swarm UI: log an agent into claude from its card; the credentials go to bao and the agent picks them up
A new swarm service, `swarm-claude-login`, in its own container on the host
that sets `deploy.claude-login.enable` (defaulted on by `allSwarmServices`
where the host has the minter's store leaf, like the review classifier).
- swarm-ui: an agent card showing "login needed" gets a "log in" button.
Its dialog starts the login, shows the URL claude printed, and takes the
pasted code.
- swarm-controller: `POST/DELETE /api/agents/{name}/claude-login` and
`POST /api/agents/{name}/claude-login/code`, behind the swarm UI's
authelia-gated `/api/`, relay the steps to the minter as requests on
`$SWARM.claude-login.request`.
- swarm-claude-login: runs `claude auth login` over piped stdio with HOME
and CLAUDE_CONFIG_DIR in a per-login scratch dir, scrapes the first
https URL, writes the code to stdin, and stores the `.credentials.json`
at `swarm/agents/<agent>/claude-credentials` with a KV v2 write, a new
version over any earlier one. The scratch dir goes on every exit path; a
login waits 15 minutes for its code.
- hive-agent: while parked in `wait_for_login`, reads that leaf every 30 s
under the agent's own cert and installs it only when its KV version is
newer than the one recorded in `<harness>/claude-credentials-version`.
An equal or older version is never put back, because claude rotates the
refresh token and the stored copy is stale after the first refresh.
- swarm-secret-client: `claude_login` paths and `SecretStore::read_versioned`.
- Credentials: a `claude-login` store leaf minted by glue-bao-tls, a
`swarm-claude-login` policy (create/update on
`swarm/agents/+/claude-credentials`, read on its own queue client
secret), an authelia machine client, and a `--claude-login-client`
grant in the queue's auth-callout responder. The unit runs as a static
system user.
The hive's own web-UI login is unchanged.
Refs #5268
This commit is contained in:
atlas
mara
parent
248df20164
commit
d5de1e4943
48 changed files with 2680 additions and 42 deletions
|
|
@ -169,7 +169,7 @@ let
|
|||
_: u: (u.environment.BAO_CLIENT_CERT or null) == granterCertFile
|
||||
) baoGrantWithConsumers.systemd.services;
|
||||
|
||||
# The nineteen units that write a `swarm-*` grant, by name, for the discovery
|
||||
# The twenty units that write a `swarm-*` grant, by name, for the discovery
|
||||
# control below.
|
||||
grantingUnitNames = [
|
||||
"swarm-bao-controller-policy"
|
||||
|
|
@ -191,6 +191,7 @@ let
|
|||
"swarm-bao-forge-publisher-policy"
|
||||
"swarm-bao-review-classifier-policy"
|
||||
"swarm-bao-builder-policy"
|
||||
"swarm-bao-claude-login-policy"
|
||||
];
|
||||
|
||||
# Comment lines dropped first: both the HCL and the scripts explain
|
||||
|
|
@ -976,24 +977,24 @@ let
|
|||
}
|
||||
{
|
||||
# A store host without the granter's pair writes its grants some other
|
||||
# way, so none of the nineteen units may exist. Without this arm
|
||||
# way, so none of the twenty units may exist. Without this arm
|
||||
# `lib.mkIf haveGranter` could be dropped from any of them and every other
|
||||
# case here would still pass.
|
||||
name = "without the granter's pair none of the nineteen granting units render";
|
||||
name = "without the granter's pair none of the twenty granting units render";
|
||||
ok =
|
||||
let
|
||||
s = baoGranterOptOut.systemd.services;
|
||||
in
|
||||
lib.all (unit: !(s ? ${unit})) (grantingUnitNames ++ [ "swarm-bao-granter-role" ])
|
||||
# The control: the same store with the pair renders all nineteen.
|
||||
# The control: the same store with the pair renders all twenty.
|
||||
&& lib.all (unit: baoGrantHere.systemd.services ? ${unit}) grantingUnitNames;
