diff --git a/CLAUDE.md b/CLAUDE.md index 4d6990f9..fb26720c 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -147,6 +147,14 @@ hand-maintained per-file tree drifts out of sync with the code. unix socket the gateway's nginx proxies to — ⚠️ **the socket's directory is its access control**; the constraint that governs it is in the crate's README, and a unit test pins the path. +- **`swarm-secret-client/`** — client for the swarm's secret store, over + `vaultrs`. Owns the *agreements* both ends of the store must share rather + than the HTTP: the path a credential lives at, the field its bytes are in, + and the translation from this deployment's environment into a logged-in + client. ⚠️ Reads the **`BAO_`** env spellings explicitly — `vaultrs`'s own + defaults look for `VAULT_ADDR`/`VAULT_CLIENT_CERT`/`VAULT_CLIENT_KEY`, which + no unit in this tree sets, so falling through to them yields a client with + **no identity** and a TLS handshake failure that names no cause. - **`swarmctl/`** — swarm-level operator CLI, installed by the swarm-controller module on the host that runs the daemon. Runs as **root and acts directly** — no socket, no HTTP route, no priv helper; diff --git a/Cargo.lock b/Cargo.lock index 0d1fafcc..f5a37f9e 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -894,14 +894,38 @@ dependencies = [ "syn 2.0.119", ] +[[package]] +name = "darling" +version = "0.20.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fc7f46116c46ff9ab3eb1597a45688b6715c6e628b5c133e288e709a29bcb4ee" +dependencies = [ + "darling_core 0.20.11", + "darling_macro 0.20.11", +] + [[package]] name = "darling" version = "0.23.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "25ae13da2f202d56bd7f91c25fba009e7717a1e4a1cc98a76d844b65ae912e9d" dependencies = [ - "darling_core", - "darling_macro", + "darling_core 0.23.0", + "darling_macro 0.23.0", +] + +[[package]] +name = "darling_core" +version = "0.20.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0d00b9596d185e565c2207a0b01f8bd1a135483d02d9b7b0a54b11da8d53412e" +dependencies = [ + "fnv", + "ident_case", + "proc-macro2", + "quote", + "strsim", + "syn 2.0.119", ] [[package]] @@ -917,13 +941,24 @@ dependencies = [ "syn 2.0.119", ] +[[package]] +name = "darling_macro" +version = "0.20.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fc34b93ccb385b40dc71c6fceac4b2ad23662c7eeb248cf10d529b7e055b6ead" +dependencies = [ + "darling_core 0.20.11", + "quote", + "syn 2.0.119", +] + [[package]] name = "darling_macro" version = "0.23.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "ac3984ec7bd6cfa798e62b4a642426a5be0e68f9401cfc2a01e3fa9ea2fcdb8d" dependencies = [ - "darling_core", + "darling_core 0.23.0", "quote", "syn 2.0.119", ] @@ -1020,6 +1055,37 @@ dependencies = [ "syn 1.0.109", ] +[[package]] +name = "derive_builder" +version = "0.20.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "507dfb09ea8b7fa618fcf76e953f4f5e192547945816d5358edffe39f6f94947" +dependencies = [ + "derive_builder_macro", +] + +[[package]] +name = "derive_builder_core" +version = "0.20.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2d5bcf7b024d6835cfb3d473887cd966994907effbe9227e8c8219824d06c4e8" +dependencies = [ + "darling 0.20.11", + "proc-macro2", + "quote", + "syn 2.0.119", +] + +[[package]] +name = "derive_builder_macro" +version = "0.20.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ab63b0e2bf4d5928aff72e83a7dace85d7bba5fe12dcc3c5a572d78caffd3f3c" +dependencies = [ + "derive_builder_core", + "syn 2.0.119", +] + [[package]] name = "derive_more" version = "1.0.0" @@ -1701,6 +1767,7 @@ dependencies = [ "serde_json", "sha2 0.11.0", "swarm-queue-client", + "swarm-secret-client", "tempfile", "tokio", "tokio-stream", @@ -3823,7 +3890,7 @@ version = "2.2.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "783d787bf21813b285f13019adc49e11af501c658890c1e519f31f937c68b7e3" dependencies = [ - "darling", + "darling 0.23.0", "proc-macro2", "quote", "serde_json", @@ -4012,6 +4079,40 @@ dependencies = [ "semver", ] +[[package]] +name = "rustify" +version = "0.7.