KES Live Cutover Window
Exact Env Change Used
The live API seam was changed in services/api/.env:
- before effective fallback mode: no override, or explicit fallback override to
Resolving locale, route permissions, and workspace projection.
Current scope: Guest
Category: 10_normative | Version: v1.0.0
Owner: DOCUMENT_CUSTODIAN | Review cycle: 90 days
Approval authority: GOVERNANCE_ADMIN
Documentation portal is read-only. Editing and mutation endpoints are disabled.
Kvary platform is originally created in Georgian. Where a Georgian version exists, Georgian is authoritative for platform UI, documentation, and legal interpretation.
Translations into other languages are provided for convenience. Some records may originate in other languages and carry their own source or legal locale for a specific flow, but where a Georgian version is available, the Georgian version prevails for platform-level wording and interpretation.
Metadata incomplete: Document ID, Version, Status, Owner Role, Last Review Date, Next Review Date, Change Log
The live API seam was changed in services/api/.env:
KES_ORCHESTRATOR_SERVICE_URLhttp://localhost:4020KES_ORCHESTRATOR_SERVICE_URL=http://localhost:4025Canonical extracted KES runtime target remains:
http://localhost:4025Because the local Node/npm wrapper is still broken in this shell, the live window was executed against the real repo dist servers in a Docker-backed localhost stack:
:4100:4020svc-kes host on :4025:4001The API route family stayed unchanged:
/api/v1/kes/orchestrator/*The live API was first started with the fallback override:
KES_ORCHESTRATOR_SERVICE_URL=http://localhost:4020This verified that the live stack still worked against the old colocated KES host before the cutover flip.
Only the API was restarted.
The restart used the repo env file with:
KES_ORCHESTRATOR_SERVICE_URL=http://localhost:4025No gateway route definitions changed.
No auth middleware changed.
Old colocated KES hosting remained up on :4020.
Pre-cutover fallback confirmation:
GET /api/v1/healthGET /api/v1/kes/orchestrator/cases?page=1&pageSize=1GET /api/v1/kes/orchestrator/control-planeGET /api/v1/kes/orchestrator/process-mapGET /api/v1/kes/orchestrator/suggestions?stakeholderId=...&limit=1PUT /api/v1/kes/orchestrator/process-mapPUT /api/v1/kes/orchestrator/process-mapPOST /api/v1/kes/orchestrator/casesPost-cutover live checks:
GET /api/v1/healthGET /api/v1/kes/orchestrator/cases?page=1&pageSize=1GET /api/v1/kes/orchestrator/control-planeGET /api/v1/kes/orchestrator/process-mapGET /api/v1/kes/orchestrator/suggestions?stakeholderId=...&limit=1PUT /api/v1/kes/orchestrator/process-mapPUT /api/v1/kes/orchestrator/process-mapPOST /api/v1/kes/orchestrator/casesFallback mode worked.
Cutover mode worked after restarting only the API.
Observed post-cutover status set:
200200200200401 missing_bearer_token200201The cutover remained in place.
No serious mismatch was found, so rollback was not needed during the window.
The old colocated KES host stayed available on :4020 throughout the window for immediate fallback if needed.