M56: make RAGcore sync fail closed

PROJECT_STATE.md

@@ -1,5 +1,26 @@
 # Project state
 
+## M56 — make RAGcore procedure sync fail closed (2026-08-24)
+
+- M55 restored private connectivity and RAGcore became reachable/ready from both Fleet Ops
+  API replicas. The repeated live canary then returned honest `insufficient` answers because
+  source-filtered search found no documents, while unfiltered search proved the procedure
+  text itself was indexed under unrelated legacy/upload identities.
+- The active n8n workflow had drifted onto `Fleet Ops Service Token` for the RAGcore upload
+  node instead of the existing `RAGcore Sync Token`. Its summary counted every body without
+  an `error` property as synced, so RAGcore Problem responses were falsely reported as 33
+  successes. No unsafe relaxation of Fleet Ops citation validation was made.
+- The committed workflow now sends the documented stable identity tuple (`source_id`,
+  `external_id`, `locale`), uses the dedicated sync credential by name and counts success
+  only when RAGcore returns a real `AcceptedJob` (`job_id` plus `status_url`). The contract
+  checker enforces all three invariants to prevent recurrence.
+- Validation: workflow JSON parses with the expected credential/fields, `git diff --check`
+  is clean and the OpenAPI/event/MCP/n8n synchronization gate passes against the current
+  source tree.
+- Exact next action: commit/push M56, import the exact workflow while binding the existing
+  RAGcore credential ID without exposing it, publish/execute it, verify all 33 stable source
+  documents through RAGcore and rerun the four live Chromium/Firefox acceptance checks.
+
 ## M55 — restore private cross-project RAGcore routing (2026-08-24)
 
 - M54 promoted successfully as `81e3fd63bdbcb2e9c4ae1d709ea46f40537b6f62`, with two

n8n/workflows/MANIFEST.md

@@ -72,8 +72,8 @@ the same way via the same CLI import path, re-verified.
 | Live workflow ID | `6wbkc4d1AouGpmWT` |
 | Active status (as of 2026-08-05) | **Active / Published** |
 | Error Workflow | `Fleet Ops — Workflow Error Handler` (wired) |
-| Execution telemetry | Successful syncs report both the bounded sync result and the canonical workflow heartbeat. |
+| Execution telemetry | Only a valid RAGcore `AcceptedJob` response counts as synced; HTTP problem bodies count as failed. Fleet Ops separately verifies exact active documents before reporting index health. |
-| Checksum (sha256) | `4afd46b6ef57b7e0a4705611732506d7fcc2a37567266847991b85050e1d37c3` |
+| Checksum (sha256) | `7e9e4beb02a9f9de69efe9f74626e44b6f34f2e0f905229b4605b8cd452b7128` |
 
 ## 4. Fleet Ops — Workflow Error Handler
 

n8n/workflows/fleet-ops-ragcore-procedure-sync.json

@@ -121,6 +121,14 @@
               "name": "source_id",
               "value": "={{ $json.id }}"
             },
+            {
+              "name": "external_id",
+              "value": "={{ $json.document_id + '.md' }}"
+            },
+            {
+              "name": "locale",
+              "value": "={{ $json.language }}"
+            },
             {
               "parameterType": "formBinaryData",
               "name": "file",
@@ -150,7 +158,7 @@
     },
     {
       "parameters": {
-        "jsCode": "const items = $input.all();\nlet synced = 0;\nlet failed = 0;\nfor (const item of items) {\n  if (item.json && item.json.error) {\n    failed += 1;\n  } else {\n    synced += 1;\n  }\n}\nreturn [{ json: { execution_id: String($execution.id), synced, failed } }];"
+        "jsCode": "const items = $input.all();\nlet synced = 0;\nlet failed = 0;\nfor (const item of items) {\n  const body = item && item.json;\n  const accepted = body && typeof body.job_id === 'string' && typeof body.status_url === 'string' && body.status_url.length > 0;\n  if (accepted) {\n    synced += 1;\n  } else {\n    failed += 1;\n  }\n}\nreturn [{ json: { execution_id: String($execution.id), synced, failed } }];"
       },
       "type": "n8n-nodes-base.code",
       "typeVersion": 2,

scripts/check-contracts.py

@@ -109,6 +109,34 @@ def check_workflows(failures: list[str]) -> None:
             fail(f"{filename} contains a cleartext Fleet Ops callback", failures)
         if filename == "fleet-ops-vehicle-return.json":
             check_return_workflow_timing(definition, failures)
+        if filename == "fleet-ops-ragcore-procedure-sync.json":
+            check_ragcore_sync_workflow(definition, failures)
+
+
+def check_ragcore_sync_workflow(definition: dict, failures: list[str]) -> None:
+    """Keep the sync identity stable and reject HTTP error bodies as successful syncs."""
+    nodes_by_name = {node.get("name"): node for node in definition.get("nodes", [])}
+    upload = nodes_by_name.get("Upload to RAGcore", {})
+    credential = upload.get("credentials", {}).get("httpHeaderAuth", {})
+    if credential.get("name") != "RAGcore Sync Token":
+        fail("RAGcore upload must use the dedicated sync credential", failures)
+
+    parameters = upload.get("parameters", {}).get("bodyParameters", {}).get("parameters", [])
+    field_names = {
+        item.get("name") for item in parameters if isinstance(item, dict)
+    }
+    required = {"space_id", "source_id", "external_id", "locale", "file"}
+    if not required.issubset(field_names):
+        fail(
+            "RAGcore upload must preserve source_id, external_id and locale provenance",
+            failures,
+        )
+
+    summary_code = (
+        nodes_by_name.get("Summarize sync result", {}).get("parameters", {}).get("jsCode", "")
+    )
+    if not all(token in summary_code for token in ("job_id", "status_url", "failed += 1")):
+        fail("RAGcore sync summary must accept only a real AcceptedJob response", failures)
 
 
 def check_return_workflow_timing(definition: dict, failures: list[str]) -> None: