nix: run the review classifier in a container of its own when a host enables it
deploy.review-classifier.enable (off by default, not derived from allSwarmServices) puts swarm-review-classifier in its own network namespace on the bridge, with claude-code and the daemon. A host unit copies the classifier's store leaf into the container; the daemon reads its queue client secret and the API key from the store with it. - glue-bao-tls mints the review-classifier leaf; swarm-bao writes the swarm-review-classifier role, reading exactly the API key path and the classifier's queue client secret; swarm.nix reserves its CN. - glue-review-classifier-oidc-client registers the machine client where authelia runs, and the publisher carries its secret to the store. - swarm-nats passes the client id to the responder as --review-classifier-client. - Where the host runs a hive-tier collector, claude exports its metrics there; the daemon adds the repo and the PR to the resource attributes. - module-eval: the new grant and leaf (bao-grants, now sixteen granting units), the container's presence and its unit (core-toggle), and the client registration and publishing (secret-publisher).
This commit is contained in:
atlas
mara
parent
d70ed41537
commit
5d8ab675cd
14 changed files with 435 additions and 8 deletions
220
nix/host-modules/swarm-review-classifier.nix
Normal file
220
nix/host-modules/swarm-review-classifier.nix
Normal file
|
|
@ -0,0 +1,220 @@
|
|||
# The review classifier, in a `swarm-review-classifier` container on the host
|
||||
# that sets `deploy.review-classifier.enable`. It answers the swarm UI's review
|
||||
# try-outs: swarm-controller sends a PR and the operator's classifications over
|
||||
# the queue, and the daemon runs `claude` once per classification and replies.
|
||||
# docs/swarm/review-classifier.md has the design.
|
||||
#
|
||||
# ⚠️ Its own network namespace on the bridge, as ./swarm-ci-runner.nix has: a
|
||||
# PR's diff and commit messages are model input, so the container reaches the
|
||||
# swarm services by name and nothing on the host's loopback.
|
||||
#
|
||||
# The container holds one credential, its own store leaf, which the host unit
|
||||
# below copies in. The daemon reads everything else from the store with it:
|
||||
# its queue client secret at start and the API key on every run.
|
||||
{
|
||||
pkgs,
|
||||
lib,
|
||||
config,
|
||||
...
|
||||
}:
|
||||
let
|
||||
hyperhiveCfg = config.services.hyperhive;
|
||||
cfg = hyperhiveCfg.deploy.review-classifier;
|
||||
baoCfg = hyperhiveCfg.swarm.bao;
|
||||
baoDeploy = hyperhiveCfg.deploy.bao;
|
||||
natsCfg = hyperhiveCfg.swarm.nats;
|
||||
autheliaCfg = hyperhiveCfg.swarm.authelia;
|
||||
gatewayCfg = hyperhiveCfg.gateway;
|
||||
networkCfg = hyperhiveCfg.network;
|
||||
otelCfg = hyperhiveCfg.otel;
|
||||
tlsCfg = hyperhiveCfg.deploy.hive-controller.tls;
|
||||
|
||||
machine = "swarm-review-classifier";
|
||||
unit = "swarm-review-classifier";
|
||||
clientId = hyperhiveCfg.swarm.review-classifier.clientId;
|
||||
|
||||
# The daemon reaches authelia, the store and the queue by name over TLS, and
|
||||
# in self-signed mode their leaves chain to the hive CA.
|
||||
caTrust = import ./lib/hive-ca-trust.nix { inherit lib tlsCfg gatewayCfg; };
|
||||
caBundleModule = caTrust.trustBundle {
|
||||
inherit pkgs;
|
||||
name = machine;
|
||||
consumers = [ unit ];
|
||||
};
|
||||
|
||||
haveClientIdentity =
|
||||
baoDeploy.reviewClassifierClientCertFile != null && baoDeploy.reviewClassifierClientKeyFile != null;
|
||||
|
||||
# Credential id → host source, copied into the container and loaded by the
|
||||
# daemon's unit alone.
|
||||
storeFiles = {
|
||||
"bao-client.pem" = baoDeploy.reviewClassifierClientCertFile;
|
||||
"bao-client-key.pem" = baoDeploy.reviewClassifierClientKeyFile;
|
||||
}
|
||||
// lib.optionalAttrs (baoDeploy.serverCaFile != null) {
|
||||
"bao-ca.pem" = baoDeploy.serverCaFile;
|
||||
};
|
||||
secretDirInContainer = "/var/lib/swarm-review-classifier";
|
||||
inContainer = id: "${secretDirInContainer}/${id}";
|
||||
secretDir = "/var/lib/nixos-containers/${machine}${secretDirInContainer}";
|
||||
credential = id: "/run/credentials/${unit}.service/${id}";
|
||||
|
||||
# What `claude` exports its metrics with, where this host runs a hive-tier
|
||||
# collector on the bridge. The daemon adds the repo and the PR to the
|
||||
# resource attributes for each run.
|
||||
otelEnv = lib.optionalAttrs otelCfg.enable {
|
||||
CLAUDE_CODE_ENABLE_TELEMETRY = "1";
|
||||
OTEL_METRICS_EXPORTER = "otlp";
|
||||
OTEL_EXPORTER_OTLP_ENDPOINT = "http://${networkCfg.bridgeIp}:${toString otelCfg.collector.port}";
|
||||
OTEL_EXPORTER_OTLP_PROTOCOL = "http/protobuf";
|
||||
# Claude Code defaults to delta, which the metrics store drops.
|
||||
OTEL_EXPORTER_OTLP_METRICS_TEMPORALITY_PREFERENCE = "cumulative";
|
||||
OTEL_RESOURCE_ATTRIBUTES = "service.name=hyperhive-review-classifier,swarm=${
|
||||
if hyperhiveCfg.swarm.name == null then "unknown" else hyperhiveCfg.swarm.name
|
||||
}";
|
||||
};
|
||||
|
||||
privateNetwork = true;
|
||||
in
|
||||
{
|
||||
options.services.hyperhive.swarm.review-classifier.clientId = lib.mkOption {
|
||||
type = lib.types.str;
|
||||
readOnly = true;
|
||||
default = "swarm-review-classifier";
|
||||
description = ''
|
||||
The OAuth2 client id the review classifier presents to the swarm queue.
|
||||
Read-only: the host running authelia registers it, the queue's
|
||||
auth-callout responder grants it the try-out subject, and the secret
|
||||
publisher carries its secret to the store, all from this one value.
|
||||
'';
|
||||
};
|
||||
|
||||
options.services.hyperhive.deploy.review-classifier.package = lib.mkOption {
|
||||
type = lib.types.package;
|
||||
defaultText = lib.literalExpression "hyperhive.packages.\${system}.swarm-review-classifier";
|
||||
description = "The review classifier daemon package.";
|
||||
};
|
||||
|
||||
config = lib.mkIf cfg.enable {
|
||||
assertions = [
|
||||
{
|
||||
assertion = haveClientIdentity;
|
||||
message = ''
|
||||
services.hyperhive.deploy.review-classifier.enable requires the
|
||||
classifier's swarm-secret-store client identity: set both
|
||||
|
||||
services.hyperhive.deploy.bao.reviewClassifierClientCertFile
|
||||
services.hyperhive.deploy.bao.reviewClassifierClientKeyFile
|
||||
|
||||
The classifier reads its queue client secret and the API key with it.
|
||||
|
||||
Both default to the pair glue-bao-tls.nix mints when
|
||||
services.hyperhive.deploy.bao.enable is true (the host that runs the
|
||||
store). Otherwise copy review-classifier.pem and
|
||||
review-classifier-key.pem from the store host's /var/lib/swarm-bao-pki/
|
||||
and name them in those two options.
|
||||
'';
|
||||
}
|
||||
];
|
||||
|
||||
# The container hangs off the bridge, takes its address from the gateway's
|
||||
# DHCP and resolves through its dnsmasq.
|
||||
services.hyperhive.network.enable = lib.mkDefault true;
|
||||
services.hyperhive.gateway.enable = lib.mkDefault true;
|
||||
services.hyperhive.gateway.dns.enable = lib.mkDefault true;
|
||||
|
||||
# A copy rather than a bind mount: nixos-container refuses to start on a
|
||||
# missing bind source, and the leaf may not be minted yet.
|
||||
systemd.services.swarm-review-classifier-identity = {
|
||||
description = "deliver the review classifier's store identity into its container";
|
||||
before = [ "container@${machine}.service" ];
|
||||
wantedBy = [ "container@${machine}.service" ];
