From a03ee0c72ce8d57c969811328732f97a5052cc8a Mon Sep 17 00:00:00 2001
From: chenanran555 <car534511@alibaba-inc.com>
Date: Mon, 27 Jul 2026 20:23:21 +0800
Subject: [PATCH] fix(agent): timeout error

---
 .../commands/managed-agent/_engine/errors.ts  | 40 +++++++++++++++----
 .../tests/managed-agent-errors.test.ts        | 16 ++++++++
 2 files changed, 48 insertions(+), 8 deletions(-)

diff --git a/packages/commands/src/commands/managed-agent/_engine/errors.ts b/packages/commands/src/commands/managed-agent/_engine/errors.ts
index 32c5c9c..f22571c 100644
--- a/packages/commands/src/commands/managed-agent/_engine/errors.ts
+++ b/packages/commands/src/commands/managed-agent/_engine/errors.ts
@@ -33,23 +33,47 @@ function parseSdkResponseBody(raw: string): ApiErrorBody {
   return { message: raw.trim() || undefined };
 }
 
+/**
+ * The SDK's session polling deadline surfaces as a plain `UserError` (no
+ * dedicated timeout class as of SDK 0.3.x), so it is recognized by its stable
+ * message shape: "Session did not complete within the timeout (N seconds)."
+ * (session-runtime's assertNotTimedOut — the SDK's only timeout UserError).
+ * It is a client-side wait limit, not a usage mistake → per bl's error
+ * boundary it must exit TIMEOUT, not USAGE.
+ */
+function isSdkPollingTimeout(error: UserError): boolean {
+  return /did not complete within the timeout/i.test(error.message);
+}
+
 /**
  * Run an SDK-backed operation, translating SDK error types into BailianError so
  * bl's error handler produces the right exit code and hint formatting.
- * SDK `UserError` → USAGE; SDK `ApiError` (server HTTP error) → GENERAL via
- * `mapApiError` (server message passed through verbatim, with
- * httpStatus/apiCode/requestId metadata for --output json); fetch transport
- * failures (`TypeError: fetch failed`) are rethrown untouched so the runtime
- * error handler maps them to NETWORK with an errno-specific hint, matching the
- * native client path; any other Error → GENERAL (message passed through, per
- * bl's "don't translate server errors" boundary).
+ * SDK `UserError` → USAGE — except the polling-deadline UserError, which is a
+ * client-side timeout → TIMEOUT with a wait-longer hint; SDK `ApiError`
+ * (server HTTP error) → GENERAL via `mapApiError` (server message passed
+ * through verbatim, with httpStatus/apiCode/requestId metadata for
+ * --output json); fetch transport failures (`TypeError: fetch failed`) are
+ * rethrown untouched so the runtime error handler maps them to NETWORK with an
+ * errno-specific hint, matching the native client path; any other Error →
+ * GENERAL (message passed through, per bl's "don't translate server errors"
+ * boundary).
  */
 export async function withAgentErrors<T>(fn: () => Promise<T>): Promise<T> {
   try {
     return await fn();
   } catch (error) {
     if (error instanceof BailianError) throw error;
-    if (error instanceof UserError) throw new BailianError(error.message, ExitCode.USAGE);
+    if (error instanceof UserError) {
+      if (isSdkPollingTimeout(error)) {
+        throw new BailianError(
+          error.message,
+          ExitCode.TIMEOUT,
+          // `bl` prefix is safe: agent commands ship on `bl` only.
+          "The session may still be running — check `bl managed-agent session get --session-id <id>` or `session events`.",
+        );
+      }
+      throw new BailianError(error.message, ExitCode.USAGE);
+    }
     if (error instanceof Error && isSdkApiError(error)) {
       throw mapApiError(error.statusCode, parseSdkResponseBody(error.responseBody));
     }
diff --git a/packages/commands/tests/managed-agent-errors.test.ts b/packages/commands/tests/managed-agent-errors.test.ts
index 238cb7e..8af71b7 100644
--- a/packages/commands/tests/managed-agent-errors.test.ts
+++ b/packages/commands/tests/managed-agent-errors.test.ts
@@ -39,6 +39,22 @@ test("SDK UserError maps to USAGE", async () => {
   expect(mapped.message).toBe("bad agents.yaml");
 });
 
+test("SDK polling-timeout UserError maps to TIMEOUT (5), not USAGE", async () => {
+  // 消息形状来自 SDK session-runtime 的 assertNotTimedOut —— 客户端等待超时，
+  // 按 bl 错误边界必须归 TIMEOUT，不能告诉自动化调用方“参数错误”。
+  const mapped = await catchMapped(
+    new UserError("Session did not complete within the timeout (600 seconds)."),
+  );
+  expect(mapped.exitCode).toBe(ExitCode.TIMEOUT);
+  expect(mapped.message).toBe("Session did not complete within the timeout (600 seconds).");
+  expect(mapped.hint).toMatch(/session get/);
+});
+
+test("提及 timeout 但非轮询超时句式的 UserError 仍归 USAGE", async () => {
+  const mapped = await catchMapped(new UserError("Invalid timeout value in agents.yaml"));
+  expect(mapped.exitCode).toBe(ExitCode.USAGE);
+});
+
 test("SDK ApiError with DashScope-style JSON body surfaces clean message and api metadata", async () => {
   const body = JSON.stringify({
     code: "InvalidParameter",