# Stalwart — a cluster-capable mail server (SMTP, IMAP, POP3, JMAP, ManageSieve).
#
# READ THIS FIRST: THIS CHART CONFIGURES ALMOST NOTHING.
#
# Since v0.16 Stalwart keeps its entire configuration — over 2400 settings in
# 117 object types, including every listener, the blob store, the in-memory
# store, TLS objects, domains and the cluster roles — INSIDE the data store,
# managed over the JMAP API (WebUI or stalwart-cli). The only thing left on
# disk is a small config.json that names the data store and nothing else:
# "It only needs to contain the DataStore object"
# (https://stalw.art/docs/configuration/declarative-deployments).
#
# So this chart renders config.json, the workloads with their STALWART_ROLE,
# the Services, the NetworkPolicies, the Ingress and a cert-manager
# Certificate. Everything else is operator work in the WebUI, and the values
# below say for each block whether it configures Stalwart or only Kubernetes.
# A value that only describes something to Kubernetes is marked as such rather
# than left to look like application configuration.

# Scale the whole chart down without uninstalling it: scaleDown: true renders
# every StatefulSet with replicas: 0 and takes precedence over every
# nodes.<group>.replicas. Services, Ingress, Secrets and the Certificate stay
# in place, so no certificate is re-issued when you scale back up.
scaleDown: false

# Chart-wide default for the limit factor of every node group. A group may
# override it as nodes.<group>.resources.limitFactor, which always wins. Memory
# and ephemeral-storage limits are computed as limitFactor x the request; a CPU
# limit is only set when configured explicitly.
limitFactor: 3

secrets:
  # op:// path of the 1Password item carrying the data-store password in the
  # field "password".
  #
  # ONLY the password. The username cannot live here, and that is an upstream
  # constraint rather than a choice: on the DataStore object authSecret has the
  # type SecretKeyOptional (which has an EnvironmentVariable variant, and that
  # is what this chart uses) while authUsername is a plain String with no
  # secret form at all. So the username is the public value
  # dataStore.postgres.username below and ends up in the ConfigMap, while the
  # password never does.
  dataStoreSecretRef: null

  # op:// path of the 1Password item carrying the field "recovery-admin" with
  # the COMPLETE value of STALWART_RECOVERY_ADMIN, i.e. "admin:<password>" in
  # one string — the same shape as valkey's auth-conf field. The chart does not
  # assemble it from two fields, because a half-built credential ("admin:" with
  # an empty password) is accepted by the server as a working back door.
  #
  # Why it is worth pinning at all: without it Stalwart generates a temporary
  # administrator password on every bootstrap or recovery start and prints it to
  # stdout — in Kubernetes that means a fresh password in the pod log on every
  # restart, visible to anyone who can read logs, and lost as soon as it
  # scrolls. Set to null to switch the variable off entirely once a permanent
  # administrator exists in the database; that is the documented end state, see
  # NOTES.txt.
  recoveryAdminSecretRef: null

  # op:// path of the 1Password item for the S3 blob store, carrying the fields
  # "access-key" and "secret-key".
  #
  # This chart does NOT configure the blob store — that object lives in the
  # database. What it does is expose both fields to the container as the
  # environment variables STALWART_S3_ACCESS_KEY and STALWART_S3_SECRET_KEY, so
  # that the BlobStore object you create in the WebUI can reference them
  # instead of storing the credentials in the database:
  #   accessKey: {"@type":"EnvironmentVariable","variableName":"STALWART_S3_ACCESS_KEY"}
  #   secretKey: {"@type":"EnvironmentVariable","variableName":"STALWART_S3_SECRET_KEY"}
  # Both fields accept that variant (accessKey is PublicStringOptional,
  # secretKey is SecretKeyOptional; both offer Value, EnvironmentVariable and
  # File). Leave null when the blob store is not S3 or when you prefer to keep
  # the credentials in the database — the variables are then not set and
  # nothing references them.
  s3SecretRef: null

