qonto-assistant/railiance/app.toml
tegwick 9fbcef7b05 QONTO-WP-0004-T06: draft isolation placement manifests + railiance/app.toml
Concrete, reviewable placement request per docs/SecurityPractice.md #7
(I1 Reinforced minimum: dedicated node pool/namespace, given internet
reachability via the facade and sole custody of the bank credential).

deploy/k8s/qonto-assistant/: modeled on llm-connect's real deployment
(deploy/k8s/activity-core-llm-connect/) but tightened -- dedicated
namespace (not shared), Deployment starts at replicas:0 (meant to be
scaled 0<->1 by the facade, QONTO-WP-0004-T05), ClusterIP-only Service,
NetworkPolicy default-deny with ingress limited to the facade and
egress limited to DNS+443 (the FQDN-egress limitation is called out
explicitly, not silently widened). Verified: `kubectl kustomize`
renders all six resources cleanly.

externalsecret.yaml depends on CCR-2026-0009 (new), proposed in
railiance-platform: a workload-scoped Kubernetes-auth access lane into
the existing tenants/binky/qonto-api credential, since CCR-2026-0008
is human/OIDC admin access only and unusable by a running pod. Mirrors
CCR-2026-0003's llm-connect/ExternalSecretsOperator pattern. Paired
draft ClusterSecretStore also added there. Both validated against
schemas/credential-change-request.schema.yaml. Status: proposed, not
approved -- explicitly not something this repo can complete alone.

railiance/app.toml: staged-promotion contract (criticality=critical,
mandatory human approval before Stage 2 traffic exposure and Stage 3
promotion, per railiance-cluster/docs/app-toml-contract.md's own rule
for production-critical workloads). Validated against
railiance-cluster/schemas/railiance-app.schema.json.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-24 00:27:37 +02:00

157 lines
4.9 KiB
TOML

schema_version = "railiance.app.v1"
[app]
id = "qonto-assistant"
name = "Qonto Governed Assistant"
repo = "qonto-assistant"
owner = "binky-tenant-owner"
criticality = "critical"
description = "Sole holder of the Binky Qonto bank API credential; governed read-only REST+MCP finance surface for agent harnesses, reachable via a facade (QONTO-WP-0004-T05, not yet built)."
[source]
revision = "git:main"
artifact = "image"
digest_policy = "required"
[rollback]
strategy = "manual-runbook"
command = "kubectl -n qonto-assistant scale deployment/qonto-assistant --replicas=0"
verification = "Facade reports the backend unreachable; no traffic proxied until re-woken against a known-good image digest."
[[platform.dependencies]]
name = "openbao"
kind = "other"
required = true
stage = "stage2"
evidence = "ExternalSecret qonto-assistant-qonto-api syncs API_KEY/API_USER without error (depends on CCR-2026-0009 approval)."
[[secrets.references]]
name = "qonto-api-credential"
route = "openbao-workload-kv-read"
target = "ExternalSecret/qonto-assistant-qonto-api"
stage = "stage2"
required = true
[[observability.health_endpoints]]
name = "local-health"
url = "http://127.0.0.1:8080/v1/health"
stage = "stage1"
expected_status = 200
[[observability.health_endpoints]]
name = "cluster-health"
url = "http://qonto-assistant.qonto-assistant.svc.cluster.local:8080/v1/health"
stage = "stage2"
expected_status = 200
[stages.stage1]
enabled = true
namespace = "local"
release = "qonto-assistant-local"
commands = ["make test", "kubectl kustomize deploy/k8s/qonto-assistant"]
checks = ["unit-tests", "kustomize-render", "local-health"]
evidence = ["pytest output", "kustomize render success", "local health 200"]
requires_approval = false
[stages.stage2]
enabled = true
namespace = "qonto-assistant"
release = "qonto-assistant-canary"
commands = ["kubectl apply -k deploy/k8s/qonto-assistant --dry-run=server", "kubectl -n qonto-assistant scale deployment/qonto-assistant --replicas=1"]
checks = ["server-dry-run", "canary-ready", "cluster-health", "operator-approval"]
evidence = ["dry-run diff", "pod readiness", "health 200", "State Hub progress id"]
requires_approval = true
canary_mode = "isolated"
observation_minutes = 60
[stages.stage3]
enabled = true
namespace = "qonto-assistant"
release = "qonto-assistant"
commands = ["kubectl apply -k deploy/k8s/qonto-assistant", "kubectl -n qonto-assistant scale deployment/qonto-assistant --replicas=0"]
checks = ["stage2-accepted", "rollback-target", "cluster-health", "operator-approval"]
evidence = ["promotion commit", "new stable digest", "post-promotion smoke, then scale back to 0 -- the facade (T05) owns wake/idle from here on"]
requires_approval = true
promotion_mode = "release-replace"
previous_stable = "kubectl:qonto-assistant:previous-digest"
[[checks]]
id = "unit-tests"
type = "command"
stage = "stage1"
description = "Run repository unit tests."
required = true
run = "make test"
timeout_seconds = 600
[[checks]]
id = "kustomize-render"
type = "command"
stage = "stage1"
description = "Render the kustomize manifest set locally, no cluster contact."
required = true
run = "kubectl kustomize deploy/k8s/qonto-assistant"
[[checks]]
id = "local-health"
type = "http"
stage = "stage1"
description = "Confirm local service health."
required = true
url = "http://127.0.0.1:8080/v1/health"
expected_status = 200
timeout_seconds = 10
[[checks]]
id = "server-dry-run"
type = "kubernetes"
stage = "stage2"
description = "Server-side dry run of the full manifest set before scaling the canary up."
required = true
namespace = "qonto-assistant"
resource = "kustomization/deploy/k8s/qonto-assistant"
condition = "DryRunAccepted"
[[checks]]
id = "canary-ready"
type = "kubernetes"
stage = "stage2"
description = "Canary deployment reaches Available after being scaled to 1."
required = true
namespace = "qonto-assistant"
resource = "deploy/qonto-assistant"
condition = "Available"
[[checks]]
id = "cluster-health"
type = "http"
stage = "stage2"
description = "Cluster health endpoint returns 200."
required = true
url = "http://qonto-assistant.qonto-assistant.svc.cluster.local:8080/v1/health"
expected_status = 200
timeout_seconds = 10
[[checks]]
id = "operator-approval"
type = "manual"
stage = "stage2"
description = "Human approval is recorded before this internet-facing, credential-holding workload takes traffic -- criticality=critical per app.toml."
required = true
evidence_required = "State Hub approval note id, candidate digest, rollback target, confirmation that CCR-2026-0009 is approved."
[[checks]]
id = "stage2-accepted"
type = "manual"
stage = "stage3"
description = "Stage 2 gates passed for the same candidate artifact."
required = true
evidence_required = "State Hub Stage 2 acceptance progress id."
[[checks]]
id = "rollback-target"
type = "manual"
stage = "stage3"
description = "Previous stable release is recorded before promotion."
required = true
evidence_required = "Previous image digest or kustomize revision."