Stop mislabeling the Compose box as production in read-only audits

2026-08-18 09:29:25 +07:00
parent 332cb657ee
commit e5afedfa2f
18 changed files with 414 additions and 494 deletions
@@ -1,36 +0,0 @@
-# ArgoCD (GitOps deployment)
-
-Deployment uses the **team's existing ArgoCD instance** (not self-hosted by
-this project) rather than a custom push-based CD pipeline. See
-`docs/adr/0002-argocd-gitops.md` for the rationale.
-
-## Flow
-
-1. CI (`infra/ci/github-actions/*-ci.yml`) builds and pushes a container image
-   per app on merge to master, then bumps that app's image tag in
-   `infra/helm/medical-chatbot/values-<env>.yaml` (or a per-app values file)
-   and pushes that commit back to the repo. CI never runs `kubectl apply` or
-   `helm upgrade` directly.
-2. ArgoCD (team-managed, pointed at this repo) watches `infra/argocd/applications/<env>/`
-   and `infra/helm/medical-chatbot/`, detects the values-file change, and
-   syncs the cluster to match — this is the actual deploy step, owned by
-   ArgoCD, not by our CI.
-3. Promotion between environments (dev -> staging -> prod) is a Git operation
-   (merge/PR that changes the target values file or image tag for that env),
-   not a manual `kubectl`/`helm` command.
-
-## Files
-
- `applications/dev/app.yaml`, `applications/staging/app.yaml`,
-  `applications/prod/app.yaml` — one ArgoCD `Application` CR per environment,
-  each pointing at this repo + the `infra/helm/medical-chatbot` chart with
-  that environment's values file.
-
-## TODO once the team's ArgoCD instance details are known
-
- Fill in `spec.destination.server` (target cluster API server / context name)
-  in each `app.yaml` — currently a placeholder.
- Confirm which ArgoCD `project` (RBAC scoping) these Applications should
-  belong to, instead of the placeholder `default`.
- Confirm the repo URL placeholder in each `app.yaml` once the GitHub repo
-  exists (filled in as part of the initial scaffold commit/push).
@@ -1,24 +0,0 @@
-apiVersion: argoproj.io/v1alpha1
-kind: Application
-metadata:
-  name: medical-chatbot-dev
-  namespace: argocd
-spec:
-  project: default # TODO: confirm the team's ArgoCD project/RBAC scope for this app
-  source:
-    repoURL: https://github.com/BaoVu2k4/vsf-duocthu.git # TODO: confirm once repo is created
-    targetRevision: master
-    path: infra/helm/medical-chatbot
-    helm:
-      valueFiles:
-        - values.yaml
-        - values-dev.yaml
-  destination:
-    server: https://kubernetes.default.svc # TODO: point at the team's target cluster/context
-    namespace: medical-chatbot-dev
-  syncPolicy:
-    automated:
-      prune: true
-      selfHeal: true
-    syncOptions:
-      - CreateNamespace=true
@@ -1,19 +0,0 @@
-apiVersion: argoproj.io/v1alpha1
-kind: Application
-metadata:
-  name: medical-chatbot-prod
-  namespace: argocd
-spec:
-  project: default # TODO: confirm the team's ArgoCD project/RBAC scope for this app
-  source:
-    repoURL: https://github.com/BaoVu2k4/vsf-duocthu.git # TODO: confirm once repo is created
-    targetRevision: master
-    path: infra/helm/medical-chatbot
-    helm:
-      valueFiles:
-        - values.yaml
-        - values-prod.yaml
-  destination:
-    server: https://kubernetes.default.svc # TODO: point at the team's target cluster/context
-    namespace: medical-chatbot-prod
-  syncPolicy: {} # intentionally NOT automated — prod sync requires manual approval in the ArgoCD UI/CLI
@@ -1,24 +0,0 @@
-apiVersion: argoproj.io/v1alpha1
-kind: Application
-metadata:
-  name: medical-chatbot-staging
-  namespace: argocd
-spec:
-  project: default # TODO: confirm the team's ArgoCD project/RBAC scope for this app
-  source:
-    repoURL: https://github.com/BaoVu2k4/vsf-duocthu.git # TODO: confirm once repo is created
-    targetRevision: master
-    path: infra/helm/medical-chatbot
-    helm:
-      valueFiles:
-        - values.yaml
-        - values-staging.yaml