# ---------------------------------------------------------------------------
# config.json — the ONLY part of Stalwart this chart actually configures
# ---------------------------------------------------------------------------
dataStore:
  postgres:
    # REQUIRED, no default (enforced by required() in the template).
    host: null
    port: 5432
    database: stalwart
    # Public on purpose — see secrets.dataStoreSecretRef above for why this is
    # not a secret reference. It is rendered into the ConfigMap.
    username: stalwart
    tls:
      # Rendered as the object's "useTls" field. The names differ because this
      # chart groups the two TLS switches that upstream keeps flat; the mapping
      # is tls.enable -> useTls and tls.allowInvalidCerts -> allowInvalidCerts.
      #
      # Note the default is the OPPOSITE of upstream's (false). A mail server's
      # data store carries every message's metadata, and this chart would
      # rather fail to connect to a plaintext-only Postgres than reach it
      # silently unencrypted.
      enable: true
      # Accepting an invalid certificate turns TLS into obfuscation: the
      # connection is encrypted against a passive listener and wide open to an
      # active one. Only ever a temporary diagnostic.
      allowInvalidCerts: false
    poolMaxConnections: 10
    # MILLISECONDS, as an integer — not "15s".
    #
    # This is not a styling preference. Stalwart's object encoding states it
    # outright: "A duration is an integer count of milliseconds, and a size is
    # an integer count of bytes. Neither accepts a string."
    # (https://stalw.art/docs/configuration/object-encoding). The DataStore
    # reference gives this field as "Duration? default: 15000". A config.json
    # carrying "15s" is rejected by the server at startup, so the key is named
    # for its unit instead of accepting a suffix the file cannot hold.
    timeoutMs: 15000
    # Extra libpq connection options, passed through verbatim as the object's
    # "options" field. null omits the field.
    options: null

# ---------------------------------------------------------------------------
# First start: Stalwart needs recovery mode when config.json is provided
# ---------------------------------------------------------------------------
bootstrap:
  # Sets STALWART_RECOVERY_MODE=1 on every node group.
  #
  # WHY THIS EXISTS, AND WHY IT IS NOT OPTIONAL ON A FIRST INSTALL. The setup
  # wizard everyone reaches for runs in BOOTSTRAP mode, and bootstrap mode is
  # entered only when there is no config.json: "The first time Stalwart is
  # started without a config.json, it enters bootstrap mode"
  # (https://stalw.art/docs/configuration/bootstrap-mode). This chart always
  # renders one, so the wizard never appears. Against an empty database that
  # leaves a server with no listeners, no domain and no administrator, and
  # nothing to fix it with.
  #
  # The documented path for exactly this case is recovery mode: "template
  # config.json onto the host, start Stalwart once with STALWART_RECOVERY_MODE=1
  # and a STALWART_RECOVERY_ADMIN supplied from a secrets manager, run
  # stalwart-cli apply against the recovery listener to load the initial
  # configuration, and then restart Stalwart without the recovery variables"
  # (https://stalw.art/docs/configuration/declarative-deployments). Recovery
  # mode brings up the management HTTP endpoint on port 8080 — the WebUI
  # included — and keeps every mail port closed.
  #
  # So: true for the first install, then false and upgrade again. Leaving it on
  # is not a small untidiness — the mail ports stay shut while the Services and
  # the Ingress look perfectly healthy, which is the loudest-looking silent
  # failure this chart has. NOTES.txt prints a warning for as long as it is on.
  enabled: false
  # Log verbosity while recovery mode is on (STALWART_RECOVERY_MODE_LOG_LEVEL).
  # Has no effect once bootstrap.enabled is false.
  logLevel: info

# ---------------------------------------------------------------------------
# Ports. KUBERNETES ONLY — these numbers do not reach Stalwart.
# ---------------------------------------------------------------------------
# THE DUPLICATION BELOW CANNOT BE AVOIDED, SO IT IS WRITTEN DOWN INSTEAD.
#
# Every listener Stalwart binds is a NetworkListener object in the database.
# This chart cannot create those objects, so containerPort here is a second
# copy of a decision that is really made in the WebUI. If the two disagree, the
# Service points at a port nothing listens on: connections are refused or time
# out, every pod stays Ready, and no object reports a problem. Check both sides
# whenever you touch one.
#
# TWO NUMBERS PER ENTRY, AND THEY ARE NOT INTERCHANGEABLE:
#   containerPort — what the application binds inside the pod, and what the
#                   NetworkListener object in the database must say.
#   nodePort      — what the cluster publishes on every node, and what the HA
#                   proxy in front of the cluster connects to.
# The Service maps one onto the other: nodePort 30025 -> targetPort 25.
#
# WHY THE APPLICATION BINDS THE ORDINARY 25/465/993. An earlier draft had it
# bind 30025/30465/30993 so that nothing privileged was ever bound and the
# NET_BIND_SERVICE capability could be dropped. That reasoning collapsed: the
# image ships "setcap cap_net_bind_service=+ep" on the binary, which makes it a
# capability-dumb binary, and the kernel then fails the execve ITSELF when the
# bounding set does not carry the capability — before the program binds
# anything. The capability has to be granted either way (see securityContext
# below), so high ports bought no hardening at all. What the ordinary numbers
# buy instead is predictability: the listener objects an operator creates in
# the WebUI carry the numbers from every page of Stalwart's documentation and
# from the image's own EXPOSE list, which takes most of the surprise out of the
# duplication above.
#
# The nodePorts must be inside the API server's --service-node-port-range
# (default 30000-32767). 30025/30465/30993 are, with the default — UNVERIFIED
# against this cluster's actual setting.
#
# Only these three plus HTTP are published. 587, 143, 110, 995 and 4190 are
# deliberately absent and can be added later without a breaking change: add an
# entry here and list it in the groups that should answer on it.
ports:
  smtp:
    containerPort: 25
    nodePort: 30025
    protocol: TCP
    public: true
  submissions:
    containerPort: 465
    nodePort: 30465
    protocol: TCP
    public: true
  imaps:
    containerPort: 993
    nodePort: 30993
    protocol: TCP
    public: true
  http:
    # The management/JMAP/WebUI port, and the port the probes use. Never
    # published as a NodePort: it is reached through the Ingress (ClusterIP
    # Service) and by the kubelet.
    containerPort: 8080
    protocol: TCP
    public: false