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4800ce4c1cc2fec12c559dae2ddbf0e17fcee7569b796e6d75898efef443368b" +dependencies = [ + "anyhow", + "async-trait", + "bytes", + "http", + "reqwest", + "rustify_derive", + "serde", + "serde_json", + "serde_urlencoded", + "thiserror 1.0.69", + "tracing", + "url", +] + +[[package]] +name = "rustify_derive" +version = "0.5.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "78ea7fda74240f7410d0198b603a8a2f662acc7d76b6667a49f9b162cd8d9b4f" +dependencies = [ + "proc-macro2", + "quote", + "regex", + "serde_urlencoded", + "syn 1.0.109", + "synstructure 0.12.6", +] + [[package]] name = "rustix" version = "1.1.4" @@ -4642,6 +4743,17 @@ dependencies = [ "tracing", ] +[[package]] +name = "swarm-secret-client" +version = "0.1.0" +dependencies = [ + "reqwest", + "serde", + "serde_json", + "thiserror 2.0.18", + "vaultrs", +] + [[package]] name = "swarmctl" version = "0.1.0" @@ -4696,6 +4808,18 @@ dependencies = [ "futures-core", ] +[[package]] +name = "synstructure" +version = "0.12.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f36bdaa60a83aca3921b5259d5400cbf5e90fc51931376a9bd4a0eb79aa7210f" +dependencies = [ + "proc-macro2", + "quote", + "syn 1.0.109", + "unicode-xid", +] + [[package]] name = "synstructure" version = "0.13.2" @@ -5337,6 +5461,25 @@ version = "0.1.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "ba73ea9cf16a25df0c8caa16c51acb937d5712a8429db78a3ee29d5dcacd3a65" +[[package]] +name = "vaultrs" +version = "0.8.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "30ffcc0e81025065dda612ec1e26a3d81bb16ef3062354873d17a35965d68522" +dependencies = [ + "async-trait", + "derive_builder", + "http", + "reqwest", + "rustify", + "rustify_derive", + "serde", + "serde_json", + "thiserror 2.0.18", + "tracing", + "url", +] + [[package]] name = "vcpkg" version = "0.2.15" @@ -5873,7 +6016,7 @@ dependencies = [ "proc-macro2", "quote", "syn 2.0.119", - "synstructure", + "synstructure 0.13.2", ] [[package]] @@ -5914,7 +6057,7 @@ dependencies = [ "proc-macro2", "quote", "syn 2.0.119", - "synstructure", + "synstructure 0.13.2", ] [[package]] diff --git a/Cargo.toml b/Cargo.toml index d1edfdd6..8ca89bd1 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -27,6 +27,7 @@ members = [ "swarm-controller", "swarm-nats-auth", "swarm-queue-client", + "swarm-secret-client", "swarmctl", ] @@ -90,7 +91,9 @@ hive-sock-client = { path = "hive-sock-client" } hive-types = { path = "hive-types" } swarm-authelia-bridge-sock = { path = "swarm-authelia-bridge-sock" } swarm-queue-client = { path = "swarm-queue-client" } +swarm-secret-client = { path = "swarm-secret-client" } thiserror = "2" +vaultrs = "0.8" tower-http = { version = "0.7", features = ["fs"] } uuid = { version = "1", features = ["v4"] } rmcp = { version = "2", default-features = false, features = [ diff --git a/hive-c0re/Cargo.toml b/hive-c0re/Cargo.toml index a1c9084f..895dc27f 100644 --- a/hive-c0re/Cargo.toml +++ b/hive-c0re/Cargo.toml @@ -54,6 +54,7 @@ serde_json.workspace = true # the swarm controller reads it with, and `kv` for the same reason: the # bucket's name and creation config belong to neither end of it alone. swarm-queue-client = { workspace = true, features = ["kv", "notices"] } +swarm-secret-client.workspace = true tokio.workspace = true tokio-stream.workspace = true tracing.workspace = true diff --git a/hive-c0re/src/swarm_status.rs b/hive-c0re/src/swarm_status.rs index aadbffac..b0c63070 100644 --- a/hive-c0re/src/swarm_status.rs +++ b/hive-c0re/src/swarm_status.rs @@ -198,7 +198,24 @@ async fn drain_swarm_events( return; } }; - tracing::info!(%subject, %deploy_subject, "swarm events: listening"); + // Also this hive's own, and for a second reason on top of the deploy + // subject's: the payload names an agent in *this* hive's state dir, so a + // notice for another hive is not merely noise, it is unactionable here. + let credential_subject = swarm_queue_client::credential_subject(&hive); + let mut credential_sub = match client.subscribe(credential_subject.clone()).await { + Ok(sub) => sub, + Err(e) => { + tracing::warn!( + subject = %credential_subject, error = %e, + "swarm events: subscribe failed; this hive will not hear credential notices" + ); + return; + } + }; + tracing::info!