Insert NATS JetStream log bus + S3 raw archive

Rework the logging pipeline around a durable message bus so logs survive a ClickHouse outage, can be replayed after a bad transform, and fan out to multiple independent consumers. Add long-term raw-log backup to S3. Topology becomes edge -> JetStream -> consumers -> sinks: - Dedicated JetStream NATS cluster (3 replicas, file storage) in the logging namespace. Deliberately separate from app messaging (streamstack) for blast-radius isolation. Stream LOGS (subjects logs.>, retention=limits, 40GiB / 72h) is the outage buffer; durable consumers give independent offsets. - Edge publishers (thin): the k8s DaemonSet and a new VM-ingest Deployment (HTTP NDJSON front door behind the logs-ingest Gateway) publish into JetStream (logs.k8s.<ns>.<container> / logs.vm.<host>). No parsing on the edge. - Transform tier (StatefulSet): pulls the whole stream via the durable `transform` consumer, routes by subject, shapes, and remains the sole ClickHouse writer. Its disk buffer shrinks (JetStream is the outage buffer). - Archiver (Deployment): its OWN durable `archiver` consumer (independent offsets — archive lag never affects the ClickHouse path) writes RAW, pre-transform events to a Ceph RGW S3 bucket (cephrgw-operator ObjectStoreUser + Bucket + BucketAccess) as gzipped NDJSON keyed by raw/<subject>/YYYY/MM/DD/. Default subject filter is Vault audit (logs.k8s.vault.>), configurable. Auth: distinct NATS users (producer publish-only, consumer pull+ack, admin for the stream/consumer bootstrap Job) with passwords from Vault (nats-auth Secret); S3 creds from the BucketAccess Secret. Streams/consumers are provisioned by an idempotent PostSync bootstrap Job. Add local kubeconform schemas for the ceph.unkin.net CRDs (datreeio lacks them) and extend the vector-test CI to cover the agent, VM-ingest and archiver configs. Verified end-to-end locally: NATS ACLs, vector JetStream publish, and durable-consumer pull+ack (at-least-once) all work. Claude-Session: https://claude.ai/code/session_015ur3i7D2azsMAWTSVABApv
2026-07-27 20:23:55 +10:00
parent 10020033d9
commit c39af2f9c3
21 changed files with 1195 additions and 89 deletions
@@ -5,11 +5,18 @@ steps:
  - name: vector-test
    image: timberio/vector:0.57.0-debian
    commands:
-      # Dummy creds + a writable data_dir so the full topology (incl. the
-      # ClickHouse sink disk buffer) builds; tests only exercise the transforms.
+      # Dummy creds + writable dirs so the full topologies build; the unit tests
+      # only exercise the transforms (sources are not started).
      - export CLICKHOUSE_USER=ci CLICKHOUSE_PASSWORD=ci
-      - mkdir -p /vector-data-dir
+      - export NATS_PRODUCER_PASSWORD=ci NATS_CONSUMER_PASSWORD=ci
+      - mkdir -p /vector-data-dir /etc/vault-ca
+      - cp /etc/ssl/certs/ca-certificates.crt /etc/vault-ca/ca.crt
+      # Transform tier + VM ingest: unit-tested transforms.
      - vector test apps/base/logging/vector/aggregator.yaml apps/base/logging/vector/aggregator-tests.yaml
+      - vector test apps/base/logging/vector/vm-ingest.yaml apps/base/logging/vector/vm-ingest-tests.yaml
+      # Agent + archiver have no transforms to unit-test; validate they build.
+      - vector validate --no-environment apps/base/logging/vector/agent.yaml
+      - vector validate --no-environment apps/base/logging/vector/archiver.yaml
    backend_options:
      kubernetes:
        serviceAccountName: default
@@ -0,0 +1,43 @@
+---
+# S3 bucket (Ceph RGW) for the long-term raw-log archive, provisioned by the
+# in-estate cephrgw-operator. The archiver Vector deployment writes here.
+apiVersion: ceph.unkin.net/v1alpha1
+kind: ObjectStoreUser
+metadata:
+  name: logs-archive-owner
+  namespace: logging
+spec:
+  displayName: "Logging raw-archive bucket owner"
+  maxBuckets: 5
+  quota:
+    enabled: true
+    # 5 TiB soft cap; real retention is enforced RGW-side by a bucket lifecycle
+    # policy (see PR notes) — the operator does not manage lifecycle.
+    maxSizeBytes: 5497558138880
+---
+apiVersion: ceph.unkin.net/v1alpha1
+kind: Bucket
+metadata:
+  name: logs-archive
+  namespace: logging
+spec:
+  bucketName: logs-archive
+  ownerRef: logs-archive-owner
+  versioning: false
+  tags:
+    app: logging
+    purpose: raw-log-archive
+  # Keep the bucket (and its objects) if this CR is ever deleted.
+  retainOnDelete: true
+---
+apiVersion: ceph.unkin.net/v1alpha1
+kind: BucketAccess
+metadata:
+  name: logs-archive-writer
+  namespace: logging
+spec:
+  bucketRef: logs-archive
+  level: read-write
+  # Operator writes AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY (+ RGW_UID,
+  # S3_ENDPOINT, BUCKET_NAME) into this Secret; the archiver consumes it.
+  secretName: logs-archive-s3
@@ -46,7 +46,7 @@ spec:
    - backendRefs:
        - group: ""
          kind: Service
-          name: vector-aggregator
+          name: vector-vm-ingest
          port: 8080
          weight: 1
      matches:
@@ -8,14 +8,31 @@ resources:
  - vaultstaticsecret.yaml
  - clickhouseinstallation.yaml
  - job_clickhouse-schema.yaml
+  - nats-bootstrap-job.yaml
+  - cephrgw.yaml
  - gateway.yaml
  - httproute.yaml

