Watch
0
0
Fork
You've already forked hyperhive
0
hyperhive/hive-c0re/src/matrix.rs

1097 lines
44 KiB
Rust

//! Optional matrix-tuwunel wiring: the hive's `@hive-<hive>:` sender token,
//! taken from the swarm secret store, and the hive Space, chat room and
//! invites provisioned with it. No-op when no homeserver is configured, so
//! operators who haven't flipped `services.hyperhive.deploy.matrix.enable =
//! true` pay nothing.
//!
//! This module creates no accounts: `swarm-controller` mints every hive's
//! sender account and every agent's account with the swarm's appservice token.
use std::path::PathBuf;
use anyhow::{Context, Result};
/// Client-server API base this daemon provisions against, from
/// `HIVE_MATRIX_API_URL` (set by the hyperhive NixOS module from
/// `services.hyperhive.swarm.matrix.apiUrl`).
///
/// `None` means **this hive has no homeserver to provision against** and
/// every matrix path no-ops — see [`is_present`]. There is deliberately no
/// fallback: a loopback default is right only when the homeserver happens to
/// share this daemon's netns, and an address baked into the binary is one
/// that builds fine and then talks to the wrong machine. The nix module
/// defaults it to `https://` on the homeserver's gateway vhost, on every
/// hive whichever host runs tuwunel.
///
/// Also not an agent-facing address either way. An agent has its own netns;
/// agents are handed the gateway vhost via `HIVE_MATRIX_URL`, and get
/// nothing at all when the hive has no vhost to offer.
fn matrix_http() -> Option<&'static str> {
static BASE: std::sync::OnceLock<Option<String>> = std::sync::OnceLock::new();
BASE.get_or_init(|| std::env::var("HIVE_MATRIX_API_URL").ok())
.as_deref()
}
/// [`matrix_http`] for the call sites that propagate with `?`.
///
/// # Errors
/// When no homeserver is configured. Reaching one of these paths at all
/// means an [`is_present`] gate was skipped, so the message names that
/// rather than the missing variable.
fn matrix_base() -> Result<&'static str> {
matrix_http().context(
"matrix: no homeserver configured \
(services.hyperhive.swarm.matrix.apiUrl / HIVE_MATRIX_API_URL) — \
this path should have been gated on matrix::is_present()",
)
}
/// Matrix localpart this hive acts as. Not an agent; has no state dir.
///
/// **Per hive, derived from the hive's name** — `hive-<name>`, built by
/// `swarm_secret_client::matrix::hive_localpart`, which is the one place the
/// derivation lives. It used to be the bare constant `hive`, and a swarm runs
/// one homeserver: every hive on it logged in as the same `@hive:`, so the
/// homeserver could not attribute an action to a hive and revoking one hive's
/// standing revoked all of them.
///
/// `swarm-controller` creates this account with the swarm's appservice token
/// (`matrix_account::hive_sender`) and stores its token where
/// [`stored_sender_token`] reads it; hive-c0re never creates it.
///
/// An ordinary account, with no homeserver-admin standing: what it
/// provisions — the Space, the chat room, the invites — it provisions as
/// the creator of those rooms.
///
/// # Errors
/// When `HYPERHIVE_HIVE_NAME` is unset or empty. That is the same variable
/// [`stored_sender_token`] logs in with and `hive-c0re`'s meta flake asserts
/// for every hive, so its absence is a broken deployment rather than a
/// supported one — and there is no safe default to fall back to: the only one
/// available is the shared account this replaced.
pub fn hive_localpart() -> Result<String> {
let hive = std::env::var("HYPERHIVE_HIVE_NAME")
.ok()
.filter(|h| !h.is_empty())
.context(
"matrix: HYPERHIVE_HIVE_NAME is unset, so this hive has no matrix account of its own \
— the localpart is derived from the hive name and has no swarm-wide fallback",
)?;
Ok(swarm_secret_client::matrix::hive_localpart(&hive))
}
/// Display name of the hive Space. Plain text, no special characters, so
/// the Space stays rediscoverable by name (no room alias needed) even when
/// the persisted room-id file is lost — preventing duplicate spaces from
/// being created on the next sweep.
pub const HIVE_SPACE_NAME: &str = "hive";
/// Display name of the default "hive chat" room — the `m.space.child` of
/// the hive Space that every agent + the operator can join. Plain text so
/// it stays rediscoverable by name (mirrors [`HIVE_SPACE_NAME`]) when the
/// persisted room-id file is lost, preventing duplicate chat rooms.
pub const HIVE_CHAT_ROOM_NAME: &str = "hive-chat";
/// Topic for the default hive chat room.
const HIVE_CHAT_ROOM_TOPIC: &str =
"Hive-wide chat for all agents and the operator. Auto-provisioned by hive-c0re.";
/// Host path for the appservice sender account's matrix access token. Outside every
/// purgeable path — not deleted by `destroy --purge` on any agent.
#[must_use]
pub fn sender_token_path() -> PathBuf {
crate::paths::matrix_sender_token()
}
/// Host path where the hive Matrix Space room ID is persisted.