( + %subject, %deploy_subject, %credential_subject, + "swarm events: listening" + ); loop { tokio::select! { @@ -223,6 +240,13 @@ async fn drain_swarm_events( }; handle_deploy_request(&coord, &msg.payload).await; } + msg = credential_sub.next() => { + let Some(msg) = msg else { + tracing::warn!(subject = %credential_subject, "swarm events: credential subscription closed"); + return; + }; + handle_credential_notice(&hive, &msg.payload).await; + } _ = shutdown.changed() => { tracing::info!("swarm events: shutdown signal received"); return; @@ -236,6 +260,39 @@ async fn drain_swarm_events( /// /// A payload that will not decode is worth a `warn`: the controller and this /// end share one type, so a decode failure means they disagree about it. +/// Deliver the credential a [`swarm_queue_client::CredentialNotice`] names. +/// +/// `hive` doubles as the cert-auth role this hive logs into the store as: +/// `glue-bao-tls.nix` mints the client certificate with the hive name as its +/// CN, and a bao cert role matches on CN — so the two share a name by +/// construction rather than by convention. +/// +/// ⚠️ Nothing here can log the secret, and that is structural rather than +/// careful: the notice carries only names, and `deliver` writes the value +/// without returning it. +async fn handle_credential_notice(hive: &str, payload: &[u8]) { + let notice: swarm_queue_client::CredentialNotice = match serde_json::from_slice(payload) { + Ok(notice) => notice, + Err(e) => { + tracing::warn!(error = %e, "swarm events: undecodable credential notice"); + return; + } + }; + if let Err(e) = crate::workers::credential::deliver(¬ice, hive).await { + // Warn rather than retry: the controller republishes, and a hive that + // spun here would hold the queue task off its other two subjects. + tracing::warn!( + agent = %notice.agent, account = %notice.account, error = ?e, + "swarm events: credential delivery failed" + ); + return; + } + tracing::info!( + agent = %notice.agent, account = %notice.account, + "swarm events: credential delivered" + ); +} + async fn handle_deploy_request( coord: &std::sync::Arc, payload: &[u8], diff --git a/hive-c0re/src/workers/credential.rs b/hive-c0re/src/workers/credential.rs new file mode 100644 index 00000000..a6f11933 --- /dev/null +++ b/hive-c0re/src/workers/credential.rs @@ -0,0 +1,144 @@ +//! Delivering an agent's external-account credential from the swarm's secret +//! store into that agent's own state dir. +//! +//! The controller publishes a [`CredentialNotice`] naming an agent and an +//! account; this reads the value out of the store and writes it where the +//! agent's matrix daemon already watches for it. Nothing here activates +//! anything: `nix/agent-modules/matrix.nix` has a `systemd.paths` unit +//! globbing `/agents/*/state/matrix-token*` that re-fires the daemon when a +//! token appears, so arrival is the whole trigger. +//! +//! 🔑 The notice carries no secret — see [`swarm_queue_client::credential_subject`] +//! for why that is a requirement rather than a preference. The value is read +//! from the store under this hive's own identity. + +use std::os::unix::fs::PermissionsExt as _; +use std::path::PathBuf; + +use anyhow::{Context, Result}; +use hive_types::Ident; +use swarm_queue_client::CredentialNotice; +use swarm_secret_client::{SecretStore, path}; + +use crate::paths::agent_state_dir; + +/// The basename every matrix token must start with. +/// +/// `nix/agent-modules/matrix.nix` asserts the same prefix on every configured +/// `tokenFile`, because its path-watcher globs for it. A name written here +/// that did not match would land a file the daemon never notices — no error, +/// just a credential that silently never arrives. +const TOKEN_PREFIX: &str = "matrix-token"; + +/// Where `agent`'s credential for `account` is written. +/// +/// Takes an [`Ident`] rather than a `&str` because the name arrives off the +/// queue: `agent_state_dir` addresses a directory, and an unvalidated name +/// there is a path-traversal argument. The compiler refusing the `&str` is the +/// check — nothing here has to remember to perform one. +#[must_use] +pub fn token_path(agent: &Ident, account: &str) -> PathBuf { + agent_state_dir(agent).join(format!