-# Aggregator pipeline is the single source of truth (also validated by
-# `vector test` in CI). Mounted into the aggregator via `existingConfigMaps`.
+# Vector pipelines are the single source of truth (also validated by
+# `vector test` in CI). Mounted into each tier via `existingConfigMaps`.
 configMapGenerator:
+  - name: vector-agent-config
+    files:
+      - agent.yaml=vector/agent.yaml
+    options:
+      disableNameSuffixHash: true
  - name: vector-aggregator-config
    files:
      - aggregator.yaml=vector/aggregator.yaml
    options:
      disableNameSuffixHash: true
+  - name: vector-vm-ingest-config
+    files:
+      - vm-ingest.yaml=vector/vm-ingest.yaml
+    options:
+      disableNameSuffixHash: true
+  - name: vector-archiver-config
+    files:
+      - archiver.yaml=vector/archiver.yaml
+    options:
+      disableNameSuffixHash: true
@@ -0,0 +1,122 @@
+---
+# Declarative JetStream provisioning: the LOGS stream + durable consumers.
+# ArgoCD PostSync hook, idempotent (add-or-converge), re-runs each sync.
+#
+# Stream LOGS: file storage, 3 replicas, retention=limits (NOT workqueue) so
+# multiple durable consumers fan out and can independently replay within the
+# window. Sized as the ClickHouse-outage buffer: 40 GiB / 72h (per-replica PVC
+# is 50Gi, see values-nats.yaml). Beyond that window the S3 archive is the
+# long-term replay source.
+#
+# Consumers (independent offsets = true fan-out):
+#   transform  -> whole log stream, feeds the ClickHouse transform tier
+#   archiver   -> configurable security-relevant subset, feeds the S3 archiver.
+#                 Default filter is Vault audit (logs.k8s.vault.>); ADD subjects
+#                 by editing ARCHIVE_SUBJECTS (space-separated -> repeated
+#                 --filter). Exact default set is an open decision for Ben.
+#
+# Runbook (replay):
+#   (a) reprocess from JetStream (within 72h): scale the transform tier to 0,
+#       then `nats consumer rm LOGS transform` and re-run this Job (recreates at
+#       DeliverAll), or `nats consumer edit`/`--replay` from a start seq/time.
+#   (b) long-horizon (beyond JetStream): re-ingest S3 archive objects back
+#       through the transform tier (vector aws_s3 source or a one-shot Job).
+apiVersion: batch/v1
+kind: Job
+metadata:
+  name: nats-bootstrap
+  namespace: logging
+  annotations:
+    argocd.argoproj.io/hook: PostSync
+    argocd.argoproj.io/hook-delete-policy: BeforeHookCreation
+  labels:
+    app.kubernetes.io/name: nats-bootstrap
+    app.kubernetes.io/component: bootstrap
+spec:
+  backoffLimit: 20
+  activeDeadlineSeconds: 1800
+  ttlSecondsAfterFinished: 3600
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: nats-bootstrap
+        vector.dev/exclude: "true"
+    spec:
+      restartPolicy: OnFailure
+      securityContext:
+        runAsNonRoot: true
+        runAsUser: 1000
+        runAsGroup: 1000
+      containers:
+        - name: nats-bootstrap
+          image: natsio/nats-box:0.18.0
+          securityContext:
+            allowPrivilegeEscalation: false
+            readOnlyRootFilesystem: true
+            capabilities:
+              drop:
+                - ALL
+          env:
+            - name: HOME
+              value: /tmp
+            - name: NATS_URL
+              value: "nats://nats.logging.svc.cluster.local:4222"
+            - name: NATS_ADMIN_PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: nats-auth
+                  key: admin_password
+            # Space-separated subject filters for the archiver consumer.
+            - name: ARCHIVE_SUBJECTS
+              value: "logs.k8s.vault.>"
+          command:
+            - /bin/sh
+            - -ec
+            - |
+              export NATS_USER=log-admin NATS_PASSWORD="$NATS_ADMIN_PASSWORD"
+              echo "Waiting for NATS + JetStream ..."
+              until nats --server "$NATS_URL" account info >/dev/null 2>&1; do
+                echo "  not ready, retry in 5s"; sleep 5
+              done
+
+              echo "Ensuring stream LOGS ..."
+              nats stream add LOGS \
+                --subjects='logs.>' --storage=file --replicas=3 \
+                --retention=limits --discard=old \
+                --max-age=72h --max-bytes=42949672960 \
+                --max-msgs=-1 --max-msgs-per-subject=-1 --max-msg-size=-1 \
+                --max-consumers=-1 --dupe-window=2m --defaults 2>/dev/null \
+              || nats stream edit -f LOGS \
+                --subjects='logs.>' --discard=old \
+                --max-age=72h --max-bytes=42949672960 --dupe-window=2m
+
+              echo "Ensuring consumer transform ..."
+              nats consumer add LOGS transform \
+                --pull --filter='logs.>' --deliver=all --ack=explicit \
+                --max-deliver=-1 --replay=instant --defaults 2>/dev/null \
+              || echo "  transform already exists"
+
+              echo "Ensuring consumer archiver (filters: $ARCHIVE_SUBJECTS) ..."
+              filter_args=""
+              for s in $ARCHIVE_SUBJECTS; do filter_args="$filter_args --filter=$s"; done
+              # shellcheck disable=SC2086
+              nats consumer add LOGS archiver \
+                --pull $filter_args --deliver=all --ack=explicit \
+                --max-deliver=-1 --replay=instant --defaults 2>/dev/null \
+              || echo "  archiver already exists"
+
+              echo "Done."
+              nats stream info LOGS
+          resources:
+            requests:
+              cpu: 50m
+              memory: 64Mi
+            limits:
+              cpu: 500m
+              memory: 256Mi
+          volumeMounts:
+            - name: tmp
+              mountPath: /tmp
+      volumes:
+        - name: tmp
+          emptyDir: {}
@@ -26,3 +26,25 @@ spec:
  refreshAfter: 5m
  type: kv-v2
  vaultAuthRef: default
+---
+# NATS JetStream auth. Distinct passwords for the producer (edge), consumer
+# (transform tier + archiver) and admin (bootstrap Job) users. Seed once:
+#   for k in admin producer consumer; do declare P_$k=$(openssl rand -base64 24); done
+#   vault kv put kv/kubernetes/namespace/logging/default/nats-auth \
+#     admin_password="$P_admin" producer_password="$P_producer" consumer_password="$P_consumer"
+apiVersion: secrets.hashicorp.com/v1beta1
+kind: VaultStaticSecret
+metadata:
+  name: nats-auth
+  namespace: logging
+spec:
+  destination:
+    create: true
+    name: nats-auth
+    overwrite: true
+  hmacSecretData: true
+  mount: kv
+  path: kubernetes/namespace/logging/default/nats-auth
+  refreshAfter: 5m
+  type: kv-v2
+  vaultAuthRef: default
@@ -0,0 +1,43 @@
+---
+# Vector EDGE agent pipeline (DaemonSet) — thin publisher, single source of
+# truth. Mounted via existingConfigMaps (NOT the chart's customConfig, whose
+# Helm `tpl` pass collides with Vector's own {{ }} / ${ } syntax). Tails all pod
+# logs, attaches only routing tokens, publishes to JetStream. No parsing.
+data_dir: /vector-data-dir
+
+api:
+  enabled: false
+
+sources:
+  kubernetes_logs:
+    type: kubernetes_logs
+
+transforms:
+  # Routing metadata only: NATS-subject-safe namespace + container tokens.
+  keymeta:
+    type: remap
+    inputs:
+      - kubernetes_logs
+    source: |
+      ns = to_string(.kubernetes.pod_namespace || "unknown") ?? "unknown"
+      .ns_token = replace(ns, r'[^a-zA-Z0-9_-]', "_")
+      cont = to_string(.kubernetes.container_name || "unknown") ?? "unknown"
+      .cont_token = replace(cont, r'[^a-zA-Z0-9_-]', "_")
+
+sinks:
+  to_jetstream:
+    type: nats
+    inputs:
+      - keymeta
+    url: nats://nats.logging.svc.cluster.local:4222
+    connection_name: vector-agent
+    subject: "logs.k8s.{{ ns_token }}.{{ cont_token }}"
+    jetstream:
+      enabled: true
+    auth:
+      strategy: user_password
+      user_password:
+        user: log-producer
+        password: ${NATS_PRODUCER_PASSWORD}
+    encoding:
+      codec: json
@@ -3,6 +3,20 @@
 # aggregator.yaml in CI (.woodpecker/vector-test.yaml). This is the pattern the
 # per-app parsing follow-ups extend: add a test per new transform here.
 tests:
+  - name: subject_routes_k8s_vs_vm
+    inputs:
+      - insert_at: route
+        type: log
+        log_fields:
+          subject: "logs.k8s.shop.web"
+          message: "routed"
+    outputs:
+      - extract_from: route.k8s
+        conditions:
+          - type: vrl
+            source: |
+              assert_eq!(.message, "routed")
+
  - name: k8s_log_is_normalised
    inputs:
      - insert_at: k8s_shape
@@ -1,16 +1,16 @@
 ---
-# Vector AGGREGATOR pipeline (the "brain") — single source of truth.
+# Vector TRANSFORM tier (the "brain") — single source of truth, also validated
+# by `vector test` in CI. Consumes the whole log stream from JetStream via the
+# durable `transform` consumer (at-least-once; durable offsets tracked by
+# JetStream), routes by subject, normalises into the logs.raw columns, and is
+# the ONLY ClickHouse writer. Per-app parsing is added here as follow-ups:
+# insert a transform and append its id to the clickhouse sink `inputs` — no edge
+# or VM rollout required.
 #
-# This file is the ConfigMap the aggregator StatefulSet runs AND the config
-# `vector test` validates in CI (see .woodpecker/vector-test.yaml, which merges
-# this with aggregator-tests.yaml). The edge tier (k8s DaemonSet + future VM
-# agents) stays thin: it only collects and attaches source metadata, then
-# forwards over the Vector-native protocol. All shaping, routing, enrichment,
-# batching, buffering and the ONLY ClickHouse credentials live here.
-#
-# Per-app pipelines arrive as follow-up tasks and are aggregator-only changes:
-# add a `remap`/`route`/enrichment transform below and append its id to the
-# clickhouse sink `inputs` — no fleet/DaemonSet rollout required.
+# Durability model: JetStream (72h / 40GiB) is the outage buffer. If ClickHouse
+# is down the sink blocks, back-pressure stops acking, and JetStream retains
+# messages for replay. The local disk buffer is small (survives pod restarts of
+# in-flight events only).
 data_dir: /vector-data-dir

