ffd5018b18
Every agent on a hive authenticates to the swarm queue with the same hive-scoped secret today, so at the auth callout one agent is indistinguishable from its co-hived neighbours and no subject can be scoped to one of them. Mint a secret per agent instead, at swarm level, into secret/swarm/agents/<agent>/queue -- inside the stanza every agent's ACL document already grants, so no policy changes and no existing agent's document is rewritten. It is written by the same node that already mints the agent's certificate, and read back under the agent's own token before that node reports success. The secret is not derived from the agent's mTLS identity: the two credentials answer different questions and coupling their lifetimes would mean renewing either implied renewing the other. Nothing here rotates a queue secret -- a re-run keeps the existing value and only corrects the principal it names, because this function is re-run deliberately against agents that are already connected. Revoking one means deleting the path. Nothing reads the new credential yet; this is the minting half.
128 lines
6.3 KiB
TOML
128 lines
6.3 KiB
TOML
[package]
|
|
name = "swarm-controller"
|
|
version.workspace = true
|
|
readme = "README.md"
|
|
edition.workspace = true
|
|
|
|
[[bin]]
|
|
name = "swarm-controller"
|
|
path = "src/main.rs"
|
|
|
|
[dependencies]
|
|
anyhow.workspace = true
|
|
# `kv` (which pulls `jetstream`) on top of the workspace's feature set: the
|
|
# queue is this daemon's *store*, not just its transport - a hive's last
|
|
# status snapshot is read out of a JetStream KV bucket. Declared here rather
|
|
# than in the workspace entry so the auth-callout responder, which speaks
|
|
# neither, does not claim to need them.
|
|
async-nats = { workspace = true, features = ["kv"] }
|
|
axum.workspace = true
|
|
# swarm-controller's own forge client (`forge.rs`) — self-contained,
|
|
# deliberately not sharing code with `hive-c0re::forge` across the crate
|
|
# boundary (see #3306's design discussion: forcing that split now, over a
|
|
# few idempotent CRUD-ish calls, is premature plumbing).
|
|
forgejo-api.workspace = true
|
|
# Only for base64-encoding file content for `forge.rs`'s
|
|
# `repo_change_files` calls — forgejo's content API takes base64, never
|
|
# raw bytes.
|
|
base64.workspace = true
|
|
# `agent_identity.rs` mints the per-agent queue secret, the one value in this
|
|
# tree this daemon invents rather than receives. Straight from the kernel's
|
|
# CSPRNG — see the workspace entry for why this and not `rand`.
|
|
getrandom.workspace = true
|
|
futures-util.workspace = true
|
|
# RFC 9457 `application/problem+json` error bodies. Same version + `axum`
|
|
# feature as hive-c0re: the two daemons answer the same operator UIs, so a
|
|
# reader that handles one's failures has to handle the other's.
|
|
problem_details = { version = "0.9.0", features = ["axum"] }
|
|
# The graph itself, held directly rather than behind a c0re-style wrapper
|
|
# module — that layering (`hive-c0re::job_queue`) is partially legacy (predates
|
|
# `hive-jobq`'s extraction into its own crate) and this daemon does not need it
|
|
# repeated. Driven by `hive_jobq::scheduler::Scheduler` (`spawn_jobq_worker`),
|
|
# same shape `hive-c0re/src/job_queue/scheduler.rs` uses over its own graph.
|
|
hive-jobq.workspace = true
|
|
hive-jobq-wire.workspace = true
|
|
hive-log.workspace = true
|
|
# The jobq-rollup OTEL exporter, wired up in `main` via
|
|
# `hive_jobq_metrics::spawn_exporter` — moved to its own crate (rather than
|
|
# living here as `jobq_metrics.rs`) specifically so a future second caller
|
|
# (e.g. hive-c0re, for its own per-hive job graph) doesn't have to depend on
|
|
# this whole binary to reuse it.
|
|
hive-jobq-metrics.workspace = true
|
|
# Direct OTEL SDK use in `vcs_metrics.rs` — sync counters recorded off
|
|
# webhook deliveries, a different shape from `hive-jobq-metrics`'s
|
|
# observable-gauge rollup, so it isn't a fit for that crate's API and lives
|
|
