diff --git a/.github/scripts/triage_with_llm.py b/.github/scripts/triage_with_llm.py
index 0908c3d76cc..6499a063b39 100644
--- a/.github/scripts/triage_with_llm.py
+++ b/.github/scripts/triage_with_llm.py
@@ -843,8 +843,11 @@ def format_issue_close_comment(verdict: dict) -> str:
         "video, a screenshot, or the exact commands you ran with their real output / "
         "traceback) plus expected vs. actual behavior. Written steps with no run output, "
         "video, or screenshot don't count, and mocked or stubbed runs don't count.\n"
-        "   - For **feature requests**: a concrete description of what should change, plus a "
-        "use case and example (config / API call / UI flow).\n"
+        "   - For **feature requests**: a concrete description of what should change, a "
+        "use case and example (config / API call / UI flow), plus end-to-end evidence of "
+        "the dead-end (a video, a screenshot, or the exact commands you ran with their "
+        "real output showing where the flow stops today). Mocked or stubbed runs don't "
+        "count.\n"
         "2. Comment `@agent-shin reconsider`. I'll re-run triage and reopen the issue if it "
         "now meets the bar. (GitHub doesn't let external authors reopen an issue a maintainer "
         "or bot closed, so the comment-based reconsider is the reliable path.)\n"
@@ -950,8 +953,10 @@ def format_grace_warning_issue_comment(verdict: dict) -> str:
         "screenshot, or the exact commands you ran with their real output / traceback) plus "
         "expected vs. actual behavior. Written steps with no run output don't count, and "
         "mocked or stubbed runs don't count.\n"
-        "- For **feature requests**: a concrete description of what should change, plus a use "
-        "case and example (config / API call / UI flow).\n"
+        "- For **feature requests**: a concrete description of what should change, a use "
+        "case and example (config / API call / UI flow), plus end-to-end evidence of the "
+        "dead-end (a video, a screenshot, or the exact commands you ran with their real "
+        "output showing where the flow stops today). Mocked or stubbed runs don't count.\n"
         "\n"
         "**If the issue does get auto-closed in 2 hours**, comment `@agent-shin reconsider` "
         "and I'll re-evaluate. If it now meets the bar, I'll reopen the issue.\n"
diff --git a/tests/test_litellm/test_github_triage_with_llm.py b/tests/test_litellm/test_github_triage_with_llm.py
index 3172dc93e82..50b198f62c5 100644
--- a/tests/test_litellm/test_github_triage_with_llm.py
+++ b/tests/test_litellm/test_github_triage_with_llm.py
@@ -207,6 +207,23 @@ class TestCloseCommentText:
         assert "end-to-end qa proof" in body.lower()
         assert "mock" in body.lower()
 
+    def test_issue_recovery_comments_should_name_feature_dead_end_evidence(
+        self, triage_module
+    ):
+        # The feature-request pass bar demands end-to-end evidence of the
+        # dead-end, so the close and grace-warning recovery bullets must ask
+        # for it too — otherwise a requester follows those exact instructions
+        # (description + use case only) and fails `reconsider` again with no
+        # hint of what else was needed.
+        verdict = {"verdict": "fail", "missing": [], "explanation": ""}
+        for body in (
+            triage_module.format_issue_close_comment(verdict),
+            triage_module.format_grace_warning_issue_comment(verdict),
+        ):
+            normalized = " ".join(body.split())
+            assert "end-to-end evidence of the dead-end" in normalized
+            assert "showing where the flow stops today" in normalized
+
     def test_all_agent_shin_comments_should_use_bullet_train_emoji(self, triage_module):
         # The bullet train (🚅) is Agent Shin's symbol, matching the LiteLLM
         # logo; the previous wave (👋) was generic and didn't match the bot's