 api:
@@ -18,30 +18,35 @@ api:
  address: 0.0.0.0:8686

 sources:
-  # In-cluster pod logs from the Vector agent DaemonSet (Vector-native proto).
-  from_agents:
-    type: vector
-    address: 0.0.0.0:6000
-
-  # Puppet-managed VM logs over HTTP (NDJSON), exposed via the logs-ingest
-  # Gateway at logs-ingest.k8s.syd1.au.unkin.net.
-  vm_http:
-    type: http_server
-    address: 0.0.0.0:8080
-    path: /
-    method: POST
+  js_in:
+    type: nats
+    url: nats://nats.logging.svc.cluster.local:4222
+    connection_name: vector-transform
+    subject: "logs.>"
+    jetstream:
+      stream: LOGS
+      consumer: transform
+    auth:
+      strategy: user_password
+      user_password:
+        user: log-consumer
+        password: ${NATS_CONSUMER_PASSWORD}
    decoding:
      codec: json
-    framing:
-      method: newline_delimited

 transforms:
-  # ---- Default normalisation into the logs.raw columns. This is intentionally
-  # the ONLY shaping today; per-app parsing is added here as follow-ups. ----
+  route:
+    type: route
+    inputs:
+      - js_in
+    route:
+      k8s: 'starts_with(to_string(.subject) ?? "", "logs.k8s.")'
+      vm: 'starts_with(to_string(.subject) ?? "", "logs.vm.")'
+
  k8s_shape:
    type: remap
    inputs:
-      - from_agents
+      - route.k8s
    source: |
      ts = .timestamp || now()
      node = to_string(.kubernetes.pod_node_name || "") ?? ""
@@ -64,10 +69,11 @@ transforms:
        "labels": lbls,
        "fields": {}
      }
+
  vm_shape:
    type: remap
    inputs:
-      - vm_http
+      - route.vm
    source: |
      ts = .timestamp || .ts || now()
      host = to_string(.host || .hostname || "") ?? ""
@@ -107,16 +113,14 @@ sinks:
      strategy: basic
      user: "${CLICKHOUSE_USER}"
      password: "${CLICKHOUSE_PASSWORD}"
-    # Fat, infrequent inserts keep ClickHouse part-count low (avoid too-many-parts).
    batch:
      max_events: 500000
      max_bytes: 134217728
      timeout_secs: 10
-    # Ride out a ClickHouse outage without dropping logs: on-disk buffer on the
-    # aggregator PVC; block upstream (back-pressure to the edge) when full.
+    # Small local buffer — JetStream is the real outage buffer now.
    buffer:
      type: disk
-      max_size: 8589934592
+      max_size: 2147483648
      when_full: block
    healthcheck:
      enabled: true
@@ -0,0 +1,62 @@
+---
+# Vector ARCHIVER tier — long-term raw-log backup to S3 (Ceph RGW). Independent
+# durable JetStream consumer (`archiver`) so its offsets/lag are fully isolated
+# from the ClickHouse transform path (archive lag can never stall ingest — true
+# fan-out). Writes RAW, pre-transform events (as they sit in JetStream) as
+# gzipped NDJSON, partitioned by subject + date. This is the long-horizon replay
+# source beyond JetStream's 72h retention window.
+data_dir: /vector-data-dir
+
+api:
+  enabled: true
+  address: 0.0.0.0:8686
+
+sources:
+  js_archive:
+    type: nats
+    url: nats://nats.logging.svc.cluster.local:4222
+    connection_name: vector-archiver
+    subject: "logs.>"
+    jetstream:
+      stream: LOGS
+      consumer: archiver
+    auth:
+      strategy: user_password
+      user_password:
+        user: log-consumer
+        password: ${NATS_CONSUMER_PASSWORD}
+    decoding:
+      codec: json
+
+sinks:
+  s3:
+    type: aws_s3
+    inputs:
+      - js_archive
+    bucket: logs-archive
+    endpoint: https://s3.ceph.unkin.net
+    region: us-east-1
+    force_path_style: true
+    tls:
+      ca_file: /etc/vault-ca/ca.crt
+    # AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY come from the logs-archive-s3
+    # Secret (cephrgw-operator) via envFrom on the deployment.
+    key_prefix: "raw/{{ subject }}/%Y/%m/%d/"
+    compression: gzip
+    encoding:
+      codec: json
+    framing:
+      method: newline_delimited
+    filename_time_format: "%Y%m%dT%H%M%SZ"
+    filename_append_uuid: true
+    batch:
+      max_bytes: 134217728
+      timeout_secs: 300
+    buffer:
+      type: memory
+      max_events: 5000
+      when_full: block
+    # Disabled so slow BucketAccess credential propagation doesn't crash-loop
+    # the pod; RGW reachability is proven by the operator's own health.
+    healthcheck:
+      enabled: false
@@ -0,0 +1,29 @@
+---
+# `vector test` unit tests for the VM-ingest routing transform.
+tests:
+  - name: host_token_is_subject_safe
+    inputs:
+      - insert_at: tag
+        type: log
+        log_fields:
+          host: "db1.syd1.example.net"
+          message: "sshd accepted"
+    outputs:
+      - extract_from: tag
+        conditions:
+          - type: vrl
+            source: |
+              assert_eq!(.host_token, "db1_syd1_example_net")
+
+  - name: missing_host_defaults_to_unknown
+    inputs:
+      - insert_at: tag
+        type: log
+        log_fields:
+          message: "no host field"
+    outputs:
+      - extract_from: tag
+        conditions:
+          - type: vrl
+            source: |
+              assert_eq!(.host_token, "unknown")
@@ -0,0 +1,50 @@
+---
+# Vector VM-INGEST tier — the VM front door. Thin: accepts NDJSON over HTTPS
+# (behind the logs-ingest Gateway) from puppet-managed VMs, attaches only a
+# routing token, and publishes into JetStream (subject logs.vm.<host>). No
+# parsing here — shaping happens in the transform tier after JetStream, so VM
+# logs get the same durability/replay/fan-out as k8s logs.
+data_dir: /vector-data-dir
+
+api:
+  enabled: true
+  address: 0.0.0.0:8686
+
+sources:
+  vm_http:
+    type: http_server
+    address: 0.0.0.0:8080
+    path: /
+    method: POST
+    decoding:
+      codec: json
+    framing:
+      method: newline_delimited
+
+transforms:
+  # Routing metadata only: derive a NATS-subject-safe host token.
+  tag:
+    type: remap
+    inputs:
+      - vm_http
+    source: |
+      host = to_string(.host || .hostname || "unknown") ?? "unknown"
+      .host_token = replace(host, r'[^a-zA-Z0-9_-]', "_")
+
+sinks:
+  to_jetstream:
+    type: nats
+    inputs:
+      - tag
+    url: nats://nats.logging.svc.cluster.local:4222
+    connection_name: vector-vm-ingest
+    subject: "logs.vm.{{ host_token }}"
+    jetstream:
+      enabled: true
+    auth:
+      strategy: user_password
+      user_password:
+        user: log-producer
+        password: ${NATS_PRODUCER_PASSWORD}
+    encoding:
+      codec: json
@@ -8,18 +8,38 @@ resources:
  - ../../../base/logging

