2fc0166427
Every run is recorded when it ends: a try-out when its reply settles it, a requested review once its review is posted or the post fails, and a request turned away by a full queue once its comment is posted. A duplicate request that starts nothing is not recorded. The newest 100 are one JSON array under `recent` in a new controller-owned KV bucket, `review-classifier-runs`, written with compare-and-set as `schedule-definitions` is (five attempts). A failed write is logged; the review is already posted by then. Each recorded run is also one info event, "review classifier run finished", with the record's fields as tracing fields. The controller logs natively to the journal, so they reach VictoriaLogs as F_<NAME>. GET /api/review-classifier/runs returns the list, newest first, gated by the gateway like the try-out GET. post_classifier_review now returns the posted review's html_url, which the record keeps as review_url. Closes #5153, part of #5096.
145 lines
6.9 KiB
TOML
145 lines
6.9 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
|
|
# `forge.rs` encodes file content for its `repo_change_files` calls and
|
|
# decodes blobs it reads: forgejo's content and blob APIs carry 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
|
|
serde_norway = "0.9.42"
|
|
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.
|
|
#
|
|
# `subagent-term`: this daemon creates every agent's subagent stream, with the
|
|
# config the crate spells.
|
|
# `agent-term`: likewise every agent's terminal stream, plus the consumer it
|
|
# replays that stream through.
|
|
# `schema`: the review classifier try-out API serves the shapes the queue
|
|
# carries.
|
|
swarm-queue-client = { workspace = true, features = [
|
|
"kv",
|
|
"subagent-term",
|
|
"agent-term",
|
|
"schema",
|
|
] }
|
|
# `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
|
|
# The appservice calls `matrix_account::agent_token` mints agents' accounts
|
|
# with — shared with `swarm-matrix-ctl`, which pins the same device id.
|
|
swarm-matrix-client.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
|
|
# `agent_renewal.rs` reads an agent certificate's validity window.
|
|
x509-cert.workspace = true
|
|
|
|
# `test-util` for `#[tokio::test(start_paused = true)]`: `agent_renewal`'s
|
|
# tests wait out its five-minute bound on paused time.
|
|
[dev-dependencies]
|
|
tokio = { workspace = true, features = ["test-util"] }
|
|
# `ServiceExt::oneshot`, to drive a route through the real router in tests.
|
|
tower = { version = "0.5", features = ["util"] }
|
|
# A layer that captures `review_classifier::runs`'s log event in a test.
|
|
tracing-subscriber.workspace = true
|
|
|
|
[lints]
|
|
workspace = true
|