fix(agents): forward memory flush write path (openclaw#41761)

Merged via squash.

Prepared head SHA: 0a8ebf8
Co-authored-by: frankekn <4488090+frankekn@users.noreply.github.com>
Co-authored-by: frankekn <4488090+frankekn@users.noreply.github.com>
Reviewed-by: @frankekn

Author: frankekn

CHANGELOG.md

@@ -51,6 +51,7 @@ Docs: https://docs.openclaw.ai
 - Tools/web search: recover OpenRouter Perplexity citation extraction from `message.annotations` when chat-completions responses omit top-level citations. (#40881) Thanks @laurieluo.
 - Security/external content: treat whitespace-delimited `EXTERNAL UNTRUSTED CONTENT` boundary markers like underscore-delimited variants so prompt wrappers cannot bypass marker sanitization. (#35983) Thanks @urianpaul94.
 - Telegram/network env-proxy: apply configured transport policy to proxied HTTPS dispatchers as well as direct `NO_PROXY` bypasses, so resolver-scoped IPv4 fallback and network settings work consistently for env-proxied Telegram traffic. (#40740) Thanks @sircrumpet.
+- Agents/memory flush: forward `memoryFlushWritePath` through `runEmbeddedPiAgent` so memory-triggered flush turns keep the append-only write guard without aborting before tool setup. Follows up on #38574. (#41761) Thanks @frankekn.
 
 ## 2026.3.8
 

src/agents/pi-embedded-runner/run.ts

@@ -850,6 +850,7 @@ export async function runEmbeddedPiAgent(
             sessionId: params.sessionId,
             sessionKey: params.sessionKey,
             trigger: params.trigger,
+            memoryFlushWritePath: params.memoryFlushWritePath,
             messageChannel: params.messageChannel,
             messageProvider: params.messageProvider,
             agentAccountId: params.agentAccountId,

src/agents/pi-embedded-runner/usage-reporting.test.ts

@@ -79,6 +79,36 @@ describe("runEmbeddedPiAgent usage reporting", () => {
     );
   });
 
+  it("forwards memory flush write paths into memory-triggered attempts", async () => {
+    mockedRunEmbeddedAttempt.mockResolvedValueOnce({
+      aborted: false,
+      promptError: null,
+      timedOut: false,
+      sessionIdUsed: "test-session",
+      assistantTexts: [],
+      // eslint-disable-next-line @typescript-eslint/no-explicit-any
+    } as any);
+
+    await runEmbeddedPiAgent({
+      sessionId: "test-session",
+      sessionKey: "test-key",
+      sessionFile: "/tmp/session.json",
+      workspaceDir: "/tmp/workspace",
+      prompt: "flush",
+      timeoutMs: 30000,
+      runId: "run-memory-forwarding",
+      trigger: "memory",
+      memoryFlushWritePath: "memory/2026-03-10.md",
+    });
+
+    expect(mockedRunEmbeddedAttempt).toHaveBeenCalledWith(
+      expect.objectContaining({
+        trigger: "memory",
+        memoryFlushWritePath: "memory/2026-03-10.md",
+      }),
+    );
+  });
+
   it("reports total usage from the last turn instead of accumulated total", async () => {
     // Simulate a multi-turn run result.
     // Turn 1: Input 100, Output 50. Total 150.