 helmCharts:
-  # Node-level agent: tails every pod's logs and forwards to the aggregator.
+  # Dedicated JetStream NATS cluster — the durable log bus.
+  - name: nats
+    repo: https://nats-io.github.io/k8s/helm/charts
+    version: "2.14.2"
+    releaseName: nats
+    namespace: logging
+    valuesFile: values-nats.yaml
+  # Edge agent (DaemonSet): tails every pod's logs, publishes to JetStream.
  - name: vector
    repo: https://helm.vector.dev
    version: "0.57.0"
    releaseName: vector-agent
    namespace: logging
    valuesFile: values-vector-agent.yaml
-  # Aggregator: receives from agents (vector proto) and from VMs (HTTP),
-  # shapes events, and writes to ClickHouse.
+  # VM ingest (Deployment): HTTP NDJSON front door -> JetStream.
+  - name: vector
+    repo: https://helm.vector.dev
+    version: "0.57.0"
+    releaseName: vector-vm-ingest
+    namespace: logging
+    valuesFile: values-vector-vm-ingest.yaml
+  # Transform tier (StatefulSet): JetStream consumer -> shape -> ClickHouse.
  - name: vector
    repo: https://helm.vector.dev
    version: "0.57.0"
    releaseName: vector-aggregator
    namespace: logging
    valuesFile: values-vector-aggregator.yaml
+  # Archiver (Deployment): independent JetStream consumer -> raw logs to S3.
+  - name: vector
+    repo: https://helm.vector.dev
+    version: "0.57.0"
+    releaseName: vector-archiver
+    namespace: logging
+    valuesFile: values-vector-archiver.yaml
@@ -0,0 +1,83 @@
+# Dedicated JetStream-enabled NATS cluster for the log bus. Deliberately NOT
+# shared with app messaging (streamstack et al. run their own NATS in their own
+# repo) — a separate cluster isolates logging blast-radius from app messaging
+# and lets us size retention/storage purely for the log outage-buffer + replay
+# use-case.
+fullnameOverride: nats
+
+config:
+  cluster:
+    enabled: true
+    replicas: 3
+  jetstream:
+    enabled: true
+    fileStore:
+      pvc:
+        size: 50Gi
+        storageClassName: cephrbd-fast-delete
+  # Per-user auth with publish/subscribe separation. Passwords are injected as
+  # env vars from the Vault-synced nats-auth Secret (NATS expands $VAR in config).
+  merge:
+    authorization:
+      users:
+        # Bootstrap Job (stream/consumer management) — full JetStream API.
+        - user: log-admin
+          password: $NATS_ADMIN_PASSWORD
+        # Edge publishers (k8s DaemonSet + VM ingest) — publish only.
+        - user: log-producer
+          password: $NATS_PRODUCER_PASSWORD
+          permissions:
+            publish:
+              allow:
+                - "logs.>"
+            subscribe:
+              allow:
+                - "_INBOX.>"
+        # Consumers (transform tier + archiver) — pull + ack only, no publish
+        # to log subjects.
+        - user: log-consumer
+          password: $NATS_CONSUMER_PASSWORD
+          permissions:
+            publish:
+              allow:
+                - "$JS.API.CONSUMER.>"
+                - "$JS.API.STREAM.INFO.>"
+                - "$JS.ACK.LOGS.>"
+            subscribe:
+              allow:
+                - "_INBOX.>"
+
+container:
+  env:
+    NATS_ADMIN_PASSWORD:
+      valueFrom:
+        secretKeyRef:
+          name: nats-auth
+          key: admin_password
+    NATS_PRODUCER_PASSWORD:
+      valueFrom:
+        secretKeyRef:
+          name: nats-auth
+          key: producer_password
+    NATS_CONSUMER_PASSWORD:
+      valueFrom:
+        secretKeyRef:
+          name: nats-auth
+          key: consumer_password
+  resources:
+    requests:
+      cpu: 250m
+      memory: 512Mi
+    limits:
+      cpu: "2"
+      memory: 4Gi
+
+# Roll the StatefulSet when nats-auth changes.
+podTemplate:
+  merge:
+    metadata:
+      annotations:
+        reloader.stakater.com/auto: "true"
+
+natsBox:
+  enabled: false
@@ -1,7 +1,7 @@
-# Vector Agent (DaemonSet) — captures ALL pod logs on every node (including
-# control-plane, via the blanket toleration) and forwards them to the
-# aggregator over the Vector native protocol. No per-app parsing here: shaping
-# and the ClickHouse write live on the aggregator.
+# Vector EDGE agent (DaemonSet) — thin publisher. Tails every node's pod logs
+# (incl. control-plane via the blanket toleration) and publishes them into
+# JetStream over the Vector NATS sink. No parsing; only a routing subject token
+# is attached. Shaping happens in the transform tier after JetStream.
 role: Agent
 fullnameOverride: vector-agent

