chore: bump SDK deps (software-agent-sdk 1.44.0, automation 1.9.0, extensions 0.19.0) (#16968)

Co-authored-by: openhands <openhands@all-hands.dev>

tests/e2e/mock-llm/automations/mock-llm-automation.spec.ts

@@ -156,23 +156,54 @@ async function listAutomationRuns(
   return resp.json();
 }
 
+interface AutomationRunRecord {
+  id: string;
+  status: string;
+  conversation_id: string | null;
+  error_detail?: string | null;
+}
+
+/** Statuses a run never leaves (see RunStatus in openhands-automation). */
+const TERMINAL_RUN_STATUSES = new Set([
+  "COMPLETED",
+  "FAILED",
+  "CANCELLED",
+  "SKIPPED",
+]);
+
 /**
  * Poll until a run reaches the expected status or times out.
+ *
+ * Fails fast, quoting the backend's `error_detail`, once every run has ended
+ * in some other terminal status — polling on would only surface a timeout
+ * and hide why the run actually stopped.
  */
 async function waitForRunStatus(
   request: import("@playwright/test").APIRequestContext,
   automationId: string,
   expectedStatus: string,
   timeoutMs = 30_000,
-) {
+): Promise<AutomationRunRecord> {
   const deadline = Date.now() + timeoutMs;
   while (Date.now() < deadline) {
     const data = await listAutomationRuns(request, automationId);
-    const runs = data.runs ?? data.items ?? [];
-    const match = runs.find(
-      (r: { status: string }) => r.status === expectedStatus,
-    );
+    const runs: AutomationRunRecord[] = data.runs ?? data.items ?? [];
+    const match = runs.find((r) => r.status === expectedStatus);
     if (match) return match;
+    if (
+      runs.length > 0 &&
+      runs.every((r) => TERMINAL_RUN_STATUSES.has(r.status))
+    ) {
+      const summary = runs
+        .map(
+          (r) =>
+            `${r.id}=${r.status}${r.error_detail ? ` (${r.error_detail})` : ""}`,
+        )
+        .join(", ");
+      throw new Error(
+        `No run reached "${expectedStatus}"; every run already ended: ${summary}`,
+      );
+    }
     await new Promise((r) => setTimeout(r, 1_000));
   }
   throw new Error(

tests/e2e/mock-llm/scripts/mock-llm-server.py

@@ -33,6 +33,11 @@ from openhands.sdk.testing import TestLLM, TestLLMExhaustedError
 BASH_TOKEN = "MOCK_LLM_E2E_BASH_OK"
 REPLY_TOKEN = "MOCK_LLM_E2E_REPLY_OK"
 
+# The user turn the agent-server sends when it pre-flights a saved LLM profile
+# (POST /api/profiles/{name}/validate, agent-server >= 1.43). Matched by
+# _is_preflight_ping() so the check never touches the scripted trajectory.
+PREFLIGHT_PING_TEXT = "ping"
+
 # SDK exception → (HTTP status, OpenAI error type)
 ERROR_MAP: dict[type, tuple[int, str]] = {
     LLMAuthenticationError: (401, "invalid_api_key"),
@@ -162,6 +167,23 @@ class MockLLMHandler(BaseHTTPRequestHandler):
         length = int(self.headers.get("Content-Length", 0))
         body = json.loads(self.rfile.read(length)) if length else {}
 
+        # ── Profile pre-flight ping ──
+        # Saving a profile against agent-server >= 1.43 fires a 1-token "ping"
+        # completion through the submitted config, and the canvas waits at
+        # most 30 s for the verdict. Answer it here instead of feeding it to
+        # TestLLM: it would otherwise consume a scripted turn, and once the
+        # trajectory is exhausted the 500 below makes the SDK retry with
+        # backoff until the canvas gives up — leaving the profile editor stuck
+        # on "Validating...". It stays out of the request history, which tests
+        # read for the conversation's own completions.
+        if _is_preflight_ping(body):
+            raw = _preflight_pong(body.get("model"))
+            if body.get("stream"):
+                self._send_streaming(raw)
+            else:
+                self._send_json(200, raw)
+            return
+
         # Append to request history for test verification.
         # Tests can GET /admin/requests to confirm image content was included.
         with self._lock:
@@ -338,6 +360,53 @@ class MockLLMHandler(BaseHTTPRequestHandler):
         print(f"[mock-llm] {args[0]}", file=sys.stderr, flush=True)
 
 
+def _is_preflight_ping(body: dict) -> bool:
+    """Match the agent-server's profile pre-flight check.
+
+    It is a single user message saying "ping" with ``max_tokens=1`` (see
+    ``profiles_router.validate_profile`` in openhands-agent-server). The text
+    arrives either as a plain string or as OpenAI content parts.
+    """
+    if body.get("max_tokens") != 1:
+        return False
+    messages = body.get("messages")
+    if not isinstance(messages, list) or len(messages) != 1:
+        return False
+    message = messages[0]
+    if not isinstance(message, dict) or message.get("role") != "user":
+        return False
+    content = message.get("content")
+    if isinstance(content, list):
+        content = "".join(
+            part.get("text", "")
+            for part in content
+            if isinstance(part, dict) and part.get("type") == "text"
+        )
+    return isinstance(content, str) and content.strip() == PREFLIGHT_PING_TEXT
+
+
+def _preflight_pong(model: str | None) -> dict:
+    """Minimal OpenAI-style completion for the pre-flight ping.
+
+    Uses the raw shape ``_send_streaming`` also understands, so the reply works
+    whether or not the caller asked for streaming.
+    """
+    return {
+        "id": "chatcmpl-mock-preflight",
+        "object": "chat.completion",
+        "created": int(time.time()),
+        "model": model or "mock-preflight",
+        "choices": [
+            {
+                "index": 0,
+                "message": {"role": "assistant", "content": "pong"},
+                "finish_reason": "stop",
+            }
+        ],
+        "usage": {"prompt_tokens": 1, "completion_tokens": 1, "total_tokens": 2},
+    }
+
+
 def _parse_trajectory_turns(raw_turns: list[dict]) -> list[Message | Exception]:
     """Convert JSON turn descriptors into Message objects.
 

tests/e2e/mock-llm/settings/mock-llm-profile-management.spec.ts

@@ -410,6 +410,21 @@ test.describe("OpenHands provider hidden base_url preservation", () => {
     // Advanced view. The value becomes hidden after switching to Basic, but it
     // is still part of the profile unless the model changes. ──
     await routeSessionApiKey(page);
+    // agent-server >= 1.43 pre-flights every profile save with a 1-token
+    // completion through the submitted config. CUSTOM_BASE_URL is a
+    // placeholder host by design — this test is about the value surviving a
+    // Basic-view re-save, not about reaching it — so answer the check from
+    // the browser instead of letting the SDK retry an unreachable host past
+    // the canvas's 30 s validation budget. Registered after
+    // routeSessionApiKey(): Playwright routes are LIFO, and that handler
+    // `continue()`s every backend request it sees first.
+    await page.route("**/api/profiles/*/validate", (route) =>
+      route.fulfill({
+        status: 200,
+        contentType: "application/json",
+        body: JSON.stringify({ valid: true, error: null }),
+      }),
+    );
     await ensureMockLLMAgentProfile(page.request);
     await page.goto("/settings/llm", { waitUntil: "domcontentloaded" });
     await dismissAnalyticsModal(page);