fix(goals): update judge consumers for transport result

tests/hermes_cli/test_goals.py

@@ -438,9 +438,12 @@ class TestJudgeParseFailureAutoPause:
             "agent.auxiliary_client.call_llm",
             side_effect=RuntimeError("connection reset"),
         ):
-            verdict, _, parse_failed, _wd, _tf = goals.judge_goal("goal", "response")
+            verdict, _, parse_failed, _wd, transport_failed = goals.judge_goal(
+                "goal", "response"
+            )
         assert verdict == "continue"
         assert parse_failed is False
+        assert transport_failed is True
 
     def test_empty_judge_reply_flagged_as_parse_failure(self):
         """End-to-end: judge returns empty content → parse_failed=True."""
@@ -507,24 +510,44 @@ class TestJudgeParseFailureAutoPause:
             assert d["should_continue"] is True
             assert mgr.state.consecutive_parse_failures == 0
 
-    def test_parse_failure_counter_not_incremented_by_api_errors(self, hermes_home):
-        """API/transport errors must NOT count toward the auto-pause threshold."""
+    def test_transport_failures_do_not_increment_parse_counter(self, hermes_home):
+        """Transport failures use their own counter and a good reply resets both."""
         from hermes_cli import goals
         from hermes_cli.goals import GoalManager
 
         mgr = GoalManager(session_id="parse-fail-sid-3", default_max_turns=20)
         mgr.set("goal")
+        assert mgr.state is not None
 
         with patch.object(
-            goals, "judge_goal", return_value=("continue", "judge error: RuntimeError", False, None, False)
-        ): 
-            for _ in range(5):
+            goals,
+            "judge_goal",
+            return_value=(
+                "continue",
+                "judge error: RuntimeError",
+                False,
+                None,
+                True,
+            ),
+        ):
+            for _ in range(2):
                 d = mgr.evaluate_after_turn("still going")
                 assert d["should_continue"] is True
             assert mgr.state.consecutive_parse_failures == 0
-            assert mgr.state.consecutive_transport_failures == 0
+            assert mgr.state.consecutive_transport_failures == 2
             assert mgr.state.status == "active"
 
+        with patch.object(
+            goals,
+            "judge_goal",
+            return_value=("continue", "making progress", False, None, False),
+        ):
+            d = mgr.evaluate_after_turn("recovered")
+
+        assert d["should_continue"] is True
+        assert mgr.state.consecutive_parse_failures == 0
+        assert mgr.state.consecutive_transport_failures == 0
+
     def test_consecutive_parse_failures_persists_across_goalmanager_reloads(
         self, hermes_home
     ):

tests/hermes_cli/test_kanban_goal_mode.py

@@ -181,8 +181,8 @@ def _patch_judge(monkeypatch, verdicts):
 
     def _fake_judge(goal, response, subgoals=None, background_processes=None, **_kw):
         v = seq.pop(0) if seq else "done"
-        # 4-tuple contract: (verdict, reason, parse_failed, wait_directive)
-        return v, f"scripted:{v}", False, None
+        # 5-tuple contract: verdict, reason, parse failure, wait, transport failure.
+        return v, f"scripted:{v}", False, None, False
 
     monkeypatch.setattr(goals, "judge_goal", _fake_judge)
 

tests/tools/test_kanban_tools.py

@@ -649,8 +649,8 @@ def test_complete_goal_mode_rejected_by_judge(monkeypatch, tmp_path):
     # judge is reachable, so force the availability probe True as well.
     def mock_judge_goal(goal, last_response, *, timeout=30.0, subgoals=None):
         # Match the real judge_goal contract:
-        # (verdict, reason, parse_failed, wait_directive)
-        return "continue", "missing verification evidence", False, None
+        # (verdict, reason, parse_failed, wait_directive, transport_failed)
+        return "continue", "missing verification evidence", False, None, False
 
     monkeypatch.setattr("tools.kanban_tools.judge_goal", mock_judge_goal)
     monkeypatch.setattr("tools.kanban_tools._goal_judge_available", lambda: True)

tools/kanban_tools.py

@@ -603,11 +603,11 @@ def _handle_complete(args: dict, **kw) -> str:
                 reason = ""
                 try:
                     # 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(
+                    # wait_directive, transport_failed) — 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(),
                     )