@@ -13,10 +13,16 @@ serviceAccount:
 podLabels:
  vector.dev/exclude: "true"

-# Run on every node so no host's pod logs are missed.
 tolerations:
  - operator: Exists

+env:
+  - name: NATS_PRODUCER_PASSWORD
+    valueFrom:
+      secretKeyRef:
+        name: nats-auth
+        key: producer_password
+
 resources:
  requests:
    cpu: 100m
@@ -25,20 +31,14 @@ resources:
    cpu: "1"
    memory: 1Gi

-# Disable the chart's auto-generated service for the agent (it ships, not serves).
 service:
  enabled: false

-customConfig:
-  data_dir: /vector-data-dir
-  api:
-    enabled: false
-  sources:
-    kubernetes_logs:
-      type: kubernetes_logs
-  sinks:
-    to_aggregator:
-      type: vector
-      inputs:
-        - kubernetes_logs
-      address: vector-aggregator.logging.svc.cluster.local:6000
+# Pipeline is the single source of truth in apps/base/logging/vector/agent.yaml,
+# mounted via existingConfigMaps (avoids the chart's customConfig Helm-tpl pass).
+dataDir: /vector-data-dir
+existingConfigMaps:
+  - vector-agent-config
+
+workloadResourceAnnotations:
+  reloader.stakater.com/auto: "true"
@@ -1,38 +1,33 @@
-# Vector AGGREGATOR (StatefulSet) — the "brain" tier: sole ClickHouse writer,
-# owns all transforms, holds the only ClickHouse credentials, HA replicas with
-# on-disk buffers to ride out a ClickHouse outage.
+# Vector TRANSFORM tier (StatefulSet) — the "brain": sole ClickHouse writer,
+# owns all transforms, holds the only ClickHouse + NATS-consumer credentials.
+# It is a pure JetStream pull consumer (no inbound ports) — durability lives in
+# JetStream, so the local disk buffer is small (5Gi PVC / 2GiB buffer).
 #
-# The pipeline itself is NOT inlined here: it lives in
-# apps/base/logging/vector/aggregator.yaml (single source of truth, unit-tested
-# by `vector test` in CI) and is mounted via existingConfigMaps. This file only
-# owns the k8s deployment shape (ports, creds, storage, HA).
+# Pipeline is the single source of truth in apps/base/logging/vector/
+# aggregator.yaml (unit-tested by `vector test` in CI), mounted via
+# existingConfigMaps.
 role: Aggregator
 fullnameOverride: vector-aggregator
 replicas: 2

-# Reload the StatefulSet when the aggregator ConfigMap or the creds Secret change.
 workloadResourceAnnotations:
  reloader.stakater.com/auto: "true"

 podLabels:
  vector.dev/exclude: "true"

-# Mount the aggregator pipeline ConfigMap (rendered from base by kustomize).
-# dataDir must be set when using existingConfigMaps; it is also where the
-# clickhouse sink's disk buffer lives (backed by the PVC below).
 dataDir: /vector-data-dir
 existingConfigMaps:
  - vector-aggregator-config

-# On-disk buffer storage so a ClickHouse outage does not drop logs.
 persistence:
  enabled: true
  storageClassName: cephrbd-fast-delete
-  size: 20Gi
+  size: 5Gi
  accessModes:
    - ReadWriteOnce

-# ClickHouse basic-auth creds — the ONLY place these are consumed.
+# The ONLY place ClickHouse + NATS-consumer creds are consumed.
 env:
  - name: CLICKHOUSE_USER
    valueFrom:
@@ -44,14 +39,14 @@ env:
      secretKeyRef:
        name: clickhouse-credentials
        key: password
+  - name: NATS_CONSUMER_PASSWORD
+    valueFrom:
+      secretKeyRef:
+        name: nats-auth
+        key: consumer_password