/// Outside every purgeable path — not deleted by `destroy --purge`.
#[must_use]
pub fn hive_space_room_id_path() -> PathBuf {
crate::paths::matrix_space_room_id()
}
/// Host path where the default hive chat room ID is persisted. Outside
/// every purgeable path — not deleted by `destroy --purge`.
#[must_use]
pub fn hive_chat_room_id_path() -> PathBuf {
crate::paths::matrix_chat_room_id()
}
/// Whether this hive has a homeserver to provision against.
///
/// **A configured API URL, not a local container**: whether the homeserver
/// runs on this host is a different question, and a remote homeserver is
/// provisioned through the same URL.
#[must_use]
pub fn is_present() -> bool {
matrix_http().is_some()
}
/// Bring the hive's `@hive-<hive>:` sender token at [`sender_token_path()`] in
/// line with the swarm secret store.
///
/// `swarm-controller` is the only minter: it creates the account with the
/// swarm's appservice token, keeps the stored token while it is live and
/// replaces it when it is not. The file follows the store, and is kept as it
/// is when the store has nothing or cannot be reached, so a store outage does
/// not take the hive's matrix provisioning down with it.
///
/// # Errors
/// When neither the store nor the file holds a token, or the file write fails.
pub async fn ensure_hive_user() -> Result<()> {
let path = sender_token_path();
let on_disk = std::fs::read_to_string(&path).ok();
let stored = stored_sender_token().await;
match sender_source(stored.as_deref(), on_disk.as_deref()) {
SenderSource::Keep => {
tracing::debug!("matrix: the sender token is already present");
Ok(())
}
SenderSource::Store(token) => persist_sender_token(&path, token),
SenderSource::Unavailable => anyhow::bail!(
"matrix: no sender token in the swarm store or at {}; swarm-controller \
mints it into the store",
path.display()
),
}
}
/// What [`ensure_hive_user`] does about the sender token this sweep.
#[derive(Debug, PartialEq, Eq)]
enum SenderSource<'a> {
/// The file already holds the token to use.
Keep,
/// Write the store's token to the file.
Store(&'a str),
/// No token in the store or the file.
Unavailable,
}
/// Decide [`ensure_hive_user`]'s step from the store's token and the file's
/// content, each `None` when absent. Blank counts as absent.
fn sender_source<'a>(stored: Option<&'a str>, on_disk: Option<&str>) -> SenderSource<'a> {
let present = |s: &&str| !s.trim().is_empty();
let stored = stored.map(str::trim).filter(present);
let on_disk = on_disk.map(str::trim).filter(present);
match (stored, on_disk) {
(Some(s), Some(d)) if s == d => SenderSource::Keep,
(Some(s), _) => SenderSource::Store(s),
(None, Some(_)) => SenderSource::Keep,
(None, None) => SenderSource::Unavailable,
}
}
/// Write the appservice sender account's access token to `path`, 0600, creating the
/// directory if it is not there. The file's mode is the only thing keeping an
/// unprivileged reader off the hive's matrix credential.
fn persist_sender_token(path: &std::path::Path, access_token: &str) -> Result<()> {
crate::secret_file::write_secret_0600(path, format!("{access_token}\n").as_bytes())
.with_context(|| format!("matrix: write the sender token to {}", path.display()))?;
tracing::info!(path = %path.display(), "matrix: provisioned the sender token");
Ok(())
}
/// Fetch the sender token `swarm-controller` published, under this hive's own
/// store identity.
///
/// The cert role is the hive's name, straight out of `HYPERHIVE_HIVE_NAME` —
/// the same role string `lifecycle::agent_identity` logs in with, and already in
/// this process's environment, so the store read costs no plumbing through
/// [`ensure_all`]. That name is also the path's own hive segment, which is
/// what makes this read reach **this** hive's token and 403 on any other's:
/// the grant behind it is the hive's own `swarm/hives/<name>/*` stanza.
///
/// `None`, never an error, for every way this can come up empty — no hive
/// name, no `BAO_*` identity, an unreachable store, nothing at the path. All
/// four mean the same thing to the caller ("keep the file"), and three of
/// them are the ordinary state of a swarm with no store token for this hive
/// yet, so raising would turn a supported deployment into a warning every
/// sweep.
///
/// 🩸 Logs the store **path** and never the value.
async fn stored_sender_token() -> Option<String> {
let hive = std::env::var("HYPERHIVE_HIVE_NAME")
.ok()
.filter(|h| !h.is_empty())?;
let path = match swarm_secret_client::matrix::sender_token_path(&hive) {
Ok(path) => path,
Err(e) => {
tracing::warn!(error = %e, "matrix: this hive's name does not form a store path");
return None;
}
};
let store = match swarm_secret_client::SecretStore::from_env(&hive).await {
Ok(store) => store,
Err(e) => {
tracing::debug!(error = %e, "matrix: no swarm secret store to read the sender token from");
return None;
}
};
match store
.read::<swarm_secret_client::matrix::Credential>(&path)
.await
{
Ok(credential) if !credential.value.trim().is_empty() => {
tracing::debug!(%path, "matrix: read the sender token from the swarm store");
Some(credential.value)
}
Ok(_) => {
tracing::warn!(%path, "matrix: the stored sender token is empty");
None
}
Err(e) => {
tracing::debug!(%path, error = %e, "matrix: no sender token in the store");
None
}
}
}
/// Discover the matrix `server_name` from the running homeserver via
/// `GET /_matrix/key/v2/server` (unauthenticated federation key endpoint).