-  destination:
-    server: https://kubernetes.default.svc # TODO: point at the team's target cluster/context
-    namespace: medical-chatbot-staging
-  syncPolicy:
-    automated:
-      prune: true
-      selfHeal: true
-    syncOptions:
-      - CreateNamespace=true
@@ -1,61 +0,0 @@
-# Production values for the eventual ArgoCD cutover of realvuxbaro.me.
-#
-# Not live yet: production still runs Docker Compose on its own EC2, which is
-# the DNS-level rollback for the migration. This file is what the production
-# ArgoCD Application will render from once the rehearsal gates pass.
-#
-# The behavioural settings mirror the production runtime contract audited on
-# 2026-08-17 — see coordination/ARGOCD_PRODUCTION_MIGRATION_STATE_2026-08-17.md.
-
-global:
-  environment: production
-  # The GHCR packages are private, same as on the practice cluster. The Secret
-  # must exist in the target namespace before the first sync.
-  imagePullSecrets:
-    - name: ghcr-pull-secret
-
-aiService:
-  replicaCount: 2
-  image:
-    repository: ghcr.io/baovu2k4/vsf-duocthu-ai-service
-    # Deliberately empty. Production must run an immutable, verifiable image,
-    # so the tag is supplied per deploy as a commit SHA — through the ArgoCD
-    # Application's inline values, exactly as the practice cluster does. A
-    # `latest` here would make "which code is production running?" unanswerable
-    # and would break rollback, since the same tag would point at new content.
-    #
-    # `medical-chatbot.image` turns this empty value into a hard render error
-    # rather than a silent fallback to the chart's `local` development tag.
-    tag: ""
-    pullPolicy: Always
-  config:
-    embeddingProvider: cohere-v4
-    embeddingDimensions: 1024
-    evidenceMinimumScore: 0.12
-    awsRegion: us-east-1
-    answerProvider: bedrock-converse
-    answerModelId: qwen.qwen3-next-80b-a3b
-    rerankEnabled: true
-    otelSampleRatio: 0.25
-
-web:
-  replicaCount: 2
-  image:
-    repository: ghcr.io/baovu2k4/vsf-duocthu-web
-    tag: ""
-    pullPolicy: Always
-
-ingress:
-  enabled: true
-  host: realvuxbaro.me
-
-secret:
-  create: false
-  existingSecret: medical-chatbot-prod
-
-observability:
-  prometheus:
-    retention: 15d
-
-serviceMonitor:
-  enabled: false
@@ -1,6 +1,6 @@
-# k3s practice cluster — the `medical-chatbot-data` release.
+# Production — the `medical-chatbot-data` release (PostgreSQL + Qdrant).
 #
-# Companion to values-practice.yaml. The practice cluster deliberately splits
+# Companion to values-production.yaml. The practice cluster deliberately splits
 # the chart into two ArgoCD Applications so that PostgreSQL and Qdrant survive
 # every app rollout, prune and self-heal: only this release owns the
 # PersistentVolumeClaims, so an app-side sync failure can never delete the
@@ -13,7 +13,7 @@
 # image tag that CI rewrites and no secret, so it is fully tracked in Git.

 global:
-  environment: k3s-practice
+  environment: production

 aiService:
  enabled: false
@@ -1,7 +1,7 @@
-# k3s practice cluster — the `medical-chatbot-app` release.
+# Production — the `medical-chatbot-app` release serving realvuxbaro.me.
 #
 # This file is the Git source of truth for every stable, non-secret setting of
-# the practice rehearsal environment. It exists because the same values used to
+# this cluster. It exists because the same values used to
 # live only inside the ArgoCD Application's inline `spec.source.helm.values`,
 # where they were invisible to review, diff and rollback: the cluster could
 # drift from the repository without a single commit recording it. That is how
@@ -25,7 +25,7 @@
 # Practice is only useful as a migration rehearsal while they stay in sync.

 global:
-  environment: k3s-practice
+  environment: production
  # The GHCR packages are private; without this the Pods fail ImagePullBackOff.
  imagePullSecrets:
    - name: ghcr-pull-secret