From f8adfcf60eb4331aa9b9c961e15bcc25c71408b6 Mon Sep 17 00:00:00 2001
From: Sebastian <19554889+sebslight@users.noreply.github.com>
Date: Mon, 16 Feb 2026 23:12:06 -0500
Subject: [PATCH] test(agents): cover exec non-zero exits

---
 CHANGELOG.md                      |  1 +
 src/agents/bash-tools.e2e.test.ts | 30 ++++++++++++++++++++++++++++++
 2 files changed, 31 insertions(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 57bcf70614b..de76fbbcdd5 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -59,6 +59,7 @@ Docs: https://docs.openclaw.ai
 - Auto-reply/Subagents: propagate group context (`groupId`, `groupChannel`, `space`) when spawning via `/subagents spawn`, matching tool-triggered subagent spawn behavior.
 - Subagents: cap announce retry loops with max attempts and expiry to prevent infinite retry spam after deferred announces. (#18444)
 - Agents/Tools/exec: add a preflight guard that detects likely shell env var injection (e.g. `$DM_JSON`, `$TMPDIR`) in Python/Node scripts before execution, preventing recurring cron failures and wasted tokens when models emit mixed shell+language source. (#12836)
+- Agents/Tools/exec: treat normal non-zero exit codes as completed and append the exit code to tool output to avoid false tool-failure warnings. (#18425)
 - Agents/Tools: make loop detection progress-aware and phased by hard-blocking known `process(action=poll|log)` no-progress loops, warning on generic identical-call repeats, warning + no-progress-blocking ping-pong alternation loops (10/20), coalescing repeated warning spam into threshold buckets (including canonical ping-pong pairs), adding a global circuit breaker at 30 no-progress repeats, and emitting structured diagnostic `tool.loop` warning/error events for loop actions. (#16808) Thanks @akramcodez and @beca-oc.
 - Agents/Tools: scope the `message` tool schema to the active channel so Telegram uses `buttons` and Discord uses `components`. (#18215) Thanks @obviyus.
 - Agents/Image tool: replace Anthropic-incompatible union schema with explicit `image` (single) and `images` (multi) parameters, keeping tool schemas `anyOf`/`oneOf`/`allOf`-free while preserving multi-image analysis support. (#18551, #18566) Thanks @aldoeliacim.
diff --git a/src/agents/bash-tools.e2e.test.ts b/src/agents/bash-tools.e2e.test.ts
index ac78a40ea29..2650f951cec 100644
--- a/src/agents/bash-tools.e2e.test.ts
+++ b/src/agents/bash-tools.e2e.test.ts
@@ -315,6 +315,36 @@ describe("exec tool backgrounding", () => {
   });
 });
 
+describe("exec exit codes", () => {
+  const originalShell = process.env.SHELL;
+
+  beforeEach(() => {
+    if (!isWin && defaultShell) {
+      process.env.SHELL = defaultShell;
+    }
+  });
+
+  afterEach(() => {
+    if (!isWin) {
+      process.env.SHELL = originalShell;
+    }
+  });
+
+  it("treats non-zero exits as completed and appends exit code", async () => {
+    const command = isWin
+      ? joinCommands(["Write-Output nope", "exit 1"])
+      : joinCommands(["echo nope", "exit 1"]);
+    const result = await execTool.execute("call1", { command });
+
+    expect(result.details.status).toBe("completed");
+    expect(result.details.exitCode).toBe(1);
+
+    const text = normalizeText(result.content.find((c) => c.type === "text")?.text);
+    expect(text).toContain("nope");
+    expect(text).toContain("Command exited with code 1");
+  });
+});
+
 describe("exec notifyOnExit", () => {
   it("enqueues a system event when a backgrounded exec exits", async () => {
     const tool = createExecTool({