/// The response JSON always includes `"server_name"` per the matrix spec.
pub async fn discover_server_name(client: &reqwest::Client) -> Result<String> {
let base = matrix_base()?;
let url = format!("{base}/_matrix/key/v2/server");
let resp = client
.get(&url)
.send()
.await
.context("matrix: GET /_matrix/key/v2/server")?;
let status = resp.status();
let body = resp
.json::<serde_json::Value>()
.await
.context("matrix: parse /_matrix/key/v2/server response")?;
if !status.is_success() {
anyhow::bail!("matrix: /_matrix/key/v2/server returned HTTP {status}, body: {body}");
}
body["server_name"]
.as_str()
.map(str::to_owned)
.with_context(|| {
format!("matrix: /_matrix/key/v2/server response missing server_name field: {body}")
})
}
/// Read the sender token from disk. Returns an error if it
/// is absent — callers should gate their homeserver calls on this.
pub fn read_sender_token() -> Result<String> {
let path = sender_token_path();
std::fs::read_to_string(&path)
.ok()
.map(|s| s.trim().to_owned())
.filter(|s| !s.is_empty())
.with_context(|| {
format!(
"the matrix sender token was not found at {} — \
ensure hive-c0re has started at least once with matrix enabled \
(it provisions the hive's @hive-<hive>: account on boot)",
path.display()
)
})
}
/// Persist the hive Space room id to [`hive_space_room_id_path()`] (0600).
fn persist_space_room_id(room_id: &str) -> Result<()> {
let path = hive_space_room_id_path();
crate::secret_file::write_secret_0600(&path, format!("{room_id}\n").as_bytes())
.with_context(|| format!("matrix: write space room_id to {}", path.display()))
}
/// Walk the admin account's joined rooms at `base` and return the first room
/// named `name` that is an `m.space` exactly when `want_space` is set (the
/// `m.room.create` `type`). `None` if the homeserver is unreachable or no
/// room matches.
async fn find_joined_room(
client: &reqwest::Client,
base: &str,
sender_token: &str,
want_space: bool,
name: &str,
) -> Option<String> {
let rooms = swarm_matrix_client::joined_rooms(client, base, sender_token)
.await
.ok()?;
for room_id in rooms {
// m.room.create `type` says whether this is a Space.
let is_space = keyless_state(client, base, sender_token, &room_id, "m.room.create")
.await
.is_some_and(|c| c["type"].as_str() == Some("m.space"));
if is_space != want_space {
continue;
}
// …and named `name` (m.room.name `name`).
let name_matches = keyless_state(client, base, sender_token, &room_id, "m.room.name")
.await
.is_some_and(|n| n["name"].as_str() == Some(name));
if name_matches {
return Some(room_id);
}
}
None
}
/// The content of a state event with an empty state key, or `None` when the
/// room has none or the read failed.
async fn keyless_state(
client: &reqwest::Client,
base: &str,
sender_token: &str,
room_id: &str,
event_type: &str,
) -> Option<serde_json::Value> {
swarm_matrix_client::room_state(client, base, sender_token, room_id, event_type, "")
.await
.ok()
.flatten()
}
/// Scan the admin account's joined rooms for the canonical hive Space: the
/// `m.space` whose name is [`HIVE_SPACE_NAME`]. Returns the first match
/// (deterministic per the homeserver's joined-rooms order) so a lost
/// room-id file recovers the existing space instead of spawning a
/// duplicate. `None` if the homeserver is unreachable or no match exists.
///
/// Name-based (not alias-based) rediscovery keeps the Space free of any
/// special-char room alias — the hardcoded plain name is the anchor.
async fn find_space_by_name(client: &reqwest::Client, sender_token: &str) -> Option<String> {
find_joined_room(client, matrix_http()?, sender_token, true, HIVE_SPACE_NAME).await
}
/// Create (or recover) the hive Matrix Space and persist its room ID to
/// [`hive_space_room_id_path()`]. The Space is a private `m.space` owned by
/// `@hive-<hive>:`, identified by its hardcoded name [`HIVE_SPACE_NAME`] (no alias).
///
/// Dedup strategy (single canonical space):
/// 1. If the room-id file exists, reuse it.
/// 2. Otherwise, rediscover by scanning the admin's joined rooms for the
/// `m.space` named [`HIVE_SPACE_NAME`] and adopt it (re-persisting the
/// file). This recovers the existing space after a state wipe instead
/// of creating a duplicate.
/// 3. Only if neither yields a room do we `createRoom`.
