From d878cf026c558cc5b381249d225cc29f6c1f25b7 Mon Sep 17 00:00:00 2001
From: Neerav Makwana <261249544+neeravmakwana@users.noreply.github.com>
Date: Wed, 22 Apr 2026 21:33:10 -0400
Subject: [PATCH] fix(pi-embedded-runner): address greptile review on
 incomplete-turn gate

- Drop redundant !lastToolError check from the messaging-tool clean-stop
  early return; the earlier lastToolError early return already handles
  that case, so the extra condition was dead and misleading.
- Update the CHANGELOG entry to reference only stopReason=stop; the pi-ai
  StopReason type does not include end_turn, so the earlier mention was
  a documentation-only discrepancy.
---
 CHANGELOG.md                                        |  2 +-
 .../pi-embedded-runner/run/incomplete-turn.ts       | 13 +++++--------
 2 files changed, 6 insertions(+), 9 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index b07777bdbdf..e00b46d2490 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -45,7 +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.
+- 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`). Real failure modes (tool errors, provider `stopReason=error`, interrupted tool use) still surface the existing "verify before retrying" warning. Fixes #70396. (#70425) Thanks @neeravmakwana.
 - 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.
diff --git a/src/agents/pi-embedded-runner/run/incomplete-turn.ts b/src/agents/pi-embedded-runner/run/incomplete-turn.ts
index 02e1ad863a4..961b5b8fddd 100644
--- a/src/agents/pi-embedded-runner/run/incomplete-turn.ts
+++ b/src/agents/pi-embedded-runner/run/incomplete-turn.ts
@@ -183,14 +183,11 @@ export function resolveIncompleteTurnPayloadText(params: {
   // 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"
-  ) {
+  // "couldn't generate a response" bubble is a false positive. Provider-side
+  // failures (stopReason=error, toolUse interruption) still fall through to
+  // the normal incomplete-turn paths below; tool-error cases are already
+  // handled by the lastToolError early return above.
+  if (params.attempt.didSendViaMessagingTool && stopReason === "stop") {
     return null;
   }
   const incompleteTerminalAssistant = isIncompleteTerminalAssistantTurn({