From 821b5d6c892186489b3c9c1bf74add5b251c1f3a Mon Sep 17 00:00:00 2001
From: tegwick <bernd.worsch@gmail.com>
Date: Sun, 21 Jun 2026 20:56:35 +0200
Subject: [PATCH] fix(STATE-WP-0064): parse consistency sweep stdout with skip
 prefixes

Extract the JSON payload from mixed script output and document Railiance01
kubectl sync steps. Mark T02 done after cluster bridge and resolver canaries.
---
 api/services/consistency_sweep.py             | 18 ++++++++++-
 docs/consistency-sweep-runbook.md             | 32 ++++++++++++-------
 tests/test_consistency_sweep.py               | 12 +++++++
 ...4-statehub-consistency-sync-railiance01.md | 14 +++++++-
 4 files changed, 62 insertions(+), 14 deletions(-)

diff --git a/api/services/consistency_sweep.py b/api/services/consistency_sweep.py
index b5f9e69..7bafaf5 100644
--- a/api/services/consistency_sweep.py
+++ b/api/services/consistency_sweep.py
@@ -50,11 +50,27 @@ def _parse_stderr(stderr: str) -> dict[str, list[str]]:
     }
 
 
+def _extract_json_payload(text: str) -> Any:
+    stripped = text.strip()
+    if not stripped:
+        return []
+    decoder = json.JSONDecoder()
+    for index, char in enumerate(stripped):
+        if char not in "{[":
+            continue
+        try:
+            payload, _end = decoder.raw_decode(stripped, index)
+            return payload
+        except json.JSONDecodeError:
+            continue
+    raise json.JSONDecodeError("No JSON payload found", stripped, 0)
+
+
 def _parse_stdout(stdout: str) -> list[ConsistencySweepRepoResult]:
     text = stdout.strip()
     if not text:
         return []
-    payload = json.loads(text)
+    payload = _extract_json_payload(text)
     items = payload if isinstance(payload, list) else [payload]
     results: list[ConsistencySweepRepoResult] = []
     for item in items:
diff --git a/docs/consistency-sweep-runbook.md b/docs/consistency-sweep-runbook.md
index 6b20686..ca226d3 100644
--- a/docs/consistency-sweep-runbook.md
+++ b/docs/consistency-sweep-runbook.md
@@ -33,23 +33,31 @@ service target).
 From the activity-core host, confirm the definition is synced and the
 Temporal schedule exists:
 
-```bash
-cd ~/activity-core
-ACTIVITY_DEFINITION_DIRS=/home/worsch/the-custodian make sync-activity-definitions
-```
-
-Reconcile Temporal schedules (pick one):
+Run on **Railiance01** (the laptop `.env` points at docker-compose hostnames
+like `app-db` and will time out from WSL):
 
 ```bash
-# Preferred when activity-core API is up (no worker restart)
-curl -s -X POST 'http://localhost:8010/admin/sync?definitions=true&schedules=true'
+export KUBECONFIG=~/.kube/config-hosteurope
 
-# CLI fallback
-ACTCORE_DB_URL=... TEMPORAL_HOST=... uv run python -m activity_core.sync_schedules
+# 1. Apply runtime manifest when definitions change
+kubectl apply -f ~/activity-core/k8s/railiance/20-runtime.yaml
+
+# 2. Sync definitions into Postgres
+kubectl -n activity-core delete job actcore-sync --ignore-not-found
+kubectl apply -f ~/activity-core/k8s/railiance/20-runtime.yaml
+kubectl -n activity-core wait --for=condition=complete job/actcore-sync --timeout=180s
+
+# 3. Reconcile Temporal schedules
+kubectl -n activity-core exec deploy/actcore-worker -- python -m activity_core.sync_schedules
 ```
 
-On Railiance01, use the in-cluster activity-core API URL and env from the
-deployment instead of `localhost:8010`.
+After changing application code, rebuild and import `activity-core:railiance01-prod`
+per `activity-core/k8s/railiance/README.md`, then restart
+`actcore-worker`, `actcore-api`, and `actcore-event-router`.
+
+Ensure `state-hub-railiance01` ops-bridge tunnel is `connected` before
+cluster-triggered sweeps; the in-cluster bridge proxy allows up to 360s for
+POST requests.
 
 Expected definition:
 
diff --git a/tests/test_consistency_sweep.py b/tests/test_consistency_sweep.py
index c6958d4..490c000 100644
--- a/tests/test_consistency_sweep.py
+++ b/tests/test_consistency_sweep.py
@@ -97,6 +97,18 @@ def test_parse_stderr_extracts_skip_lists():
     }
 
 
+def test_extract_json_payload_skips_human_readable_prefix_lines():
+    stdout = (
+        "  CLEAN (skipped): quiet-repo\n"
+        "  BUDGET EXHAUSTED after 30s (skipped): other-repo\n"
+        '{\n  "repo_slug": "state-hub",\n  "repo_path": "/home/worsch/state-hub",\n'
+        '  "result": "pass",\n  "summary": {"fail": 0, "warn": 0, "info": 0},\n'
+        '  "fixes_applied": []\n}\n'
+    )
+    payload = sweep_service._extract_json_payload(stdout)
+    assert payload["repo_slug"] == "state-hub"
+
+
 def test_parse_stdout_handles_single_and_batch_payloads():
     single = json.dumps(
         {
diff --git a/workplans/STATE-WP-0064-statehub-consistency-sync-railiance01.md b/workplans/STATE-WP-0064-statehub-consistency-sync-railiance01.md
index 11314a5..f86f4d4 100644
--- a/workplans/STATE-WP-0064-statehub-consistency-sync-railiance01.md
+++ b/workplans/STATE-WP-0064-statehub-consistency-sync-railiance01.md
@@ -92,7 +92,7 @@ Done 2026-06-21:
 
 ```task
 id: STATE-WP-0064-T02
-status: todo
+status: done
 priority: high
 state_hub_task_id: "2e9b5b66-a7b1-46a5-8e1f-22e6b5caeff6"
 ```
@@ -104,6 +104,18 @@ Trigger one manual ActivityRun. Confirm:
 - progress or activity-core run history shows success
 - no duplicate side-effects when local timer also fires (idempotent)
 
+Done 2026-06-21:
+
+- Applied `20-runtime.yaml` on Railiance01; `actcore-sync` upserted definition
+  `7c4e9a12-8f3b-4d5e-9c6a-1b2d3e4f5a6b` (paused schedule).
+- Rebuilt/imported `activity-core:railiance01-prod` with
+  `consistency_sweep_remote_all` resolver.
+- Bridge proxy POST timeout raised to 360s (30s was aborting sweeps).
+- Manual canaries: cluster POST via bridge (`exit_code 0`, progress event
+  `65d0bc12-…`) and worker resolver (`exit_code 0`, 1 repo @ 60s budget).
+- Laptop `make sync-activity-definitions` is not valid against Railiance01 DB;
+  use kubectl `actcore-sync` job instead.
+
 ## T3 — Parallel run and observability
 
 ```task