///
/// # Errors
///
/// Returns an error if the homeserver is unreachable, `createRoom` fails,
/// or the room-ID file cannot be written.
pub async fn ensure_hive_space(client: &reqwest::Client, sender_token: &str) -> Result<String> {
let base = matrix_base()?;
// 1. Stored room id wins (fast path).
if let Ok(existing) = std::fs::read_to_string(hive_space_room_id_path()) {
let trimmed = existing.trim().to_owned();
if !trimmed.is_empty() {
tracing::debug!(room_id = %trimmed, "matrix: hive space already provisioned");
return Ok(trimmed);
}
}
// 2. No stored id — rediscover the existing space by its hardcoded name
// before creating a new one (prevents duplicate spaces after a wipe).
if let Some(room_id) = find_space_by_name(client, sender_token).await {
persist_space_room_id(&room_id)?;
tracing::info!(%room_id, "matrix: recovered hive space by name");
return Ok(room_id);
}
// 3. Create the space (plain hardcoded name, no alias).
let body = serde_json::json!({
"name": HIVE_SPACE_NAME,
"creation_content": { "type": "m.space" },
"preset": "private_chat",
"visibility": "private",
});
let room_id = swarm_matrix_client::create_room(client, base, sender_token, &body)
.await
.context("matrix: create hive space")?;
persist_space_room_id(&room_id)?;
tracing::info!(%room_id, "matrix: created hive space");
Ok(room_id)
}
/// Persist the hive chat room id to [`hive_chat_room_id_path()`] (0600).
fn persist_chat_room_id(room_id: &str) -> Result<()> {
let path = hive_chat_room_id_path();
crate::secret_file::write_secret_0600(&path, format!("{room_id}\n").as_bytes())
.with_context(|| format!("matrix: write chat room_id to {}", path.display()))
}
/// Scan the admin account's joined rooms for the canonical hive chat room:
/// a non-space room named [`HIVE_CHAT_ROOM_NAME`]. Mirrors
/// [`find_space_by_name`] so a lost room-id file recovers the existing chat
/// room instead of spawning a duplicate. `None` if the homeserver is
/// unreachable or no match exists.
async fn find_chat_room_by_name(client: &reqwest::Client, sender_token: &str) -> Option<String> {
find_joined_room(
client,
matrix_http()?,
sender_token,
false,
HIVE_CHAT_ROOM_NAME,
)
.await
}
/// Whether the state event still has to be written.
///
/// `current` is the room's existing content for this `(type, state_key)`,
/// or `None` when it could not be read. **Unreadable means write**: the
/// re-apply exists so a missing link gets repaired, and one redundant
/// event is cheaper than a hierarchy that never reconverges.
///
/// Comparison is `serde_json::Value` equality, which compares objects as
/// maps — key order in the response does not matter.
fn state_needs_write(current: Option<&serde_json::Value>, desired: &serde_json::Value) -> bool {
current != Some(desired)
}
/// Read the room's current content for one state event. `None` on any
/// failure — absent state, transport error, a refusal, or an unparseable body
/// are all "we don't know", and [`state_needs_write`] turns that into a write.
///
/// A failure other than absent state is logged at `warn`: **a read that breaks
/// while the write still works** makes the guard degrade to writing every
/// time, and the sweep resumes waking the hive with nothing else to show for
/// it. An absent state event (404) is the expected first-setup case.
async fn current_room_state(
client: &reqwest::Client,
base: &str,
sender_token: &str,
room_id: &str,
event_type: &str,
state_key: &str,
) -> Option<serde_json::Value> {
match swarm_matrix_client::room_state(
client,
base,
sender_token,
room_id,
event_type,
state_key,
)
.await
{
Ok(content) => content,
Err(e) => {
tracing::warn!(
error = %format!("{e:#}"),
%room_id,
event_type,
"matrix: state read failed while writes still work — the \
skip-if-unchanged guard is off and every sweep will re-emit"
);
None
}
}
}
/// PUT a state event into `room_id` using the sender token, **skipping the
/// write when the room already carries identical content**.
///
/// The read is not an optimisation. A PUT of identical content is a no-op
/// on the room's *state*, and the homeserver still appends an event to the
/// *timeline* — so "idempotent" was true one level too high. Downstream,
/// an event is unread activity, which is a todo, which is a turn: a caller
/// re-applying a link on a periodic sweep wakes every agent in the room on
/// that sweep's cadence, forever. Measured at ~30 minutes per wake per
/// agent before this guard existed.
///
/// The self-healing property the re-apply exists for is unaffected: a
/// missing or divergent link still gets written.
async fn set_room_state(
client: &reqwest::Client,
sender_token: &str,
room_id: &str,
event_type: &str,
state_key: &str,
content: &serde_json::Value,
) -> Result<()> {
let base = matrix_base()?;
let current =
current_room_state(client, base, sender_token, room_id, event_type, state_key).await;
if !state_needs_write(current.as_ref(), content) {
tracing::debug!(
%room_id,
event_type,
"matrix: state already current, skipping PUT (no timeline event)"
);
return Ok(());
}
swarm_matrix_client::put_state(
client,
base,
sender_token,
room_id,
event_type,
state_key,
content,
)
.await
.context("matrix: set room state")
}
/// Create (or recover) the default hive chat room and wire it as a child of
/// the hive Space, persisting its room id to [`hive_chat_room_id_path()`].
///
/// The room is a normal room (not an `m.space`) named [`HIVE_CHAT_ROOM_NAME`]
/// with a `restricted` join rule allowing any member of the hive Space to
/// join — so the operator (who is in the Space) and every agent can chat
/// without needing an explicit invite. It's linked bidirectionally to the
/// Space: `m.space.child` on the Space points at the room, `m.space.parent`
/// on the room points back. Joining a Space does NOT auto-join its children
/// (Matrix semantics), so this gives clients a concrete room to surface +
/// join instead of an empty Space.
///
/// Dedup mirrors [`ensure_hive_space`]: persisted id wins, else rediscover
/// by name, else create. The space-child link is re-checked on every call
/// so a recovered room reconverges its hierarchy link — and written only
/// when it differs, see [`set_room_state`].
///
/// # Errors
///
/// Returns an error if the homeserver is unreachable, `createRoom` fails,
/// or the room-ID file cannot be written. A failure wiring the space-child
/// link is logged but not fatal (the room still exists + is joinable).
pub async fn ensure_hive_chat_room(
client: &reqwest::Client,
sender_token: &str,
space_room_id: &str,
server_name: &str,
) -> Result<String> {
let base = matrix_base()?;
// 1. Stored room id wins (fast path). 2. Rediscover by name before
// creating (prevents duplicates after a state wipe). 3. Create.
let room_id = if let Some(id) = std::fs::read_to_string(hive_chat_room_id_path())
.ok()
.map(|s| s.trim().to_owned())
.filter(|s| !s.is_empty())
{
tracing::debug!(room_id = %id, "matrix: hive chat room already provisioned");
id
} else if let Some(id) = find_chat_room_by_name(client, sender_token).await {
persist_chat_room_id(&id)?;
tracing::info!(room_id = %id, "matrix: recovered hive chat room by name");
id
} else {
// `initial_state` is applied after the preset-derived state, so the
// restricted join rule overrides private_chat's invite-only default.
let body = serde_json::json!({
"name": HIVE_CHAT_ROOM_NAME,
"topic": HIVE_CHAT_ROOM_TOPIC,
// Pin the room version explicitly: the `restricted` join rule
// below needs room version >= 8. tuwunel's default is currently
// higher, but pinning makes the dependency explicit so a future
// homeserver-default change can't silently invalidate the
// restricted rule (which would quietly fall back to invite-only
// and break the "operator joins from the Space" path).
"room_version": "10",
"preset": "private_chat",
"visibility": "private",
"initial_state": [
{
"type": "m.room.join_rules",
"state_key": "",
"content": {
"join_rule": "restricted",
"allow": [
{ "type": "m.room_membership", "room_id": space_room_id }
]
}
},
{
"type": "m.space.parent",
"state_key": space_room_id,
"content": { "via": [server_name], "canonical": true }
}
]
});
let id = swarm_matrix_client::create_room(client, base, sender_token, &body)
.await
.context("matrix: create hive chat room")?;
persist_chat_room_id(&id)?;
tracing::info!(room_id = %id, "matrix: created hive chat room");
id
};
// Wire the Space → room child link. Without an `m.space.child` carrying
// a `via`, the room won't surface in the Space hierarchy. `suggested`
// hints clients to surface it prominently.
let child_content = serde_json::json!({
"via": [server_name],
"suggested": true,
});
if let Err(e) = set_room_state(
client,
sender_token,
space_room_id,
"m.space.child",
&room_id,
&child_content,
)
.await
{
tracing::warn!(error = ?e, "matrix: set m.space.child on hive space failed");
}
Ok(room_id)
}
/// Invite `@{localpart}:{server_name}` to `room_id` using the admin
/// account. Idempotent — treats already-member responses as success.
async fn invite_to_room(
client: &reqwest::Client,
sender_token: &str,
room_id: &str,
localpart: &str,
server_name: &str,
) -> Result<()> {
let user_id = format!("@{localpart}:{server_name}");
invite_user_id(client, sender_token, room_id, &user_id).await
}
/// Fetch a user's current membership in a room via the sender token, or
/// `None` if there is no membership event (never invited) or the lookup
/// fails. Returns the raw membership string (`invite`, `join`, `leave`, …).
async fn room_membership(
client: &reqwest::Client,
sender_token: &str,
room_id: &str,
user_id: &str,
) -> Option<String> {
let base = matrix_http()?;
// A refused or failed read is "unknown": the caller falls through to the
// invite attempt.
let member = swarm_matrix_client::room_state(
client,
base,
sender_token,
room_id,
"m.room.member",
user_id,
)
.await
.ok()??;
member["membership"].as_str().map(ToOwned::to_owned)
}
/// Invite a fully-qualified Matrix user id (`@user:server`) to `room_id`
/// using the sender token. Idempotent: a user who is already a member or
/// already has a pending invite is left untouched (no fresh invite is sent,
/// so they are not re-notified). A refused invite is an error unless the
/// user turns out to be invited or joined anyway — see [`forbidden_invite`].
async fn invite_user_id(
client: &reqwest::Client,
sender_token: &str,
room_id: &str,
user_id: &str,
) -> Result<()> {
let base = matrix_base()?;
// Skip the invite entirely when the user is already invited or joined.
