
-                        logVerbose(`block reply typing signal failed: ${String(err)}`);
-                      });
-
-                    params.blockReplyPipeline?.enqueue(blockPayload);
+                  // Use pipeline if available (block streaming enabled), otherwise send directly
+                  if (params.blockStreamingEnabled && params.blockReplyPipeline) {
+                    params.blockReplyPipeline.enqueue(blockPayload);
+                  } else {
+                    // Send directly when flushing before tool execution (no streaming).
+                    // Track sent key to avoid duplicate in final payloads.
+                    directlySentBlockKeys.add(createBlockReplyPayloadKey(blockPayload));
+                    await params.opts?.onBlockReply?.(blockPayload);
                   }
-                : undefined,
+                }
+              : undefined,
             onBlockReplyFlush:
               params.blockStreamingEnabled && blockReplyPipeline
                 ? async () => {
@@ -447,5 +462,6 @@ export async function runAgentTurnWithFallback(params: {
     fallbackModel,
     didLogHeartbeatStrip,
     autoCompactionCompleted,
+    directlySentBlockKeys: directlySentBlockKeys.size > 0 ? directlySentBlockKeys : undefined,
   };
 }

src/auto-reply/reply/agent-runner-payloads.ts

@@ -5,7 +5,7 @@ import type { OriginatingChannelType } from "../templating.js";
 import { SILENT_REPLY_TOKEN } from "../tokens.js";
 import type { ReplyPayload } from "../types.js";
 import { formatBunFetchSocketError, isBunFetchSocketError } from "./agent-runner-utils.js";
-import type { BlockReplyPipeline } from "./block-reply-pipeline.js";
+import { createBlockReplyPayloadKey, type BlockReplyPipeline } from "./block-reply-pipeline.js";
 import { parseReplyDirectives } from "./reply-directives.js";
 import {
   applyReplyThreading,
@@ -20,6 +20,8 @@ export function buildReplyPayloads(params: {
   didLogHeartbeatStrip: boolean;
   blockStreamingEnabled: boolean;
   blockReplyPipeline: BlockReplyPipeline | null;
+  /** Payload keys sent directly (not via pipeline) during tool flush. */
+  directlySentBlockKeys?: Set<string>;
   replyToMode: ReplyToMode;
   replyToChannel?: OriginatingChannelType;
   currentMessageId?: string;
@@ -98,11 +100,16 @@ export function buildReplyPayloads(params: {
     payloads: replyTaggedPayloads,
     sentTexts: messagingToolSentTexts,
   });
+  // Filter out payloads already sent via pipeline or directly during tool flush.
   const filteredPayloads = shouldDropFinalPayloads
     ? []
     : params.blockStreamingEnabled
       ? dedupedPayloads.filter((payload) => !params.blockReplyPipeline?.hasSentPayload(payload))
-      : dedupedPayloads;
+      : params.directlySentBlockKeys?.size
+        ? dedupedPayloads.filter(
+            (payload) => !params.directlySentBlockKeys!.has(createBlockReplyPayloadKey(payload)),
+          )
+        : dedupedPayloads;
   const replyPayloads = suppressMessagingToolReplies ? [] : filteredPayloads;
 
   return {

src/auto-reply/reply/agent-runner.ts

@@ -272,7 +272,7 @@ export async function runReplyAgent(params: {
       return finalizeWithFollowup(runOutcome.payload, queueKey, runFollowupTurn);
     }
 
-    const { runResult, fallbackProvider, fallbackModel } = runOutcome;
+    const { runResult, fallbackProvider, fallbackModel, directlySentBlockKeys } = runOutcome;
     let { didLogHeartbeatStrip, autoCompactionCompleted } = runOutcome;
 
     if (
@@ -314,6 +314,7 @@ export async function runReplyAgent(params: {
       didLogHeartbeatStrip,
       blockStreamingEnabled,
       blockReplyPipeline,
+      directlySentBlockKeys,
       replyToMode,
       replyToChannel,
       currentMessageId: sessionCtx.MessageSid,

src/cli/gateway-cli/register.ts

@@ -53,13 +53,6 @@ export function registerGatewayCli(program: Command) {
       ),
   );
 
-  // Back-compat: legacy launchd plists used gateway-daemon; keep hidden alias.
-  addGatewayRunCommand(
-    program
-      .command("gateway-daemon", { hidden: true })
-      .description("Run the WebSocket Gateway as a long-lived daemon"),
-  );
-
   gatewayCallOpts(
     gateway
       .command("call")

src/commands/status-all.ts

@@ -119,10 +119,11 @@ export async function statusAllCommand(
 
     const localFallbackAuth = resolveProbeAuth("local");
     const remoteAuth = resolveProbeAuth("remote");
+    const probeAuth = isRemoteMode && !remoteUrlMissing ? remoteAuth : localFallbackAuth;
 
     const gatewayProbe = await probeGateway({
       url: connection.url,
-      auth: remoteUrlMissing ? localFallbackAuth : remoteAuth,
+      auth: probeAuth,
       timeoutMs: Math.min(5000, opts?.timeoutMs ?? 10_000),
     }).catch(() => null);
     const gatewayReachable = gatewayProbe?.ok === true;
@@ -291,7 +292,7 @@ export async function statusAllCommand(
         ? `unreachable (${gatewayProbe.error})`
         : "unreachable";
     const gatewayAuth = gatewayReachable
-      ? ` · auth ${formatGatewayAuthUsed(remoteUrlMissing ? localFallbackAuth : remoteAuth)}`
+      ? ` · auth ${formatGatewayAuthUsed(probeAuth)}`
       : "";
     const gatewaySelfLine =
       gatewaySelf?.host || gatewaySelf?.ip || gatewaySelf?.version || gatewaySelf?.platform