diff --git a/CHANGELOG.md b/CHANGELOG.md
index b715e0bf27a..fd8773edab7 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -170,6 +170,7 @@ Docs: https://docs.openclaw.ai
 - Providers/DeepSeek: expose native DeepSeek V4 `xhigh` and `max` thinking levels through the provider `resolveThinkingProfile` hook so `/think xhigh|max` applies the intended effort instead of falling back to base levels. (#73008) Thanks @ai-hpc.
 - Agents/Codex: bound embedded-run cleanup, trajectory flushing, and command-lane task timeouts after runtime failures, so Discord and other chat sessions return to idle instead of staying stuck in processing. Thanks @vincentkoc.
 - Heartbeat/exec: consume successful metadata-only async exec completions silently so Telegram and other chat surfaces no longer ask users for missing command logs after `No session found`. Fixes #74595. Thanks @gkoch02.
+- Active Memory/Memory: materialize allowlisted memory plugin tools for lightweight embedded recall runs so Memory Core tools do not collapse to an empty runtime allowlist. Fixes #74572. (#74592) Thanks @LaFleurAdvertising and @vyctorbrzezowski.
 - Web fetch: add a documented `tools.web.fetch.ssrfPolicy.allowIpv6UniqueLocalRange` opt-in and thread it through cache keys and DNS/IP checks so trusted fake-IP proxy stacks using `fc00::/7` can work without broad private-network access. Fixes #74351. Thanks @jeffrey701.
 - OpenAI Codex: restore `/verbose full` persistence and app-server tool-output forwarding, and retry Gateway E2E temp-home cleanup so debug runs do not regress on stale validation or cleanup flakes. Thanks @vincentkoc.
 - Anthropic/Meridian: preserve text and thinking content seeded on `content_block_start` in anthropic-messages streams, so `[thinking, text]` replies no longer persist as empty turns or trigger empty-response fallbacks. Fixes #74410. Thanks @vyctorbrzezowski.
diff --git a/extensions/active-memory/index.test.ts b/extensions/active-memory/index.test.ts
index 8dd18a641c1..db134ced46e 100644
--- a/extensions/active-memory/index.test.ts
+++ b/extensions/active-memory/index.test.ts
@@ -1039,6 +1039,7 @@ describe("active-memory plugin", () => {
       "If memory_recall is unavailable, use memory_search and memory_get.",
     );
     expect(runParams?.toolsAllow).toEqual(["memory_recall", "memory_search", "memory_get"]);
+    expect(runParams?.allowGatewaySubagentBinding).toBe(true);
     expect(runParams?.prompt).toContain(
       "When searching for preference or habit recall, use a permissive recall limit or memory_search threshold before deciding that no useful memory exists.",
     );
diff --git a/extensions/active-memory/index.ts b/extensions/active-memory/index.ts
index d8b0194fdfa..24639081981 100644
--- a/extensions/active-memory/index.ts
+++ b/extensions/active-memory/index.ts
@@ -2138,6 +2138,7 @@ async function runRecallSubagent(params: {
       trigger: "manual",
       toolsAllow: ["memory_recall", "memory_search", "memory_get"],
       disableMessageTool: true,
+      allowGatewaySubagentBinding: true,
       bootstrapContextMode: "lightweight",
       verboseLevel: "off",
       thinkLevel: params.config.thinking,
diff --git a/src/agents/pi-embedded-runner/run/attempt.test.ts b/src/agents/pi-embedded-runner/run/attempt.test.ts
index b55712c86cf..31a88f23156 100644
--- a/src/agents/pi-embedded-runner/run/attempt.test.ts
+++ b/src/agents/pi-embedded-runner/run/attempt.test.ts
@@ -30,6 +30,7 @@ import {
   wrapStreamFnSanitizeMalformedToolCalls,
   wrapStreamFnTrimToolCallNames,
 } from "./attempt.js";
+import { buildEmbeddedAttemptToolRunContext } from "./attempt.tool-run-context.js";
 
 type FakeWrappedStream = {
   result: () => Promise<unknown>;
@@ -82,6 +83,24 @@ describe("applyEmbeddedAttemptToolsAllow", () => {
   });
 });
 
