fix: recover tool-result delivery chain after errors

joshavant · joshavant · commit 68adbf58c8ec · 2026-02-19T17:14:23.000-08:00
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -23,6 +23,7 @@ Docs: https://docs.openclaw.ai
 - Discord/Gateway: handle close code 4014 (missing privileged gateway intents) without crashing the gateway. Thanks @thewilloftheshadow.
 - Security/Net: strip sensitive headers (`Authorization`, `Proxy-Authorization`, `Cookie`, `Cookie2`) on cross-origin redirects in `fetchWithSsrFGuard` to prevent credential forwarding across origin boundaries. (#20313) Thanks @afurm.
 - Auto-reply/Runner: emit `onAgentRunStart` only after agent lifecycle or tool activity begins (and only once per run), so fallback preflight errors no longer mark runs as started. (#21165) Thanks @shakkernerd.
+- Auto-reply/Tool results: serialize tool-result delivery and keep the delivery chain progressing after individual failures so concurrent tool outputs preserve user-visible ordering. (#21231) thanks @ahdernasr.
 - Auto-reply/Prompt caching: restore prefix-cache stability by keeping inbound system metadata session-stable and moving per-message IDs (`message_id`, `message_id_full`, `reply_to_id`, `sender_id`) into untrusted conversation context. (#20597) Thanks @anisoptera.
 - CLI/Onboarding: fix Anthropic-compatible custom provider verification by normalizing base URLs to avoid duplicate `/v1` paths during setup checks. (#21336) Thanks @17jmumford.
 - Security/Dependencies: bump transitive `hono` usage to `4.11.10` to incorporate timing-safe authentication comparison hardening for `basicAuth`/`bearerAuth` (`GHSA-gq3j-xvxp-8hrf`). Thanks @vincentkoc.
diff --git a/src/auto-reply/reply/agent-runner-execution.ts b/src/auto-reply/reply/agent-runner-execution.ts
@@ -386,23 +386,25 @@ export async function runAgentTurnWithFallback(params: {
                   // See: https://github.com/openclaw/openclaw/issues/11044
                   let toolResultChain: Promise<void> = Promise.resolve();
                   return (payload: ReplyPayload) => {
-                    const task = (toolResultChain = toolResultChain.then(async () => {
-                      const { text, skip } = normalizeStreamingText(payload);
-                      if (skip) {
-                        return;
-                      }
-                      await params.typingSignals.signalTextDelta(text);
-                      await onToolResult({
-                        text,
-                        mediaUrls: payload.mediaUrls,
-                      });
-                    }))
+                    toolResultChain = toolResultChain
+                      .then(async () => {
+                        const { text, skip } = normalizeStreamingText(payload);
+                        if (skip) {
+                          return;
+                        }
+                        await params.typingSignals.signalTextDelta(text);
+                        await onToolResult({
+                          text,
+                          mediaUrls: payload.mediaUrls,
+                        });
+                      })
                       .catch((err) => {
+                        // Keep chain healthy after an error so later tool results still deliver.
                         logVerbose(`tool result delivery failed: ${String(err)}`);
-                      })
-                      .finally(() => {
-                        params.pendingToolTasks.delete(task);
                       });
+                    const task = toolResultChain.finally(() => {
+                      params.pendingToolTasks.delete(task);
+                    });
                     params.pendingToolTasks.add(task);
                   };
                 })()
diff --git a/src/auto-reply/reply/agent-runner.runreplyagent.test.ts b/src/auto-reply/reply/agent-runner.runreplyagent.test.ts
@@ -562,6 +562,32 @@ describe("runReplyAgent typing (heartbeat)", () => {
     expect(deliveryOrder).toEqual(["first", "second"]);
   });
 
+  it("continues delivering later tool results after an earlier tool result fails", async () => {
+    const delivered: string[] = [];
+    const onToolResult = vi.fn(async (payload: { text?: string }) => {
+      if (payload.text === "first") {
+        throw new Error("simulated delivery failure");
+      }
+      delivered.push(payload.text ?? "");
+    });
+
+    state.runEmbeddedPiAgentMock.mockImplementationOnce(async (params: AgentRunParams) => {
+      void params.onToolResult?.({ text: "first", mediaUrls: [] });
+      void params.onToolResult?.({ text: "second", mediaUrls: [] });
+      await new Promise((r) => setTimeout(r, 50));
+      return { payloads: [{ text: "final" }], meta: {} };
+    });
+
+    const { run } = createMinimalRun({
+      typingMode: "message",
+      opts: { onToolResult },
+    });
+    await run();
+
+    expect(onToolResult).toHaveBeenCalledTimes(2);
+    expect(delivered).toEqual(["second"]);
+  });
+
   it("announces auto-compaction in verbose mode and tracks count", async () => {
     await withTempStateDir(async (stateDir) => {
       const storePath = path.join(stateDir, "sessions", "sessions.json");