# here instead. Same three crates that pairing already pulls in transitively,
|
|
# named directly since this module builds its own `SdkMeterProvider`.
|
|
opentelemetry.workspace = true
|
|
opentelemetry_sdk.workspace = true
|
|
opentelemetry-otlp.workspace = true
|
|
# The forge webhook HMAC (`webhook.rs`). Kept in this crate rather than
|
|
# shared with hive-c0re's equivalent: c0re's copy is scheduled to be deleted
|
|
# with its webhook routes once registration moves here, so the second holder
|
|
# is departing, not arriving — see that module's docs.
|
|
hmac.workspace = true
|
|
sha2.workspace = true
|
|
# Validates `POST /api/agents`' `name` before it becomes `agent`/`repo`
|
|
# everywhere downstream — see `create_agent`'s doc comment for why this is
|
|
# defense-in-depth, not the only gate (per an argus review finding).
|
|
hive-types.workspace = true
|
|
# `auth`'s bridge client — same crate the bridge itself uses to define the
|
|
# request/response shape, so the two ends cannot drift. `forge.rs` also
|
|
# uses this directly for `StatusCode` in its error-classification helpers.
|
|
#
|
|
# `blocking` on top of the workspace default: `vcs_metrics`'s OTLP exporter
|
|
# runs on a thread with no tokio reactor (see that module's doc), so the
|
|
# `reqwest::blocking::Client` it hands to `AuthenticatedHttpClient` has to
|
|
# come from the blocking half of this crate, not the async one every other
|
|
# consumer here uses.
|
|
reqwest = { workspace = true, features = ["blocking"] }
|
|
serde.workspace = true
|
|
serde_json.workspace = true
|
|
strum.workspace = true
|
|
swarm-authelia-bridge-sock.workspace = true
|
|
# The queue connect (token mint + auth callback + reconnect) is shared with
|
|
# every other participant - a hive publishing its own status runs the same
|
|
# code with a different client id. Two copies of credential handling is one
|
|
# token-refresh fix that has to be found twice.
|
|
#
|
|
# `kv` for the same reason one level in: the status bucket's name and
|
|
# creation config are shared with the hive that writes it, so this end does
|
|
# not get to declare them privately.
|
|
#
|
|
swarm-queue-client = { workspace = true, features = ["kv"] }
|
|
# `matrix_account.rs` writes the credential this daemon's route accepts. Same
|
|
# crate the hive reads it back with, which is the point: the path, the field
|
|
# name and the object's shape are agreements between the two ends, and a
|
|
# second spelling here would be a store this hive could not read.
|
|
swarm-secret-client.workspace = true
|
|
# `agent_identity.rs` signs the per-agent client leaf the store authenticates
|
|
# an agent container by. The one runtime signer in this tree — every other CA
|
|
# here is a deploy-time `openssl` oneshot — because this one issues per agent
|
|
# creation and must keep the key it generates in memory, never on disk.
|
|
rcgen.workspace = true
|
|
# `rcgen::CertificateParams`'s validity window is a `time::OffsetDateTime`,
|
|
# which `agent_identity::validity` builds. Same workspace pin every other
|
|
# holder of a timestamp here uses.
|
|
time.workspace = true
|
|
# `otel_http_client.rs`'s `AuthenticatedHttpClient` — an
|
|
# `opentelemetry_http::HttpClient` impl authenticated with this crate's own
|
|
# `swarm-queue-client` identity. Lives in this crate rather than
|
|
# `swarm-queue-client` (mara's own call during review) since this daemon is
|
|
# its only caller; see that module's doc for the full rationale. `opentelemetry-http`
|
|
# is also needed directly (not just transitively) so `main.rs` can name
|
|
# `Box<dyn opentelemetry_http::HttpClient>` when handing
|
|
# `vcs_metrics::authenticated_http_client()`'s output to
|
|
# `hive_jobq_metrics::spawn_exporter`.
|
|
opentelemetry-http.workspace = true
|
|
async-trait.workspace = true
|
|
bytes.workspace = true
|
|
http.workspace = true
|
|
tokio.workspace = true
|
|
tracing.workspace = true
|
|
url.workspace = true
|
|
utoipa.workspace = true
|
|
utoipa-axum.workspace = true
|
|
|
|
[lints]
|
|
workspace = true
|