fix(pi-embedded-runner): suppress incomplete-turn warning after clean messaging-tool delivery

The agent runner was surfacing a '⚠️ Agent couldn't generate a response'
warning even when the assistant had already sent user-visible content
through a messaging tool and the turn ended cleanly. Treat that path as
a successful delivery and skip the warning while keeping real failure
modes (tool errors, stopReason=error, interrupted tool use) intact.

Fixes #70396.

CHANGELOG.md

@@ -45,6 +45,7 @@ Docs: https://docs.openclaw.ai
 - Providers/SDK retry: cap long `Retry-After` sleeps in Stainless-based Anthropic/OpenAI model SDKs so 60s+ retry windows surface immediately for OpenClaw failover instead of blocking the run. (#68474) Thanks @jetd1.
 - Agents/TTS: preserve spoken text in TTS tool results while defusing reply directives in transcript content, so future turns remember voice replies without treating spoken `MEDIA:` or voice tags as delivery metadata. (#68869) Thanks @zqchris.
 - Providers/OpenAI: harden Voice Call realtime transcription against OpenAI Realtime session-update drift, forward language and prompt hints, and add live coverage for realtime STT.
+- Agents/Pi embedded runs: suppress the "⚠️ Agent couldn't generate a response" warning when the assistant already delivered user-visible content through a messaging tool and the turn ended cleanly (`stopReason=stop`/`end_turn`). Real failure modes (tool errors, provider `stopReason=error`, interrupted tool use) still surface the existing "verify before retrying" warning. Fixes #70396.
 - Providers/Moonshot: stop strict-sanitizing Kimi's native tool_call IDs (shaped like `functions.<name>:<index>`) on the OpenAI-compatible transport, so multi-turn agentic flows through Kimi K2.6 no longer break after 2-3 tool-calling rounds when the serving layer fails to match mangled IDs against the original tool definitions. Adds a `sanitizeToolCallIds` opt-out to the shared `openai-compatible` replay family helper and wires Moonshot to it. Fixes #62319. (#70030) Thanks @LeoDu0314.
 - Dependencies/security: override transitive `uuid` to `14.0.0`, clearing the runtime advisory across dependencies.
 - Codex harness: ignore dynamic tool descriptions when deciding whether to reuse a native app-server thread while still fingerprinting tool schemas, so channel-specific copy changes no longer reset otherwise compatible Codex conversations. (#69976) Thanks @chen-zhang-cs-code.

src/agents/pi-embedded-runner/run.incomplete-turn.test.ts

@@ -292,7 +292,7 @@ describe("runEmbeddedPiAgent incomplete-turn safety", () => {
     );
   });
 
-  it("does not retry reasoning-only turns after side effects", async () => {
+  it("does not retry or warn on reasoning-only turns when a messaging tool already delivered", async () => {
     mockedClassifyFailoverReason.mockReturnValue(null);
     mockedRunEmbeddedAttempt.mockResolvedValueOnce(
       makeAttemptResult({
@@ -300,7 +300,7 @@ describe("runEmbeddedPiAgent incomplete-turn safety", () => {
         didSendViaMessagingTool: true,
         lastAssistant: {
           role: "assistant",
-          stopReason: "end_turn",
+          stopReason: "stop",
           provider: "openai",
           model: "gpt-5.4",
           content: [
@@ -322,8 +322,7 @@ describe("runEmbeddedPiAgent incomplete-turn safety", () => {
     });
 
     expect(mockedRunEmbeddedAttempt).toHaveBeenCalledTimes(1);
-    expect(result.payloads?.[0]?.isError).toBe(true);
-    expect(result.payloads?.[0]?.text).toContain("verify before retrying");
+    expect(result.payloads).toBeUndefined();
   });
 
   it("does not retry reasoning-only turns when the assistant ended in error", async () => {
@@ -761,6 +760,49 @@ describe("runEmbeddedPiAgent incomplete-turn safety", () => {
     expect(incompleteTurnText).toBeNull();
   });
 
+  it("suppresses the incomplete-turn warning when a messaging tool delivered and the turn ended cleanly", () => {
+    const incompleteTurnText = resolveIncompleteTurnPayloadText({
+      payloadCount: 0,
+      aborted: false,
+      timedOut: false,
+      attempt: makeAttemptResult({
+        assistantTexts: [],
+        didSendViaMessagingTool: true,
+        lastAssistant: {
+          role: "assistant",
+          stopReason: "stop",
+          provider: "ollama",
+          model: "kimi-k2.6:cloud",
+          content: [],
+        } as unknown as EmbeddedRunAttemptResult["lastAssistant"],
+      }),
+    });
+
+    expect(incompleteTurnText).toBeNull();
+  });
+
+  it("still surfaces the incomplete-turn warning after a messaging tool when the provider signalled an error", () => {
+    const incompleteTurnText = resolveIncompleteTurnPayloadText({
+      payloadCount: 0,
+      aborted: false,
+      timedOut: false,
+      attempt: makeAttemptResult({
+        assistantTexts: [],
+        didSendViaMessagingTool: true,
+        lastAssistant: {
+          role: "assistant",
+          stopReason: "error",
+          provider: "ollama",
+          model: "kimi-k2.6:cloud",
+          errorMessage: "provider failed mid-turn",
+          content: [],
+        } as unknown as EmbeddedRunAttemptResult["lastAssistant"],
+      }),
+    });
+
+    expect(incompleteTurnText).toContain("verify before retrying");
+  });
+
   it("does not retry reasoning-only GPT turns after side effects", () => {
     const retryInstruction = resolveReasoningOnlyRetryInstruction({
       provider: "openai",

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

@@ -20,6 +20,7 @@ type IncompleteTurnAttempt = Pick<
   | "currentAttemptAssistant"
   | "yieldDetected"
   | "didSendDeterministicApprovalPrompt"
+  | "didSendViaMessagingTool"
   | "lastToolError"
   | "lastAssistant"
   | "replayMetadata"
@@ -179,6 +180,19 @@ export function resolveIncompleteTurnPayloadText(params: {
   }
 
   const stopReason = params.attempt.lastAssistant?.stopReason;
+  // If the assistant already delivered user-visible content via a messaging
+  // tool during this turn and ended cleanly (stopReason=stop), do not surface
+  // an incomplete-turn warning. The user has received the reply; a follow-up
+  // "couldn't generate a response" bubble is a false positive. Real failure
+  // modes (tool errors, provider stopReason=error, tool-use interruption)
+  // still fall through to the normal incomplete-turn paths below.
+  if (
+    params.attempt.didSendViaMessagingTool &&
+    !params.attempt.lastToolError &&
+    stopReason === "stop"
+  ) {
+    return null;
+  }
   const incompleteTerminalAssistant = isIncompleteTerminalAssistantTurn({
     hasAssistantVisibleText: params.payloadCount > 0,
     lastAssistant: params.attempt.lastAssistant,