# The init container that seeds /etc/stalwart/config.json out of the ConfigMap.
# Pinned here rather than hardcoded in the template, and reviewed on every
# app-update round, because it is an auxiliary image and its tag does not come
# from appVersion (README, guideline 3).
initImage:
  repository: docker.io/library/busybox
  tag: "1.37.0-uclibc"

service:
  # Cluster, and Local is not an option here — this is a property of the
  # deployment's topology, not a preference.
  #
  # externalTrafficPolicy: Local only forwards to pods on the node that
  # received the packet. Mail enters through an HA proxy that distributes
  # 25/465/993 across the three control-plane nodes, and no Stalwart pod is
  # ever scheduled on a control-plane node — so under Local EVERY packet would
  # be dropped, not some.
  #
  # The price of Cluster is that kube-proxy masquerades the source address to
  # the receiving node's IP (it has to: the reply would otherwise leave through
  # a different node than the one the sender holds its connection with). For a
  # mail server a lost source address is not cosmetic; it switches off SPF,
  # takes DMARC with it, makes every blocklist report "clean", collapses
  # per-IP rate limits onto one address, removes greylisting's key, and makes
  # the auto-ban lock out every sender at once by banning the node IP. The
  # Received: chain becomes worthless, which is the one item on that list that
  # destroys evidence retroactively instead of just failing.
  #
  # What pays that price back is the PROXY protocol, and only because of this
  # topology: the HA proxy terminates the inbound connection and opens its OWN
  # to the node, so it can prepend a PROXY v2 header on that connection — for
  # port 25 as well, where no remote mail server would ever send one. The real
  # client address then travels in the header and the masquerading stops
  # mattering. This is a MANDATORY companion step, not an optimisation; the
  # wiki page has the all-or-nothing warning that goes with it.
  externalTrafficPolicy: Cluster
  # Extra annotations for every Service this chart renders (ClusterIP and
  # NodePort alike). Free-form by nature.
  annotations: {}

