fix(kanban): unpack judge_goal's 4-tuple at the completion gate (#67973)

judge_goal() returns (verdict, reason, parse_failed, wait_directive) since
the goals.py wait-directive change, but the kanban goal-mode completion gate
at tools/kanban_tools.py still unpacked 3 values. Every judge call raised
ValueError, the defensive except swallowed it, and the pre-initialized
verdict='done' let every completion through — the acceptance gate was
silently disabled.

Now unpacks all 4 values; the test mock is updated to match the real
contract. The other two judge_goal consumers (hermes_cli/goals.py) already
use 4-value unpacks.

Reported and diagnosed by @bill3wits in PR #57276; reimplemented under
project authorship because the original commit was authored under a
non-existent local identity (bash@hermes.local) that cannot be carried
into history. Also fixes #58066 (duplicate report by @Gibcity).

tests/tools/test_kanban_tools.py

@@ -648,7 +648,9 @@ def test_complete_goal_mode_rejected_by_judge(monkeypatch, tmp_path):
     # Mock the judge to reject the completion. The gate only runs when a
     # judge is reachable, so force the availability probe True as well.
     def mock_judge_goal(goal, last_response, *, timeout=30.0, subgoals=None):
-        return "continue", "missing verification evidence", False
+        # Match the real judge_goal contract:
+        # (verdict, reason, parse_failed, wait_directive)
+        return "continue", "missing verification evidence", False, None
 
     monkeypatch.setattr("tools.kanban_tools.judge_goal", mock_judge_goal)
     monkeypatch.setattr("tools.kanban_tools._goal_judge_available", lambda: True)

tools/kanban_tools.py

@@ -602,7 +602,12 @@ def _handle_complete(args: dict, **kw) -> str:
                 verdict = "done"
                 reason = ""
                 try:
-                    verdict, reason, _ = judge_goal(
+                    # judge_goal returns (verdict, reason, parse_failed,
+                    # wait_directive) — see hermes_cli/goals.py. Unpacking
+                    # fewer raises ValueError, which the defensive handler
+                    # below swallows, leaving verdict="done" and silently
+                    # disabling the gate.
+                    verdict, reason, _, _ = judge_goal(
                         goal=f"{task.title}\n\n{task.body or ''}".strip(),
                         last_response=(summary or result or "").strip(),
                     )