diff --git a/packages/casan-harness/scripts/bash/goal-orchestrator.py b/packages/casan-harness/scripts/bash/goal-orchestrator.py
index 09e9590..46863ca 100644
--- a/packages/casan-harness/scripts/bash/goal-orchestrator.py
+++ b/packages/casan-harness/scripts/bash/goal-orchestrator.py
@@ -802,8 +802,13 @@ def run(job_path: str) -> int:
         job = load_json(job_path)
         audit_hash = audit(job, "failed")
         emit(goal_id, "H5-governance", "pass", "Failed decision anchored", {"audit_hash": audit_hash})
-        emit(goal_id, "H6-agentops", "error", "Orchestration failed", {"reason": reason, "latency_ms": int((time.monotonic() - started) * 1000)})
-        emit(goal_id, "H7-orchestration", "blocked", "Goal workflow stopped", {"reason": reason})
+        # Keep gate semantics distinct. H2 may report a patch-contract failure,
+        # while H6/H7 must report their own lifecycle state and retain the H2
+        # error only as causal evidence. Reusing `reason` here made the UI show
+        # goal_patch_missing as if telemetry and orchestration independently
+        # failed the patch contract.
+        emit(goal_id, "H6-agentops", "error", "goal_orchestration_failed", {"root_reason": reason, "latency_ms": int((time.monotonic() - started) * 1000)})
+        emit(goal_id, "H7-orchestration", "blocked", "goal_workflow_stopped", {"root_reason": reason})
         update_job(job_path, audit_hash=audit_hash)
         return 2