# ---------------------------------------------------------------------------
# Node groups. One StatefulSet, one headless Service and one NetworkPolicy each.
# ---------------------------------------------------------------------------
# A MAP, NOT A LIST, and on purpose: with a list every override would be
# index-based (--set nodes[1].replicas=2), so inserting a group later would
# silently repoint every existing override at the wrong group.
#
# The key is the cluster role name and goes into STALWART_ROLE. A ClusterRole
# object of exactly that name has to exist in the database — see the fail-open
# warning below, which is the most important paragraph in this file.
#
# THERE IS NO nodes.<group>.tasks KEY. Which tasks and listeners a role runs is
# a property of the ClusterRole object in the database, and this chart cannot
# write it. A values key that looked like it set them and did not would be
# worse than its absence.
#
# FAIL-OPEN: A NODE WHOSE ROLE IS MISSING FROM THE DATABASE BECOMES A FULL NODE.
#
# From the source, not the documentation. The bootstrap registry looks a role
# up by name; when it finds none it records a non-fatal error and leaves the
# role unset, and the listener check then reads
#   bp.role.as_ref().is_none_or(|r| ...)
# which yields true for EVERY listener when the role is None. The same holds
# for the task set. So a typo in a group name here, or a rename here without
# the matching rename in the database, turns that group into a node that binds
# everything — the mx group would serve IMAP and the admin interface. The pod
# is Running, the log holds one line ('Cluster role "mx" not found in
# registry'), and the readiness probe is GREEN. Kubernetes cannot detect it.
#
# Three things in this chart contain that failure, and they are the reason the
# layout looks the way it does: mx ships with replicas: 0, the per-port
# Services publish only what was asked for, and the NetworkPolicy is a ceiling
# on reachability that holds no matter which ports the process actually bound.
# Documented as a trap rather than explained away.
nodes:
  # Everything: all tasks, all listeners. The group the Ingress points at.
  full:
    # 0 is allowed and scales this group down; the chart-global scaleDown wins.
    replicas: 1
    # Which ports this group may be reached on. NOT a copy of the listener
    # configuration in the database but a statement of its own: "this group is
    # reachable here and nowhere else". That is why a disagreement in either
    # direction is harmless — a role that binds more is unreachable on the
    # extra ports, and a policy that permits more has nothing listening — and
    # it is exactly what takes the edge off the fail-open above.
    #
    # Every group needs http, including mx: it is the port all three probes
    # use. It is not published for mx.
    exposedPorts: [smtp, submissions, imaps, http]
    resources:
      requests:
        cpu: 200m
        memory: 512Mi
        ephemeral-storage: 64Mi
    # Additive environment entries for this group's container, appended to the
    # ones the chart sets (STALWART_ROLE, STALWART_HOSTNAME and the secret-fed
    # ones). Supports the value, secretKeyRef and configMapKeyRef forms and is
    # rendered through tpl.
    #
    # ADDITIVE MEANS ADDITIVE: an entry repeating a name the chart already sets
    # does not replace it. At install both reach the pod and the later one wins;
    # on an EXISTING release Kubernetes merges env by name, the pair collapses
    # to the chart's own value, and helm upgrade still reports success. Do not
    # use this to override STALWART_ROLE.
    env: []
  # SMTP intake only. Add the matching ClusterRole in the database first:
  #   {"name":"mx","tasks":{"@type":"DisableAll"},"listeners":{"@type":"EnableSome", ...}}
  mx:
    # Zero until the role "mx" exists in the database. Raising this before the
    # role is there does not fail — it produces a second full node (see
    # fail-open above), which is the opposite of what this group is for.
    replicas: 0
    exposedPorts: [smtp, http]
    resources:
      requests:
        cpu: 100m
        memory: 256Mi
        ephemeral-storage: 64Mi
    env: []

# ---------------------------------------------------------------------------
# NetworkPolicy — the ceiling on reachability, independent of what bound what
# ---------------------------------------------------------------------------
networkPolicy:
  # On by default. Only a real boundary where the cluster's CNI enforces
  # NetworkPolicies; an unenforced policy is accepted by the API server and
  # filters nothing.
  enabled: true
  # Source CIDRs allowed to reach the http port, in addition to
  # allowedNamespaces. This is where the kubelet's probe traffic has to be
  # permitted: probes come from the IP of the WORKER node running the pod, an
  # address this chart cannot know.
  #
  # EMPTY MEANS OPEN, not blocked. With no entry the http rule is rendered
  # without a "from" selector, so the port is reachable from anywhere the CNI
  # routes to. That is the deliberate choice between two bad defaults: a
  # guessed CIDR that excludes the real node addresses blocks every probe, and
  # a pod that never becomes Ready reads as a broken application rather than as
  # a policy. http is not a NodePort, so "open" here means open inside the
  # cluster, not from the internet. Narrow it by listing the worker node IPs
  # (e.g. ["10.0.1.11/32", "10.0.1.12/32"]).
  #
  # And mind the companion trap: once this list is non-empty the http rule is
  # restricted, which cuts off the ingress controller too unless its namespace
  # is in allowedNamespaces below.
  probeSources: []
  # Namespaces allowed to reach the http port, matched on the
  # kubernetes.io/metadata.name label Kubernetes sets on every namespace
  # itself. The release's own namespace is always allowed. Put the ingress
  # controller's namespace here (e.g. ["ingress-nginx"]) as soon as
  # probeSources is set. A name that does not exist matches nothing and is
  # silently ineffective.
  allowedNamespaces: []
  # Egress is restricted BY PORT, not by destination, and the reason is a limit
  # of the object rather than laziness: a NetworkPolicy matches ipBlock CIDRs
  # and pod/namespace selectors, never hostnames — so dataStore.postgres.host
  # and externalServices.*.host cannot appear in it. Each rule below therefore
  # permits its port to any destination. What it still buys is real: a
  # compromised pod cannot open arbitrary ports outbound.
  #
  # Outbound SMTP is the one that must stay wide: delivering mail means
  # connecting to port 25 on any host on the internet.
  egress:
    # DNS (UDP and TCP 53) to any destination. Switching this off breaks
    # everything, including MX lookups and SPF.
    dns: true
    # Outbound SMTP on port 25 to any destination — required for delivery.
    # Deliberately NOT derived per group from the outboundMta task: this chart
    # does not know which tasks a role runs, the value would drift away from
    # the database, and the failure mode would be mail silently not leaving.
    # So it is uniform for every group.
    smtp: true
    # Additional outbound TCP ports, beyond the data store, S3 and Valkey ports
    # the chart already derives from the values above. Add 443 here if the
    # deployment needs outbound HTTPS (ACME over DNS-01 through a provider API,
    # an AI model endpoint, a remote lookup list).
    extraPorts: []