|
||||
}
|
||||
{
|
||||
# 🩸 What replaced the silent skip. With no bootstrap token the nineteen still
|
||||
# 🩸 What replaced the silent skip. With no bootstrap token the twenty still
|
||||
# render, and a refused granter fails them with the step that fixes it.
|
||||
# A store host that never named a token is told to name one, since the
|
||||
# unit that sets the granter up renders only where it has.
|
||||
name = "a store host without a bootstrap token renders the nineteen, each failing loudly with the one-time step";
|
||||
name = "a store host without a bootstrap token renders the twenty, each failing loudly with the one-time step";
|
||||
ok =
|
||||
let
|
||||
s = baoGranterNoToken.systemd.services;
|
||||
|
|
@ -1595,6 +1596,44 @@ let
|
|||
in
|
||||
lib.hasInfix "/builder.pem ]" s && lib.hasInfix "swarm-builder \"\" clientAuth" s;
|
||||
}
|
||||
{
|
||||
# The minter writes one leaf under every agent, create and update so a
|
||||
# relogin replaces the last, and reads its own queue client secret. No
|
||||
# read on the leaf, and nothing else under an agent.
|
||||
name = "the claude login minter's grant is create and update on agents' claude-credentials, and its queue client secret";
|
||||
ok =
|
||||
let
|
||||
s = baoGrantHere.systemd.services.swarm-bao-claude-login-policy.script;
|
||||
grants = grantsIn s;
|
||||
in
|
||||
(grantFor grants "secret/data/swarm/agents/+/claude-credentials").caps == [
|
||||
"create"
|
||||
"update"
|
||||
]
|
||||
&& (grantFor grants "secret/data/swarm/services/swarm-claude-login/oidc/client").caps == [ "read" ]
|
||||
&& lib.length grants == 2
|
||||
&& !(lib.hasInfix "secret/data/swarm/agents/*" s)
|
||||
&& lib.hasInfix "auth/cert/certs/swarm-claude-login" s
|
||||
&& lib.hasInfix "allowed_common_names=swarm-claude-login" s
|
||||
&& lib.hasInfix "token_policies=swarm-claude-login" s;
|
||||
}
|
||||
{
|
||||
# The leaf by name: the minter writes it. The agent's own read and the
|
||||
# controller's `swarm/agents/*` reach it without naming it.
|
||||
name = "no granting unit but the claude login minter's names the claude-credentials leaf";
|
||||
ok =
|
||||
lib.filter (
|
||||
u: lib.hasInfix "claude-credentials" baoGrantHere.systemd.services.${u}.script
|
||||
) grantingUnitNames == [ "swarm-bao-claude-login-policy" ];
|
||||
}
|
||||
{
|
||||
name = "the PKI unit signs the claude login minter's leaf under its own subject";
|
||||
ok =
|
||||
let
|
||||
s = baoGrantHere.systemd.services.swarm-bao-pki.script;
|
||||
in
|
||||
lib.hasInfix "/claude-login.pem ]" s && lib.hasInfix "swarm-claude-login \"\" clientAuth" s;
|
||||
}
|
||||
{
|
||||
name = "the PKI unit signs the CI runner's leaf under its own subject";
|
||||
ok =
|
||||
|
|
@ -1826,8 +1865,8 @@ let
|
|||
}
|
||||
{
|
||||
# What makes the case above mean something: discovery by the granter's
|
||||
# certificate reaches all nineteen units, and each yields calls.
|
||||
name = "the granter-policy check sees all nineteen granting units, and parses calls from each";
|
||||
# certificate reaches all twenty units, and each yields calls.
|
||||
name = "the granter-policy check sees all twenty granting units, and parses calls from each";
|
||||
ok =
|
||||
lib.sort lib.lessThan (lib.attrNames granterUnits) == lib.sort lib.lessThan grantingUnitNames
|
||||
&& lib.all (u: baoCalls u.script != [ ]) (lib.attrValues granterUnits)
|
||||
|
|
|
|||
|
|
@ -365,6 +365,27 @@ let
|
|||
&& lib.hasInfix socket l."/webhook/forge/".proxyPass
|
||||
&& !(lib.hasInfix "auth_request" l."/webhook/forge/".extraConfig);