+# Pure consumer: expose only the Vector API for debugging.
 containerPorts:
-  - name: vector
-    containerPort: 6000
-    protocol: TCP
-  - name: http-ingest
-    containerPort: 8080
-    protocol: TCP
  - name: api
    containerPort: 8686
    protocol: TCP
@@ -60,14 +55,6 @@ service:
  enabled: true
  type: ClusterIP
  ports:
-    - name: vector
-      port: 6000
-      targetPort: 6000
-      protocol: TCP
-    - name: http-ingest
-      port: 8080
-      targetPort: 8080
-      protocol: TCP
    - name: api
      port: 8686
      targetPort: 8686
@@ -0,0 +1,52 @@
+# Vector ARCHIVER tier (Deployment) — independent JetStream consumer writing raw
+# logs to S3 (Ceph RGW). Isolated from the ClickHouse path (own durable
+# consumer). Pipeline: apps/base/logging/vector/archiver.yaml.
+role: Stateless-Aggregator
+fullnameOverride: vector-archiver
+replicas: 1
+
+workloadResourceAnnotations:
+  reloader.stakater.com/auto: "true"
+
+podLabels:
+  vector.dev/exclude: "true"
+
+dataDir: /vector-data-dir
+existingConfigMaps:
+  - vector-archiver-config
+
+env:
+  - name: NATS_CONSUMER_PASSWORD
+    valueFrom:
+      secretKeyRef:
+        name: nats-auth
+        key: consumer_password
+
+# S3 creds (AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY) from the cephrgw-operator
+# BucketAccess Secret.
+envFrom:
+  - secretRef:
+      name: logs-archive-s3
+
+# Trust the internal unkin.net Vault-PKI CA to verify s3.ceph.unkin.net.
+# vault-ca-cert is reflected into every namespace from the certificates ns.
+extraVolumes:
+  - name: vault-ca-cert
+    secret:
+      secretName: vault-ca-cert
+extraVolumeMounts:
+  - name: vault-ca-cert
+    mountPath: /etc/vault-ca/ca.crt
+    subPath: ca.crt
+    readOnly: true
+
+service:
+  enabled: false
+
+resources:
+  requests:
+    cpu: 100m
+    memory: 256Mi
+  limits:
+    cpu: "1"
+    memory: 1Gi
@@ -0,0 +1,52 @@
+# Vector VM-INGEST tier (Deployment) — VM front door. HTTP NDJSON in (behind the
+# logs-ingest Gateway), publishes into JetStream. Stateless publisher.
+# Pipeline: apps/base/logging/vector/vm-ingest.yaml (unit-tested in CI).
+role: Stateless-Aggregator
+fullnameOverride: vector-vm-ingest
+replicas: 2
+
+workloadResourceAnnotations:
+  reloader.stakater.com/auto: "true"
+
+podLabels:
+  vector.dev/exclude: "true"
+
+dataDir: /vector-data-dir
+existingConfigMaps:
+  - vector-vm-ingest-config
+
+env:
+  - name: NATS_PRODUCER_PASSWORD
+    valueFrom:
+      secretKeyRef:
+        name: nats-auth
+        key: producer_password
+
+containerPorts:
+  - name: http-ingest
+    containerPort: 8080
+    protocol: TCP
+  - name: api
+    containerPort: 8686
+    protocol: TCP
+
+service:
+  enabled: true
+  type: ClusterIP
+  ports:
+    - name: http-ingest
+      port: 8080
+      targetPort: 8080
+      protocol: TCP
+    - name: api
+      port: 8686
+      targetPort: 8686
+      protocol: TCP
+
+resources:
+  requests:
+    cpu: 100m
+    memory: 256Mi
+  limits:
+    cpu: "1"
+    memory: 1Gi
@@ -0,0 +1,176 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "properties": {
+    "apiVersion": {
+      "type": "string"
+    },
+    "kind": {
+      "type": "string"
+    },
+    "metadata": {
+      "type": "object"
+    },
+    "spec": {
+      "properties": {
+        "bucketName": {
+          "type": "string"
+        },
+        "managePolicy": {
+          "default": true,
+          "type": "boolean"
+        },
+        "objectLock": {
+          "properties": {
+            "days": {
+              "format": "int32",
+              "type": "integer"
+            },
+            "enabled": {
+              "type": "boolean"
+            },
+            "mode": {
+              "enum": [
+                "GOVERNANCE",
+                "COMPLIANCE"
+              ],
+              "type": "string"
+            },
+            "years": {
+              "format": "int32",
+              "type": "integer"
+            }
+          },
+          "required": [
+            "enabled"
+          ],
+          "type": "object"
+        },
+        "ownerRef": {
+          "type": "string"
+        },
+        "placementTarget": {
+          "type": "string"
+        },
+        "purgeOnDelete": {
+          "type": "boolean"
+        },
+        "quota": {
+          "properties": {
+            "enabled": {
+              "default": true,
+              "type": "boolean"
+            },
+            "maxObjects": {
+              "format": "int64",
+              "type": "integer"
+            },
+            "maxSizeBytes": {
+              "format": "int64",
+              "type": "integer"
+            }
+          },
+          "type": "object"
+        },
+        "retainOnDelete": {
+          "type": "boolean"
+        },
+        "tags": {
+          "additionalProperties": {
+            "type": "string"
+          },
+          "type": "object"
+        },
+        "versioning": {
+          "type": "boolean"
+        },
+        "zonegroup": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "ownerRef"
+      ],
+      "type": "object"
+    },
+    "status": {
+      "properties": {
+        "adopted": {
+          "type": "boolean"
+        },
+        "bucketID": {
+          "type": "string"
+        },
+        "bucketName": {
+          "type": "string"
+        },
+        "conditions": {
+          "items": {
+            "properties": {
+              "lastTransitionTime": {
+                "format": "date-time",
+                "type": "string"
+              },
+              "message": {
+                "maxLength": 32768,
+                "type": "string"
+              },
+              "observedGeneration": {
+                "format": "int64",
+                "minimum": 0,
+                "type": "integer"
+              },
+              "reason": {
+                "maxLength": 1024,
+                "minLength": 1,
+                "pattern": "^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$",
+                "type": "string"
+              },
+              "status": {
+                "enum": [
+                  "True",
+                  "False",
+                  "Unknown"
+                ],
+                "type": "string"
+              },
+              "type": {
+                "maxLength": 316,
+                "pattern": "^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$",
+                "type": "string"
+              }
+            },
+            "required": [
+              "lastTransitionTime",
+              "message",
+              "reason",
+              "status",
+              "type"
+            ],
+            "type": "object"
+          },
+          "type": "array",
+          "x-kubernetes-list-map-keys": [
+            "type"
+          ],
+          "x-kubernetes-list-type": "map"
+        },
+        "observedGeneration": {
+          "format": "int64",
+          "type": "integer"
+        },
+        "owner": {
+          "type": "string"
+        },
+        "phase": {
+          "type": "string"
+        },
+        "policyPrincipals": {
+          "format": "int32",
+          "type": "integer"
+        }
+      },
+      "type": "object"
+    }
+  },
+  "type": "object"
+}
@@ -0,0 +1,191 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "properties": {
+    "apiVersion": {
+      "type": "string"
+    },
+    "kind": {
+      "type": "string"