// Re-POSTing an invite to a pending member re-sends the invite event,
// which re-notifies the agent on every provisioning sweep.
if let Some(membership) = room_membership(client, sender_token, room_id, user_id).await
&& matches!(membership.as_str(), "invite" | "join")
{
tracing::debug!(%user_id, %room_id, %membership, "matrix: invite skipped (already a member/invited)");
return Ok(());
}
match swarm_matrix_client::invite(client, base, sender_token, room_id, user_id)
.await
.context("matrix: invite")?
{
swarm_matrix_client::Invited::Sent => {
tracing::debug!(%user_id, %room_id, "matrix: invited to room");
Ok(())
}
swarm_matrix_client::Invited::Forbidden => {
// The pre-check misses a member when its read failed or a
// concurrent invite landed after it, so a refusal re-reads the
// membership.
let membership = room_membership(client, sender_token, room_id, user_id).await;
forbidden_invite(membership.as_deref(), user_id, room_id)
}
}
}
/// Outcome of an invite the homeserver refused with 403. That is success only
/// when `membership`, re-read after the refusal, shows the user invited or
/// joined: `M_FORBIDDEN` covers both "already in the room" and real refusals
/// (banned target, sender lacks power), so the errcode can't tell them apart.
fn forbidden_invite(membership: Option<&str>, user_id: &str, room_id: &str) -> Result<()> {
if matches!(membership, Some("invite" | "join")) {
tracing::debug!(%user_id, %room_id, "matrix: invite refused, user already member/invited");
return Ok(());
}
anyhow::bail!(
"matrix: invite {user_id} to {room_id}: HTTP 403 and the user is not invited or joined"
)
}
/// Invite an arbitrary Matrix user to the hive Space (default) or an
/// explicit `room_id` / alias. `user` may be a fully-qualified id
/// (`@name:server`) or a bare localpart, which is qualified with the
/// homeserver's `server_name`. Returns the resolved room id the invite
/// targeted. Used by `hivectl matrix invite`.
///
/// # Errors
///
/// Returns an error if the sender token or `server_name` can't be read,
/// the target room can't be resolved (no `--room` and no persisted hive
/// space), or the invite POST fails for a reason other than the user
/// already being a member / invited.
pub async fn invite_user(
client: &reqwest::Client,
sender_token: &str,
user: &str,
room_override: Option<&str>,
server_name: &str,
) -> Result<String> {
// Qualify a bare localpart to a full user id on the hive homeserver.
let user_id = if user.starts_with('@') {
user.to_owned()
} else {
format!("@{user}:{server_name}")
};
// Resolve the room: explicit override (id or #alias) wins; otherwise
// the persisted hive Space.
let room_id = match room_override {
Some(r) if r.starts_with('#') => {
swarm_matrix_client::resolve_alias(client, matrix_base()?, sender_token, r).await?
}
Some(r) if r.starts_with('!') => r.to_owned(),
Some(r) => anyhow::bail!(
"matrix: --room {r:?} is neither a room id nor an alias; \
prefix with '!' for a room id (!abc:server) or '#' for an \
alias (#name:server)"
),
None => std::fs::read_to_string(hive_space_room_id_path())
.map(|s| s.trim().to_owned())
.context(
"matrix: no --room given and no persisted hive space \
(run the hive-c0re matrix sweep first)",
)?,
};
invite_user_id(client, sender_token, &room_id, &user_id).await?;
Ok(room_id)
}
/// Make sure the hive's own `@hive-<hive>:` account exists, then provision
/// the hive Space and chat room and invite every agent container to both.
/// Agents' own accounts are not created here: `swarm-controller` mints them
/// with the swarm's appservice token. Runs only as a `MatrixSweep` job node
/// (see `job_queue::templates::matrix_sweep`). No-op when the
/// hive-matrix container isn't running. Per-step failures are logged
/// but don't abort the sweep.
///
/// Returns `true` when every step of the sweep succeeded, `false` when at
/// least one step failed — the caller feeds this into a
/// [`crate::stats::sweep_health::SweepHealth`] to raise a debounced
/// dashboard banner on persistent failure (this sweep re-runs every 30
/// minutes, so a one-off blip self-heals without ever bannering).
pub async fn ensure_all() -> bool {
if !is_present() {
tracing::debug!("matrix: hive-matrix container absent, skipping user sweep");
return true;
}
let mut ok = true;
// One HTTP client for the whole sweep.
let client = match swarm_matrix_client::client() {
Ok(c) => c,
Err(e) => {
tracing::warn!(error = ?e, "matrix: build HTTP client failed; skipping sweep");
return false;
}
};
// The hive's `@hive-<hive>:` account first, because everything below provisions
// THROUGH it (the Space, the chat room and every invite are sent with
// its token) — as an ordinary user that created those rooms, not as a
// homeserver admin.
