M54: harden operations and demo resilience

scripts/check-contracts.py

@@ -11,6 +11,7 @@ from pathlib import Path
 
 import yaml
 
+from app.core.config import get_settings
 from app.main import app
 
 ROOT = Path(__file__).resolve().parents[1]
@@ -106,6 +107,58 @@ def check_workflows(failures: list[str]) -> None:
         serialized = raw.decode("utf-8")
         if "http://fleetops.itworx.tech" in serialized:
             fail(f"{filename} contains a cleartext Fleet Ops callback", failures)
+        if filename == "fleet-ops-vehicle-return.json":
+            check_return_workflow_timing(definition, failures)
+
+
+def check_return_workflow_timing(definition: dict, failures: list[str]) -> None:
+    """Keep nested retry budgets inside the dispatcher's recoverable delivery lease."""
+    nodes_by_name = {node.get("name"): node for node in definition.get("nodes", [])}
+    validation_code = (
+        nodes_by_name.get("Validate and derive follow-up", {}).get("parameters", {}).get("jsCode", "")
+    )
+    if not all(field in validation_code for field in ("event_id", "correlation_id")):
+        fail(
+            "Vehicle-return workflow must preserve event_id and correlation_id for its callback",
+            failures,
+        )
+    required_nodes = ("Record follow-up", "Report workflow heartbeat")
+    workflow_budget_ms = 0
+    for name in required_nodes:
+        node = nodes_by_name.get(name)
+        if not isinstance(node, dict):
+            fail(f"Vehicle-return workflow is missing timing-critical node {name!r}", failures)
+            return
+        options = node.get("parameters", {}).get("options", {})
+        timeout_ms = options.get("timeout")
+        if node.get("retryOnFail") is not True:
+            fail(f"{name!r} must retain bounded retries", failures)
+            return
+        max_tries = node.get("maxTries")
+        wait_ms = node.get("waitBetweenTries", 0)
+        if not all(
+            isinstance(value, int) and not isinstance(value, bool) and value > 0
+            for value in (timeout_ms, max_tries)
+        ) or (
+            max_tries < 2
+            or not isinstance(wait_ms, int)
+            or isinstance(wait_ms, bool)
+            or wait_ms < 0
+        ):
+            fail(f"{name!r} has an invalid timeout/retry budget", failures)
+            return
+        workflow_budget_ms += timeout_ms * max_tries + wait_ms * (max_tries - 1)
+
+    settings = get_settings()
+    dispatcher_timeout_ms = settings.n8n_http_timeout_seconds * 1000
+    lease_ms = settings.n8n_delivery_lease_seconds * 1000
+    if not workflow_budget_ms < dispatcher_timeout_ms < lease_ms:
+        fail(
+            "Vehicle-return timing contract violated: complete callback/heartbeat retry "
+            f"budget {workflow_budget_ms}ms must be below dispatcher timeout "
+            f"{dispatcher_timeout_ms:g}ms, which must be below delivery lease {lease_ms:g}ms",
+            failures,
+        )
 
 
 def main() -> int:

scripts/check-source-budgets.py

@@ -12,6 +12,7 @@ LINE_LIMITS = {
 }
 BYTE_LIMITS = {
     "frontend/src/styles.css": 78_000,
+    "frontend/src/styles-architecture-flow.css": 9_000,
     "frontend/src/styles-data-quality.css": 8_000,
 }