diff --git a/server/src/services/native-runtime/native-execution-input.test.ts b/server/src/services/native-runtime/native-execution-input.test.ts
index b0dedfb8464..24079be1cd1 100644
--- a/server/src/services/native-runtime/native-execution-input.test.ts
+++ b/server/src/services/native-runtime/native-execution-input.test.ts
@@ -461,6 +461,8 @@ describe("native execution input external-chat framing", () => {
       runtimeContext: nativeRuntimeContextFixture(),
     });
     expect(input.task.prompt).not.toContain("## Questions that need a user response");
+    expect(input.task.prompt).toContain("Use Paperclip's request_human_input for user questions");
+    expect(input.task.prompt).not.toContain("payload.questionSet");
   });
 
 });
diff --git a/server/src/services/native-runtime/native-execution-input.ts b/server/src/services/native-runtime/native-execution-input.ts
index 427464764d6..5b0f2b1f494 100644
--- a/server/src/services/native-runtime/native-execution-input.ts
+++ b/server/src/services/native-runtime/native-execution-input.ts
@@ -156,6 +156,9 @@ export function buildNativeExecutionInput(input: {
     isPaperclipExternalChatQuestionResponseTurn(wakePayload);
   const taskPrompt = [
     wakePrompt,
+    // Provider-local elicitation can wait without creating a Paperclip card.
+    // Keep routing visible before deferred tool discovery; usage belongs in the tool schema.
+    "Use Paperclip's request_human_input for user questions; provider-local question tools do not reach the Paperclip UI.",
     externalChatTurn && wake?.externalChatProvider === "github"
       ? NATIVE_GITHUB_ATTACHMENT_RECOVERY_GUIDANCE
       : "",
diff --git a/tests/runner-e2e/README.md b/tests/runner-e2e/README.md
index 5220159ff1b..f8de10418f4 100644
--- a/tests/runner-e2e/README.md
+++ b/tests/runner-e2e/README.md
@@ -161,7 +161,7 @@ Both suites save and restore experimental settings. Browser E2E always starts a
 throwaway instance; never point the authenticated suite at the running demo.
 Missing provider credentials fail paid preflight and are not passing coverage.
 
-The default `--all` selection is 160 cells (137 local and 23 Daytona) and 340
+The default `--all` selection is 160 cells (137 local and 23 Daytona) and 344
 expected paid agent turns. The explicit-only everyday suite adds 30 catalog cells
 and is excluded from `--all`. Follow-up steps remain ordered within their cell; all other
 cells are independent. Narrow selectors are strongly recommended while
diff --git a/tests/runner-e2e/catalog.test.ts b/tests/runner-e2e/catalog.test.ts
index 8e7102c08b4..adcc9e8c6d9 100644
--- a/tests/runner-e2e/catalog.test.ts
+++ b/tests/runner-e2e/catalog.test.ts
@@ -68,7 +68,7 @@ describe("runner E2E catalog", () => {
         (total, execution) => total + execution.task.expectedRunCount,
         0,
       ),
-    ).toBe(340);
+    ).toBe(344);
     expect(
       runnerTasks.find((task) => task.id === "plan-revise-accept")
         ?.attemptTimeoutMs,
diff --git a/tests/runner-e2e/continuation-cases.ts b/tests/runner-e2e/continuation-cases.ts
index 8af9308f559..495a047a6bc 100644
--- a/tests/runner-e2e/continuation-cases.ts
+++ b/tests/runner-e2e/continuation-cases.ts
@@ -55,13 +55,15 @@ export const continuationTasks: readonly RunnerTaskFixture[] =
     groups: [],
     workMode: "standard",
     flow: "continuation",
-    expectedRunCount: [
-      "clarification-not-approval",
-      "revision-preserves-approval",
-      "completed-action-resume",
-    ].includes(id)
-      ? 3
-      : 2,
+    expectedRunCount:
+      id === "completed-action-resume"
+        ? 4
+        : [
+              "clarification-not-approval",
+              "revision-preserves-approval",
+            ].includes(id)
+          ? 3
+          : 2,
     attemptTimeoutMs: { local: 10 * 60_000, daytona: 10 * 60_000 },
     expectedTerminalState: { issue: "done", run: "succeeded" },
     buildTitle: (nonce) => `Continuation ${id} ${nonce}`,