+describe("buildEmbeddedAttemptToolRunContext", () => {
+  it("carries runtime toolsAllow into coding tool construction", () => {
+    expect(
+      buildEmbeddedAttemptToolRunContext({
+        trigger: "manual",
+        jobId: "job-1",
+        memoryFlushWritePath: "memory/log.md",
+        toolsAllow: ["memory_search", "memory_get"],
+      }),
+    ).toMatchObject({
+      trigger: "manual",
+      jobId: "job-1",
+      memoryFlushWritePath: "memory/log.md",
+      runtimeToolAllowlist: ["memory_search", "memory_get"],
+    });
+  });
+});
+
 describe("normalizeMessagesForLlmBoundary", () => {
   it("strips tool result details before provider conversion", () => {
     const input = [
diff --git a/src/agents/pi-embedded-runner/run/attempt.tool-run-context.ts b/src/agents/pi-embedded-runner/run/attempt.tool-run-context.ts
index be92832f32d..577fdcea6a1 100644
--- a/src/agents/pi-embedded-runner/run/attempt.tool-run-context.ts
+++ b/src/agents/pi-embedded-runner/run/attempt.tool-run-context.ts
@@ -8,17 +8,20 @@ export function buildEmbeddedAttemptToolRunContext(params: {
   trigger?: EmbeddedRunTrigger;
   jobId?: string;
   memoryFlushWritePath?: string;
+  toolsAllow?: string[];
   trace?: DiagnosticTraceContext;
 }): {
   trigger?: EmbeddedRunTrigger;
   jobId?: string;
   memoryFlushWritePath?: string;
+  runtimeToolAllowlist?: string[];
   trace?: DiagnosticTraceContext;
 } {
   return {
     trigger: params.trigger,
     jobId: params.jobId,
     memoryFlushWritePath: params.memoryFlushWritePath,
+    ...(params.toolsAllow ? { runtimeToolAllowlist: params.toolsAllow } : {}),
     ...(params.trace ? { trace: freezeDiagnosticTraceContext(params.trace) } : {}),
   };
 }
diff --git a/src/agents/pi-tools.create-openclaw-coding-tools.test.ts b/src/agents/pi-tools.create-openclaw-coding-tools.test.ts
index 514a8dc3ee4..78960d20f84 100644
--- a/src/agents/pi-tools.create-openclaw-coding-tools.test.ts
+++ b/src/agents/pi-tools.create-openclaw-coding-tools.test.ts
@@ -1,7 +1,7 @@
 import fs from "node:fs/promises";
 import os from "node:os";
 import path from "node:path";
-import { describe, expect, it } from "vitest";
+import { describe, expect, it, vi } from "vitest";
 import type { OpenClawConfig } from "../config/types.openclaw.js";
 import {
   applyXaiModelCompat,
@@ -12,6 +12,7 @@ import {
 import "./test-helpers/fast-bash-tools.js";
 import "./test-helpers/fast-coding-tools.js";
 import "./test-helpers/fast-openclaw-tools.js";
+import { createOpenClawTools } from "./openclaw-tools.js";
 import { createOpenClawCodingTools } from "./pi-tools.js";
 import { createHostSandboxFsBridge } from "./test-helpers/host-sandbox-fs-bridge.js";
 import { expectReadWriteEditTools } from "./test-helpers/pi-tools-fs-helpers.js";
@@ -163,6 +164,22 @@ describe("createOpenClawCodingTools", () => {
     ).toBeNull();
   });
 
+  it("uses runtime toolsAllow when materializing plugin tools", () => {
+    const createOpenClawToolsMock = vi.mocked(createOpenClawTools);
+    createOpenClawToolsMock.mockClear();
+
+    createOpenClawCodingTools({
+      config: testConfig,
+      runtimeToolAllowlist: ["memory_search", "memory_get"],
+    });
+
+    expect(createOpenClawToolsMock).toHaveBeenCalledWith(
+      expect.objectContaining({
+        pluginToolAllowlist: expect.arrayContaining(["memory_search", "memory_get"]),
+      }),
+    );
+  });
+
   it("preserves action enums in normalized schemas", () => {
     const defaultTools = createOpenClawCodingTools({ config: testConfig, senderIsOwner: true });
     const toolNames = ["canvas", "nodes", "cron", "gateway", "message"];
diff --git a/src/agents/pi-tools.ts b/src/agents/pi-tools.ts
index cfc721d5427..793f948ea59 100644
--- a/src/agents/pi-tools.ts
+++ b/src/agents/pi-tools.ts
@@ -333,6 +333,8 @@ export function createOpenClawCodingTools(options?: {
   hasRepliedRef?: { value: boolean };
   /** Allow plugin tools for this run to late-bind the gateway subagent. */
   allowGatewaySubagentBinding?: boolean;
+  /** Runtime-scoped explicit allowlist used to materialize matching plugin tools. */
+  runtimeToolAllowlist?: string[];
   /** If true, the model has native vision capability */
   modelHasVision?: boolean;
   /** Require explicit message targets (no implicit last-route sends). */
@@ -629,6 +631,7 @@ export function createOpenClawCodingTools(options?: {
         groupPolicy,
         sandboxToolPolicy,
         subagentPolicy,
+        options?.runtimeToolAllowlist ? { allow: options.runtimeToolAllowlist } : undefined,
       ]),
       currentChannelId: options?.currentChannelId,
       currentThreadTs: options?.currentThreadTs,
diff --git a/src/agents/test-helpers/fast-openclaw-tools.ts b/src/agents/test-helpers/fast-openclaw-tools.ts
index aa71bacc98c..fad86a4c05b 100644
--- a/src/agents/test-helpers/fast-openclaw-tools.ts
+++ b/src/agents/test-helpers/fast-openclaw-tools.ts
@@ -46,8 +46,10 @@ const coreTools = [
   stubTool("pdf"),
 ];
 
+const createOpenClawToolsMock = vi.fn(() => coreTools.map((tool) => Object.assign({}, tool)));
+
 vi.mock("../openclaw-tools.js", () => ({
-  createOpenClawTools: () => coreTools.map((tool) => Object.assign({}, tool)),
+  createOpenClawTools: createOpenClawToolsMock,
   __testing: {
     setDepsForTest: () => {},
   },