if let Err(e) = ensure_hive_user().await {
tracing::warn!(error = ?e, "matrix: ensure_hive_user failed");
ok = false;
}
let Ok(containers) = crate::lifecycle::list().await else {
tracing::warn!("matrix: nixos-container list failed; skipping user sweep");
return false;
};
let mut agent_names: Vec<String> = Vec::new();
for c in &containers {
let Some(name) = c.strip_prefix(crate::lifecycle::AGENT_PREFIX) else {
continue;
};
agent_names.push(name.to_owned());
}
if !provision_space(&client, &agent_names).await {
ok = false;
}
ok
}
/// Provision the hive Space + default chat room and invite every agent
/// (+ the admin account) to both. Split out of [`ensure_all`] purely to
/// keep that function under the `too_many_lines` threshold — this is the
/// tail half of the same sequential sweep and shares its aggregate-bool,
/// log-and-continue failure handling.
async fn provision_space(client: &reqwest::Client, agent_names: &[String]) -> bool {
let mut ok = true;
// server_name is needed to form full Matrix user IDs for invites.
let sender_token = match read_sender_token() {
Ok(t) => t,
Err(e) => {
tracing::warn!(error = ?e, "matrix: skipping hive space provisioning (no matrix sender token)");
return false;
}
};
// server_name first — the agent invites need it (fully-qualified user ids).
let server_name = match discover_server_name(client).await {
Ok(s) => s,
Err(e) => {
tracing::warn!(error = ?e, "matrix: discover_server_name failed; skipping space provisioning");
return false;
}
};
let room_id = match ensure_hive_space(client, &sender_token).await {
Ok(id) => id,
Err(e) => {
tracing::warn!(error = ?e, "matrix: ensure_hive_space failed");
return false;
}
};
// This hive's own account first, then all agents.
let localpart = match hive_localpart() {
Ok(l) => l,
Err(e) => {
tracing::warn!(error = ?e, "matrix: skipping hive space provisioning");
return false;
}
};
if let Err(e) = invite_to_room(client, &sender_token, &room_id, &localpart, &server_name).await
{
tracing::warn!(error = ?e, %localpart, "matrix: invite the hive account to the space failed");
ok = false;
}
for name in agent_names {
if let Err(e) = invite_to_room(client, &sender_token, &room_id, name, &server_name).await {
tracing::warn!(%name, error = ?e, "matrix: invite agent to space failed");
ok = false;
}
}
// Provision the default hive chat room as an m.space.child of the Space
// and invite `@hive-<hive>:` + every agent. Joining a Space alone surfaces no
// rooms to chat in (Matrix semantics — children aren't auto-joined), so
// without this the Space is empty. The restricted join rule additionally
// lets the operator (a Space member) join from the Space hierarchy.
match ensure_hive_chat_room(client, &sender_token, &room_id, &server_name).await {
Ok(chat_room_id) => {
if let Err(e) = invite_to_room(
client,
&sender_token,
&chat_room_id,
&localpart,
&server_name,
)
.await
{
tracing::warn!(error = ?e, %localpart, "matrix: invite the hive account to the chat room failed");
ok = false;
}
for name in agent_names {
if let Err(e) =
invite_to_room(client, &sender_token, &chat_room_id, name, &server_name).await
{
tracing::warn!(%name, error = ?e, "matrix: invite agent to chat room failed");
ok = false;
}
}
}
Err(e) => {
tracing::warn!(error = ?e, "matrix: ensure_hive_chat_room failed");
ok = false;
}
}
ok
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn with_no_file_the_store_token_is_taken() {
assert_eq!(sender_source(Some("tok"), None), SenderSource::Store("tok"));
}
#[test]
fn a_store_token_replaces_a_different_file_token() {
// The swarm re-minted a dead token; the file must follow it.
assert_eq!(
sender_source(Some("new\n"), Some("old\n")),
SenderSource::Store("new")
);
}
#[test]
fn a_file_matching_the_store_is_kept() {
// Trailing newline on disk is how `persist_sender_token` writes it.
assert_eq!(
sender_source(Some("tok"), Some("tok\n")),
SenderSource::Keep
);
}
#[test]
fn with_nothing_in_the_store_the_file_is_kept() {
assert_eq!(sender_source(None, Some("tok\n")), SenderSource::Keep);
}
#[test]
fn with_no_token_anywhere_nothing_is_available() {
assert_eq!(
sender_source(Some(""), Some(" \n")),
SenderSource::Unavailable
);
assert_eq!(sender_source(None, None), SenderSource::Unavailable);
}
/// The steady state. This is the whole point of the guard: the sweep
/// runs forever, and every write it makes is a wake for every agent
/// in the room.
#[test]
fn state_matching_the_room_is_not_rewritten() {
let desired = serde_json::json!({ "via": ["example.org"], "suggested": true });
let current = desired.clone();
assert!(!state_needs_write(Some(&current), &desired));
}
/// Key order in the homeserver's response must not force a write —
/// the guard leans on `serde_json::Value` comparing objects as maps,
/// and a byte- or order-sensitive comparison would silently degrade
/// to writing every time while still looking correct.