|
||||
# Ordering only: where the store's PKI is minted on this host, the leaf
|
||||
# is one of its files.
|
||||
after = [ "swarm-bao-pki.service" ];
|
||||
serviceConfig = {
|
||||
Type = "oneshot";
|
||||
RemainAfterExit = true;
|
||||
SyslogIdentifier = "swarm-review-classifier-identity";
|
||||
};
|
||||
path = [ pkgs.coreutils ];
|
||||
script = ''
|
||||
set -euo pipefail
|
||||
install -d -m 0700 ${lib.escapeShellArg secretDir}
|
||||
''
|
||||
+ lib.concatStrings (
|
||||
lib.mapAttrsToList (id: source: ''
|
||||
install -m 0400 ${lib.escapeShellArg source} ${lib.escapeShellArg "${secretDir}/${id}"}
|
||||
'') storeFiles
|
||||
);
|
||||
};
|
||||
|
||||
systemd.services."container@${machine}" = caTrust.containerOrdering;
|
||||
|
||||
containers.${machine} = {
|
||||
autoStart = true;
|
||||
# Not ephemeral: an ephemeral root lives under /run, where the identity
|
||||
# copy above does not write. The daemon itself keeps no state.
|
||||
ephemeral = false;
|
||||
# Journal files on the host, not inside the container: nixpkgs hardcodes
|
||||
# --link-journal=try-guest, and EXTRA_NSPAWN_FLAGS expands after it.
|
||||
extraFlags = [ "--link-journal=host" ];
|
||||
inherit privateNetwork;
|
||||
hostBridge = networkCfg.bridgeName;
|
||||
bindMounts = caTrust.bindMount;
|
||||
|
||||
config =
|
||||
{ pkgs, lib, ... }:
|
||||
{
|
||||
imports = [
|
||||
../container-modules/swarm-container.nix
|
||||
caBundleModule
|
||||
];
|
||||
|
||||
services.hyperhive.swarmContainer = {
|
||||
inherit privateNetwork;
|
||||
writesOwnResolvConf = false;
|
||||
};
|
||||
networking.nameservers = [ networkCfg.bridgeIp ];
|
||||
networking.interfaces.eth0.useDHCP = true;
|
||||
|
||||
# `claude-code` is unfree, and this container evaluates its own
|
||||
# nixpkgs, so the host's allowance does not reach here.
|
||||
nixpkgs.config.allowUnfreePredicate = pkg: builtins.elem (lib.getName pkg) [ "claude-code" ];
|
||||
|
||||
systemd.services.${unit} = {
|
||||
description = "answer the swarm UI's review try-outs";
|
||||
wantedBy = [ "multi-user.target" ];
|
||||
wants = [ "network-online.target" ];
|
||||
after = [ "network-online.target" ];
|
||||
environment = {
|
||||
BAO_ADDR = "https://${baoCfg.domain}:${toString baoCfg.port}";
|
||||
BAO_CLIENT_CERT = credential "bao-client.pem";
|
||||
BAO_CLIENT_KEY = credential "bao-client-key.pem";
|
||||
SWARM_REVIEW_CLASSIFIER_NATS_URL = "tls://${natsCfg.domain}:${toString natsCfg.port}";
|
||||
SWARM_REVIEW_CLASSIFIER_OIDC_TOKEN_ENDPOINT = "${autheliaCfg.url}/api/oidc/token";
|
||||
SWARM_REVIEW_CLASSIFIER_OIDC_CLIENT_ID = clientId;
|
||||
SWARM_REVIEW_CLASSIFIER_CLAUDE = "${pkgs.claude-code}/bin/claude";
|
||||
}
|
||||
// lib.optionalAttrs (storeFiles ? "bao-ca.pem") {
|
||||
BAO_CACERT = credential "bao-ca.pem";
|
||||
}
|
||||
// lib.optionalAttrs caTrust.useSelfSigned {
|
||||
SWARM_REVIEW_CLASSIFIER_OIDC_CA_FILE = caTrust.bundlePathFor machine;
|
||||
}
|
||||
// otelEnv;
|
||||
serviceConfig = {
|
||||
ExecStart = "${cfg.package}/bin/swarm-review-classifier";
|
||||
DynamicUser = true;
|
||||
# Each classification's scratch directory, gone with the unit.
|
||||
PrivateTmp = true;
|
||||
LoadCredential = lib.mapAttrsToList (id: _: "${id}:${inContainer id}") storeFiles;
|
||||
Restart = "on-failure";
|
||||
RestartSec = "10s";
|
||||
SyslogIdentifier = unit;
|
||||
};
|
||||
};
|
||||
};
|
||||
};
|
||||
};
|
||||
}
|
||||
Loading…
Reference in a new issue