|
||||
}
|
||||
{
|
||||
# nginx serves a path from its longest matching prefix location, so that
|
||||
# one must be the gated `/api/`, and no exact location may take a route
|
||||
# out from under it.
|
||||
name = "the claude login routes reach the controller only through a location that asks authelia";
|
||||
ok =
|
||||
let
|
||||
l = allLocal.services.nginx.virtualHosts."t.local".locations;
|
||||
route = "/api/agents/a/claude-login/code";
|
||||
covering = lib.filter (
|
||||
name: !(lib.hasPrefix "~" name) && !(lib.hasPrefix "= " name) && lib.hasPrefix (prefix name) route
|
||||
) (lib.attrNames l);
|
||||
prefix = lib.removePrefix "^~ ";
|
||||
longest = lib.foldl' (
|
||||
a: b: if lib.stringLength (prefix b) > lib.stringLength (prefix a) then b else a
|
||||
) "" covering;
|
||||
in
|
||||
longest == "/api/"
|
||||
&& lib.hasInfix "auth_request /__hive_authelia;" l.${longest}.extraConfig
|
||||
&& !(lib.any (name: lib.hasPrefix "= /api/agents" name) (lib.attrNames l));
|
||||
}
|
||||
{
|
||||
name = "a hive with matrix off serves no matrix discovery endpoint";
|
||||
ok =
|
||||
|
|
|
|||
|
|
@ -163,8 +163,9 @@ let
|
|||
lib.filter (l: swarmServiceLinkDomains ? ${l.label}) cfg.services.hyperhive.swarm.controller.links;
|
||||
|
||||
# Every service container at once: the services-only host plus the CI
|
||||
# runner. The CI runner, the review classifier, the builder, the metrics
|
||||
# store and the homeserver are the five containers on a netns of their own.
|
||||
# runner. The CI runner, the review classifier, the builder, the claude login
|
||||
# minter, the metrics store and the homeserver are the six containers on a
|
||||
# netns of their own.
|
||||
serviceContainersWithCi = hive {
|
||||
deploy.hive-controller.enable = false;
|
||||
deploy.allSwarmServices = true;
|
||||
|
|
@ -247,6 +248,30 @@ let
|
|||
&& !(swarmServicesBaoElsewhere.containers ? swarm-builder)
|
||||
&& swarmServicesBaoElsewhere.services.hyperhive.deploy.nats.enable;
|
||||
}
|
||||
{
|
||||
# Static, not `DynamicUser`: the user is declared in the container and
|
||||
# the unit names it. `nats` is the control that the switch is on at all.
|
||||
name = "hosting the swarm's shared services runs the claude login minter in its container as a static user";
|
||||
ok =
|
||||
let
|
||||
c = swarmServicesHere.containers.swarm-claude-login.config;
|
||||
sc = c.systemd.services.swarm-claude-login.serviceConfig;
|
||||
in
|
||||
swarmServicesHere.services.hyperhive.deploy.claude-login.enable
|
||||
&& c.users.users.swarm-claude-login.isSystemUser
|
||||
&& sc.User == "swarm-claude-login"
|
||||
&& !(sc.DynamicUser or false)
|
||||
&& swarmServicesHere.services.hyperhive.deploy.nats.enable;
|
||||
}
|
||||
{
|
||||
# The minter's module asserts the store identity the store's host mints,
|
||||
# as the classifier's does.
|
||||
name = "the claude login minter stays off where the shared services are hosted without the store";
|
||||
ok =
|
||||
!swarmServicesBaoElsewhere.services.hyperhive.deploy.claude-login.enable
|
||||
&& !(swarmServicesBaoElsewhere.containers ? swarm-claude-login)
|
||||
&& swarmServicesBaoElsewhere.services.hyperhive.deploy.nats.enable;
|
||||
}
|
||||
{
|
||||
# The switch fills in for an operator who has not spoken and yields to
|
||||
# one who has — that is what keeps a shared service placeable on a host
|
||||
|
|
|
|||
Loading…
Reference in a new issue