# ---------------------------------------------------------------------------
# External services — KUBERNETES ONLY. These do not configure Stalwart.
# ---------------------------------------------------------------------------
# The blob store and the in-memory store are objects in the database and are
# created in the WebUI. What the chart uses these values for is exactly three
# things, and nothing else:
#   - the port goes into the egress rule of every NetworkPolicy,
#   - the valkey host decides whether the in-memory store has an address at all
#     (see the fail below), and
#   - both hosts are printed in NOTES.txt as the addresses to enter in the
#     WebUI, so the installation checklist is not a separate document.
# Setting a host here does not point Stalwart at it.
externalServices:
  s3:
    host: ""
    port: 443
  valkey:
    # Empty plus valkey.enabled: true resolves to the subchart's Service,
    # "<release>-valkey". Empty with the subchart off and more than one
    # Stalwart pod ABORTS THE RENDER with a message naming both values, because
    # that combination is a cluster without an in-memory store: from v0.16 the
    # coordinator's Default variant "reuses the Redis connection already
    # configured on the in-memory store", so a multi-node install has no
    # coordination path at all. Failing the render is the loud version of a
    # cluster that comes up and then does not agree with itself.
    host: ""
    port: 6379

# ---------------------------------------------------------------------------
# TLS for the mail ports — cert-manager, not Stalwart's own ACME
# ---------------------------------------------------------------------------
# Why not Stalwart's built-in ACME: the HA proxy forwards 25, 465 and 993, and
# NOT 80, so an HTTP-01 challenge answered by Stalwart is unreachable from
# outside. DNS-01 inside Stalwart would work but would duplicate what
# cert-manager already does in this cluster.
#
# Why a certificate is needed at all when there is an Ingress: the Ingress
# covers only the WebUI and JMAP. The HA proxy terminates no TLS, so Stalwart
# itself has to present the certificate for STARTTLS on 25 and implicit TLS on
# 465 and 993.
certificate:
  enabled: true
  # Cluster issuer for the MAIL certificate. null falls back to
  # ingress.clusterIssuer.
  #
  # MIND THE CHALLENGE TYPE. The same reasoning that rules out Stalwart's ACME
  # rules out an HTTP-01 issuer here: port 80 does not reach this cluster for
  # the mail hostname. A DNS-01 issuer is usually the right answer, and it is
  # usually a DIFFERENT issuer from the one the Ingress uses — which is why
  # this is its own value instead of reusing ingress.clusterIssuer silently.
  clusterIssuer: null
  # Additional DNS names for the mail certificate. ingress.domain is always
  # included, so this is for the hostnames clients and other MTAs actually
  # connect to when they differ from the WebUI host — typically the MX name and
  # the autoconfig names (mail., smtp., imap.).
  extraDnsNames: []
  # Mount path of the issued certificate inside the container. A separate
  # top-level path rather than something under /etc/stalwart, so there is no
  # mount nested inside the config emptyDir.
  #
  # These two files are what the TLS object in the DATABASE has to point at:
  #   certificate: /etc/stalwart-tls/tls.crt
  #   privateKey:  /etc/stalwart-tls/tls.key
  mountPath: /etc/stalwart-tls