+    },
+    "metadata": {
+      "type": "object"
+    },
+    "spec": {
+      "properties": {
+        "actions": {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "bucketRef": {
+          "type": "string"
+        },
+        "conditions": {
+          "properties": {
+            "secureTransportOnly": {
+              "type": "boolean"
+            },
+            "sourceIPs": {
+              "items": {
+                "type": "string"
+              },
+              "type": "array"
+            }
+          },
+          "type": "object"
+        },
+        "level": {
+          "enum": [
+            "read-only",
+            "read-write",
+            "full"
+          ],
+          "type": "string"
+        },
+        "paths": {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "rawStatements": {
+          "items": {
+            "properties": {
+              "actions": {
+                "items": {
+                  "type": "string"
+                },
+                "type": "array"
+              },
+              "conditions": {
+                "additionalProperties": {
+                  "additionalProperties": {
+                    "items": {
+                      "type": "string"
+                    },
+                    "type": "array"
+                  },
+                  "type": "object"
+                },
+                "type": "object"
+              },
+              "effect": {
+                "default": "Allow",
+                "enum": [
+                  "Allow",
+                  "Deny"
+                ],
+                "type": "string"
+              },
+              "resources": {
+                "items": {
+                  "type": "string"
+                },
+                "type": "array"
+              },
+              "sid": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "actions"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "retainOnDelete": {
+          "type": "boolean"
+        },
+        "secretName": {
+          "type": "string"
+        },
+        "uid": {
+          "type": "string"
+        },
+        "userRef": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "bucketRef",
+        "level"
+      ],
+      "type": "object"
+    },
+    "status": {
+      "properties": {
+        "bound": {
+          "type": "boolean"
+        },
+        "conditions": {
+          "items": {
+            "properties": {
+              "lastTransitionTime": {
+                "format": "date-time",
+                "type": "string"
+              },
+              "message": {
+                "maxLength": 32768,
+                "type": "string"
+              },
+              "observedGeneration": {
+                "format": "int64",
+                "minimum": 0,
+                "type": "integer"
+              },
+              "reason": {
+                "maxLength": 1024,
+                "minLength": 1,
+                "pattern": "^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$",
+                "type": "string"
+              },
+              "status": {
+                "enum": [
+                  "True",
+                  "False",
+                  "Unknown"
+                ],
+                "type": "string"
+              },
+              "type": {
+                "maxLength": 316,
+                "pattern": "^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$",
+                "type": "string"
+              }
+            },
+            "required": [
+              "lastTransitionTime",
+              "message",
+              "reason",
+              "status",
+              "type"
+            ],
+            "type": "object"
+          },
+          "type": "array",
+          "x-kubernetes-list-map-keys": [
+            "type"
+          ],
+          "x-kubernetes-list-type": "map"
+        },
+        "observedGeneration": {
+          "format": "int64",
+          "type": "integer"
+        },
+        "phase": {
+          "type": "string"
+        },
+        "secretName": {
+          "type": "string"
+        },
+        "uid": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    }
+  },
+  "type": "object"
+}
@@ -0,0 +1,132 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "properties": {
+    "apiVersion": {
+      "type": "string"
+    },
+    "kind": {
+      "type": "string"
+    },
+    "metadata": {
+      "type": "object"
+    },
+    "spec": {
+      "properties": {
+        "displayName": {
+          "type": "string"
+        },
+        "email": {
+          "type": "string"
+        },
+        "maxBuckets": {
+          "default": 1000,
+          "format": "int32",
+          "type": "integer"
+        },
+        "quota": {
+          "properties": {
+            "enabled": {
+              "default": true,
+              "type": "boolean"
+            },
+            "maxObjects": {
+              "format": "int64",
+              "type": "integer"
+            },
+            "maxSizeBytes": {
+              "format": "int64",
+              "type": "integer"
+            }
+          },
+          "type": "object"
+        },
+        "retainOnDelete": {
+          "type": "boolean"
+        },
+        "secretName": {
+          "type": "string"
+        },
+        "suspended": {
+          "type": "boolean"
+        },
+        "uid": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "status": {
+      "properties": {
+        "adopted": {
+          "type": "boolean"
+        },
+        "conditions": {
+          "items": {
+            "properties": {
+              "lastTransitionTime": {
+                "format": "date-time",
+                "type": "string"
+              },
+              "message": {
+                "maxLength": 32768,
+                "type": "string"
+              },
+              "observedGeneration": {
+                "format": "int64",
+                "minimum": 0,
+                "type": "integer"
+              },
+              "reason": {
+                "maxLength": 1024,
+                "minLength": 1,
+                "pattern": "^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$",
+                "type": "string"
+              },
+              "status": {
+                "enum": [
+                  "True",
+                  "False",
+                  "Unknown"
+                ],
+                "type": "string"
+              },
+              "type": {
+                "maxLength": 316,
+                "pattern": "^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$",
+                "type": "string"
+              }
+            },
+            "required": [
+              "lastTransitionTime",
+              "message",
+              "reason",
+              "status",
+              "type"
+            ],
+            "type": "object"
+          },
+          "type": "array",
+          "x-kubernetes-list-map-keys": [
+            "type"
+          ],
+          "x-kubernetes-list-type": "map"
+        },
+        "observedGeneration": {
+          "format": "int64",
+          "type": "integer"
+        },
+        "phase": {
+          "type": "string"
+        },
+        "secretName": {
+          "type": "string"
+        },
+        "uid": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    }
+  },
+  "type": "object"
+}