#[test]
fn state_matching_but_reordered_is_not_rewritten() {
let desired = serde_json::json!({ "via": ["example.org"], "suggested": true });
let current = serde_json::json!({ "suggested": true, "via": ["example.org"] });
assert!(!state_needs_write(Some(&current), &desired));
}
#[test]
fn diverged_state_is_rewritten() {
let desired = serde_json::json!({ "via": ["example.org"], "suggested": true });
let current = serde_json::json!({ "via": ["old.example.org"], "suggested": true });
assert!(state_needs_write(Some(&current), &desired));
}
/// Fail-open, and deliberately so: an unreadable current state must
/// write. The re-apply exists to repair a missing link, so "we don't
/// know" has to behave like "it's missing", not like "it's fine".
#[test]
fn unknown_state_is_written() {
let desired = serde_json::json!({ "via": ["example.org"], "suggested": true });
assert!(state_needs_write(None, &desired));
}
/// A banned target or a sender without power gets a 403; with no
/// membership behind it, the invite did not happen.
#[test]
fn a_refused_invite_without_membership_is_an_error() {
for membership in [None, Some("ban"), Some("leave")] {
let outcome = forbidden_invite(membership, "@a:x", "!r:x");
assert!(outcome.is_err(), "membership {membership:?} must not pass");
}
}
#[test]
fn a_refused_invite_for_a_member_is_success() {
for membership in ["invite", "join"] {
forbidden_invite(Some(membership), "@a:x", "!r:x")
.expect("already invited/joined is the goal state");
}
}
/// The homeserver's reply body reaches no error: `invite_user_id` is
/// driven against a stub whose 500 and 403 bodies carry a marker.
#[tokio::test]
async fn an_invite_refusal_error_does_not_quote_the_response_body() {
const BODY: &str = r#"{"errcode":"M_UNKNOWN","error":"free-form-marker"}"#;
for status in [500_u16, 403] {
let app = axum::Router::new().fallback(move || async move {
(
axum::http::StatusCode::from_u16(status).expect("a status"),
[(axum::http::header::CONTENT_TYPE, "application/json")],
BODY,
)
});
let listener = tokio::net::TcpListener::bind("127.0.0.1:0")
.await
.expect("bind");
let base = format!("http://{}", listener.local_addr().expect("local addr"));
let server = tokio::spawn(async move {
axum::serve(listener, app).await.expect("serve");
});
let client = swarm_matrix_client::client().expect("client");
let outcome = swarm_matrix_client::invite(&client, &base, "tok", "!r:x", "@a:x").await;
server.abort();
let message = match (status, outcome) {
(403, Ok(swarm_matrix_client::Invited::Forbidden)) => {
format!("{:#}", forbidden_invite(None, "@a:x", "!r:x").unwrap_err())
}
(500, Err(e)) => format!("{e:#}"),
(status, other) => panic!("HTTP {status}: unexpected {other:?}"),
};
assert!(message.contains(&status.to_string()), "{message}");
assert!(!message.contains("free-form-marker"), "{message}");
}
}
/// Serve a fake homeserver on loopback: `!space` is an `m.space` and
/// `!chat` a plain room, both named "shared"; `!decoy` is a plain room
/// named "other". Returns the base URL and the server task.
async fn fake_homeserver() -> (String, tokio::task::JoinHandle<()>) {
let app = axum::Router::new().fallback(|uri: axum::http::Uri| async move {
let path = uri.path();
let body = if path.ends_with("/joined_rooms") {
serde_json::json!({"joined_rooms": ["!decoy", "!space", "!chat"]})
} else if path.ends_with("/m.room.create/") {
if path.contains("space") {
serde_json::json!({"type": "m.space"})
} else {
serde_json::json!({})
}
} else if path.ends_with("/m.room.name/") {
let name = if path.contains("decoy") {
"other"
} else {
"shared"
};
serde_json::json!({"name": name})
} else {
serde_json::json!({})
};
axum::Json(body)
});
let listener = tokio::net::TcpListener::bind("127.0.0.1:0")
.await
.expect("bind");
let base = format!("http://{}", listener.local_addr().expect("local addr"));
let server = tokio::spawn(async move {
axum::serve(listener, app).await.expect("serve");
});
(base, server)
}
#[tokio::test]
async fn find_joined_room_matches_a_space_only_when_a_space_is_wanted() {
let (base, server) = fake_homeserver().await;
let client = reqwest::Client::new();
let want_space = find_joined_room(&client, &base, "tok", true, "shared").await;
let want_chat = find_joined_room(&client, &base, "tok", false, "shared").await;
let no_name = find_joined_room(&client, &base, "tok", true, "absent").await;
server.abort();
assert_eq!(want_space.as_deref(), Some("!space"));
assert_eq!(want_chat.as_deref(), Some("!chat"));
assert_eq!(no_name, None);
}
}