ingress:
  # Gates the whole Ingress template. ingress.domain stays REQUIRED either way:
  # it is read by the Certificate's dnsNames as well, so switching the Ingress
  # off would otherwise render a certificate with no name in it. Only
  # ingress.clusterIssuer becomes unnecessary — and only if
  # certificate.clusterIssuer is set, since that falls back to it.
  enabled: true
  # REQUIRED, no default.
  clusterIssuer: null
  # REQUIRED, no default.
  domain: null
  className: nginx
  # Which node group the Ingress routes to. Must be a key of nodes: above, and
  # that group must list http in its exposedPorts — both are checked, and the
  # render aborts naming the value. It matters that this is a single group: the
  # WebUI's setup and management screens are not safe to spread over a group
  # that may not run the management tasks, and a Service selecting several
  # groups would send every request to a random one of them.
  nodeGroup: full
  # Extra annotations for the Ingress; merged with the cert-manager
  # cluster-issuer annotation the chart always sets.
  annotations: {}

# ---------------------------------------------------------------------------
# Hardening — chart-wide, applied to every node group
# ---------------------------------------------------------------------------
securityContext:
  pod:
    # uid/gid 2000 is the image's own "stalwart" user: the image already runs
    # as non-root, so nothing has to be bent here.
    runAsNonRoot: true
    runAsUser: 2000
    runAsGroup: 2000
    # In the pod context so it also covers the init container that places
    # config.json; a container-level profile would have to be repeated for
    # every container and would be missed on the next one added.
    seccompProfile:
      type: RuntimeDefault
    # No fsGroup and no fsGroupChangePolicy: this chart mounts no PVC. Both
    # volumes are emptyDirs (state lives in Postgres, S3 and Valkey) and the
    # kubelet creates those owned by the pod's user already.
  container:
    allowPrivilegeEscalation: false
    readOnlyRootFilesystem: true
    runAsNonRoot: true
    # DOCUMENTED DEVIATION from the repo's hardening baseline (README,
    # guideline 5), forced by the stalwartlabs/stalwart image. Precedent for a
    # justified capability: samba.
    #
    # NET_BIND_SERVICE IS REQUIRED TO *START* THE CONTAINER, NOT TO BIND A PORT.
    # Both published image variants run
    #   setcap cap_net_bind_service=+ep /usr/local/bin/stalwart
    # (Dockerfile.build at v0.16.24, line 164 for the glibc target and line 186
    # for the musl/-alpine one). The "e" in "+ep" sets the file's effective
    # bit, which makes the binary a "capability-dumb binary" in the kernel's
    # terms, and capabilities(7) then applies this check at execve time:
    #
    #   "When executing a capability-dumb binary, the kernel checks if the
    #    process obtained all permitted capabilities that were specified in the
    #    file permitted set... If the process did not obtain the full set of
    #    file permitted capabilities, then execve(2) fails with the error
    #    EPERM."
    #
    # drop: [ALL] empties the bounding set, so the capability cannot be
    # obtained, so the exec fails outright:
    #   exec /usr/local/bin/stalwart: operation not permitted
    # The check runs BEFORE the program binds anything, and it does not ask
    # whether the capability is needed. This is why the three escape routes
    # that look obvious all fail for the same reason: high ports do not help,
    # the -alpine image carries the identical setcap, and the
    # net.ipv4.ip_unprivileged_port_start sysctl addresses binding rather than
    # exec.
    #
    # AND THE SECOND HALF, WHICH IS WHY THIS LINE MUST NOT BE "CLEANED UP":
    # THE CAPABILITY IS NEVER ACTUALLY USED. It is spent entirely on satisfying
    # the execve check. Stalwart does bind 25/465/993 here, which are
    # privileged — but inside a pod that needs no capability either way: the
    # kubelet sets net.ipv4.ip_unprivileged_port_start=0 in the pod network
    # namespace, so a non-root container binds low ports regardless (measured
    # in k3d for template-chart, see its ports comment). So a hardening pass
    # that greps for "a capability nobody uses" will find exactly this one and
    # removing it stops the chart from starting at all. Do not remove it
    # without first checking whether upstream still sets the file capability;
    # the day that setcap disappears from Dockerfile.build is the day this
    # deviation can go with it.
    capabilities:
      drop:
        - ALL
      add:
        - NET_BIND_SERVICE

# Probes for every node group, on the two separate endpoints the image
# provides. Values-configurable; an erased block falls back to these defaults
# rather than removing the probe.
#
# THE INTERVALS ARE CALCULATED, NOT TASTE. DO NOT TIGHTEN THEM WITHOUT REDOING
# THE ARITHMETIC BELOW.
#
# Stalwart applies an anonymous HTTP rate limit to /healthz as to everything
# else, and its default is 100 requests per 60 seconds KEYED ON THE SOURCE IP
# (registry default rate_limit_anonymous: count 100, period 60000ms). Kubelet
# probes arrive from the IP of the NODE running the pod, not from the pod, so
# every Stalwart pod on one node draws from the SAME bucket. Exceeding it
# returns 429, a 429 fails the probe, and failing liveness restarts the pod —
# a self-inflicted restart loop that gets worse the more pods a node holds.
#
# The budget per pod, with the values below:
#   steady state   liveness 60/20 = 3/min  +  readiness 60/20 = 3/min  = 6/min
#   while starting startup   60/10 = 6/min                             = 6/min
# The startup probe GATES liveness and readiness, so the three never run at
# once and 6 requests/min/pod is the worst case in both phases. Against a
# 100/60s bucket that leaves room for about 16 Stalwart pods per node before
# the limit is in sight.
#
# For comparison, the obvious 10/10/5 defaults would cost 12/min/pod in steady
# state and allow only about 8 pods per node — which is not far from a
# plausible deployment. That is the whole reason these numbers are 20/20/10.
#
# What the wider intervals cost, stated so the trade is visible: up to 20s
# before unreadiness removes a pod from its Services, and up to 60s
# (3 x 20s) before a hung pod is restarted. For a mail server both are
# acceptable — SMTP senders retry for days.
#
# WHY HTTP AND NOT A tcpSocket READINESS PROBE. A tcpSocket probe on the mail
# port would bypass the bucket entirely, and it was considered for exactly that
# reason. It is rejected on three grounds, none of them about convenience:
#   1. It would be GREEN in precisely the failure this chart is built to
#      contain. A node that fail-opens (its ClusterRole missing from the
#      database) binds every listener, so a TCP connect to 25 succeeds on a
#      broken "mx" node just as it does on a healthy "full" one.
#   2. It proves strictly less. A TCP accept says a socket is bound;
#      /healthz/ready additionally says the server reached the point where a
#      data store handle exists at all.
#   3. It would have to differ per node group (the "mx" group has no 465 or
#      993), so the fallback default in _helpers.tpl could no longer carry the
#      probe's context — the failure mode guideline 12.5 exists for.
# If a node ever does need to carry more than ~16 pods, the right move is to
# raise the limit on the server (the allow-list bypasses the limiter outright
# for listed addresses) rather than to blind the probes.
#
# WHAT THESE PROVE, AND WHAT THEY DO NOT — three honest limits:
#   - Liveness is deliberately on /healthz/live so a Postgres outage cannot
#     restart every pod in the cluster at once; the restart would fix nothing
#     and would drop every connection in flight (guideline 12.3).
#   - /healthz/ready DOES NOT QUERY THE DATABASE. Read from the source at
#     v0.16.24: it returns 200 iff the data store handle is not Store::None.
#     So readiness here does not hang on the dependency the way guideline 12.3
#     asks, and it cannot — the endpoint upstream offers is shallow. Named
#     rather than papered over, because a green pod proves less than it looks.
#   - It also does not catch the missing-config.json trap (a server that fell
#     back to an ephemeral in-memory store still has a data store handle).
#
# NOT VERIFIED AGAINST A RUNNING SERVER: whether /healthz answers a plain
# kubelet probe at all. The source shows no auth, no loopback check and no
# trusted-network restriction, but the request still passes the configurable
# Http.allowedEndpoints expression (default "200", i.e. everything allowed) —
# and its loopback escape hatch does NOT cover a node IP, so an operator who
# later writes a restrictive expression breaks every probe. The image's own
# healthcheck sends "X-Forwarded-For: 127.0.0.1", which is how it puts itself
# in the loopback rate-limit bucket; that only has an effect when
# Http.useXForwarded is on, and it is off by default.
livenessProbe:
  httpGet:
    path: /healthz/live
    port: http
  periodSeconds: 20
  timeoutSeconds: 5
  failureThreshold: 3
readinessProbe:
  httpGet:
    path: /healthz/ready
    port: http
  periodSeconds: 20
  timeoutSeconds: 5
  failureThreshold: 3
# The startup probe gates liveness and readiness, so neither needs an
# initialDelaySeconds. Budget = periodSeconds x failureThreshold = 300s, which
# is generous on purpose: the first start of a node has to reach Postgres,
# acquire its cluster node-id lease and read the whole configuration registry
# out of the database.
startupProbe:
  httpGet:
    path: /healthz/ready
    port: http
  periodSeconds: 10
  timeoutSeconds: 5
  failureThreshold: 30

# ---------------------------------------------------------------------------
# The Valkey subchart — THIS REPO'S OWN valkey CHART, off by default
# ---------------------------------------------------------------------------
# Stalwart needs an in-memory store for a cluster, and the coordinator rides on
# the same connection. The subchart is the path for a deployment that has no
# Valkey yet; an installation that already runs one points
# externalServices.valkey.host at it and leaves this off.
#
# THE SWITCH IS HERE AND NOT UNDER "valkey:", and it has to be. Everything under
# "valkey:" is handed to the subchart as its values, and our valkey chart ships
# a strict schema (additionalProperties: false) with no "enabled" property — so
# "valkey.enabled" is rejected BY THE SUBCHART. Measured; and because Helm skips
# a disabled subchart's schema validation, the error would only ever appear for
# whoever first switched it on. Chart.yaml has the error text.
valkeySubchart:
  enabled: false

# ---------------------------------------------------------------------------
# Values passed THROUGH to the valkey subchart
# ---------------------------------------------------------------------------
# Read as the subchart's own values, so the key names are ITS schema, not
# upstream's and not this chart's. `valkey/values.yaml` in the repo is the
# reference; its header comment explains the pairs. Nothing here has any effect
# while valkeySubchart.enabled is false.
#
# WHY THIS IS NOT "upstream's chart as it comes": it is our chart, so there is
# no third party's defaults to leave unpatched and no shortfall against this
# repo's conventions to document — it follows them because it IS one of them.
# What still applies in full is the subchart being invisible downstream (a
# Valkey fix reaches a cluster only when THIS chart is republished — Chart.yaml
# has the detail and the PR-ordering warning), that scaleDown and
# checksum/config stop at the subchart boundary, and that every helm command
# needs ci/helm-dependencies.sh to have run first.
valkey:
  secrets:
    # REQUIRED once the subchart is on — the subchart's own required() aborts
    # the render without it, which is the correct loud failure.
    #
    # MIND THE FIELD, it is not a password. The 1Password item carries ONE
    # field, `auth-conf`, whose value is the COMPLETE configuration line
    #     requirepass <password>
    # The valkey chart mounts that file and `include`s it, and an init container
    # refuses to start the pod unless the line is really there — because the
    # alternative failure is an open server that looks perfectly healthy. A bare
    # password in that field does not work.
    authSecretRef: null

  # CACHE, not queue — a decision, with its cost named.
  #
  # The valkey chart treats persistence and eviction as a PAIR and warns against
  # mixing them: QUEUE is `persistence.enabled: true` + `noeviction`, CACHE is
  # `persistence.enabled: false` + `allkeys-lru`.
  #
  # Stalwart's in-memory store holds rate-limiter counters, auth tokens and
  # sessions, auto-ban entries, and the cluster coordination pub/sub. Every one
  # of those is reconstructible: counters and bans restart from zero, tokens and
  # sessions force a re-authentication, and pub/sub messages are not stored keys
  # at all. Nothing in it is the system of record — messages and metadata are in
  # Postgres, blobs in S3, and the cluster node-id lease is in the data store
  # too, not here. Paying for a PVC and for AOF replay to protect data that is
  # worthless after a restart is the wrong trade, so: cache.
  #
  # THE COST, because `allkeys-lru` means keys really are discarded under memory
  # pressure: the rate limiters and the auto-ban FAIL OPEN. An attacker who can
  # drive memory usage can age out their own ban entry. The answer is to size
  # memory for the working set rather than to switch to `noeviction` — with
  # `noeviction` Stalwart's writes to the store start erroring instead, which
  # takes out authentication rather than just the limits. Size it, and treat the
  # limiters as a nuisance filter, not as a security boundary.
  persistence:
    enabled: false

  valkey:
    maxmemoryPolicy: allkeys-lru
    # The subchart derives maxmemory from the computed memory limit and aborts
    # its render if an explicit maxmemory exceeds it. Defaults left alone.
    resources:
      requests:
        cpu: 50m
        memory: 128Mi
        ephemeral-storage: 32Mi

  # The subchart's own NetworkPolicy, with its own semantics — this chart's
  # networkPolicy block does not reach it. On by default there, allowing the
  # release's own namespace. It needs an entry here only when Stalwart runs in a
  # DIFFERENT namespace from the Valkey, which with the subchart it does not.
  networkPolicy:
    allowedNamespaces: []