("{TOKEN_PREFIX}-{account}")) +} + +/// Read the credential `notice` names and write it into the agent's state dir. +/// +/// `cert_role` is the role on the store's `cert` auth mount whose policy scopes +/// what this hive may read. +/// +/// # Errors +/// The store refusing, being unreachable, or holding nothing at that path; a +/// name that is not a single path segment; or the write failing. +pub async fn deliver(notice: &CredentialNotice, cert_role: &str) -> Result<()> { + // Parsed before anything is read, so a malformed name costs a decode and + // not a round trip to the store. + let agent = Ident::parse(¬ice.agent) + .map_err(|e| anyhow::anyhow!("agent name {:?} off the queue: {e}", notice.agent))?; + let secret_path = path::matrix_account(¬ice.agent, ¬ice.account) + .context("building the credential's path in the store")?; + + let store = SecretStore::from_env(cert_role) + .await + .context("connecting to the swarm secret store")?; + let value = store + .read(&secret_path) + .await + .with_context(|| format!("reading {secret_path} from the store"))?; + + write_token(&token_path(&agent, ¬ice.account), &value) +} + +/// Write `value` to `dest` at `0600`, atomically. +/// +/// Atomic because the daemon's path-watcher fires on the file *appearing*: a +/// token written in place would be visible while still partial, and the daemon +/// would read a truncated credential exactly once, at the moment it is hardest +/// to reproduce. The temp name is dot-prefixed so it cannot match the +/// `matrix-token*` glob on its way past. +fn write_token(dest: &PathBuf, value: &str) -> Result<()> { + let dir = dest + .parent() + .context("a token path always has a parent state dir")?; + let name = dest + .file_name() + .context("a token path always has a file name")?; + let mut tmp = dir.join("."); + tmp.as_mut_os_string().push(name); + tmp.as_mut_os_string().push(".partial"); + + std::fs::write(&tmp, value).with_context(|| format!("writing {}", tmp.display()))?; + // Before the rename, so the file is never briefly readable by others under + // its final name. + std::fs::set_permissions(&tmp, std::fs::Permissions::from_mode(0o600)) + .with_context(|| format!("restricting {}", tmp.display()))?; + std::fs::rename(&tmp, dest).with_context(|| format!("publishing {}", dest.display())) +} + +#[cfg(test)] +mod tests { + use super::*; + + #[test] + fn the_written_name_matches_the_glob_the_daemon_watches() { + // The other end of this agreement is an assertion in + // `nix/agent-modules/matrix.nix` and a `systemd.paths` glob — neither + // reachable from a Rust test, so the prefix is pinned here. + let p = token_path(&Ident::parse("dmatrix").expect("a legal agent name"), "ccc"); + let name = p.file_name().unwrap().to_str().unwrap(); + assert!(name.starts_with("matrix-token"), "got {name}"); + assert_eq!(name, "matrix-token-ccc"); + } + + #[test] + fn the_partial_file_cannot_match_that_glob() { + // A temp name starting with `matrix-token` would be picked up + // mid-write; the dot prefix is what stops it. + let p = token_path(&Ident::parse("dmatrix").expect("a legal agent name"), "ccc"); + let name = p.file_name().unwrap().to_str().unwrap(); + let tmp = format!(".{name}.partial"); + assert!(!tmp.starts_with("matrix-token"), "got {tmp}"); + } + + #[test] + fn a_name_that_could_address_another_agent_is_refused() { + // `path::matrix_account` owns this rule; asserted here because this is + // the module that feeds it names off the wire. + assert!(path::matrix_account("../argus", "ccc").is_err()); + assert!(path::matrix_account("dmatrix", "../../etc/x").is_err()); + assert!(path::matrix_account("dmatrix", "ccc").is_ok()); + } + + #[test] + fn an_agent_name_off_the_queue_must_pass_the_ident_parser_too() { + // Two independent refusals, not one restated: `path::matrix_account` + // guards the address in the *store*, `Ident` guards the address on + // *disk*. `token_path` cannot even be called without the second, + // which is why it takes an `Ident` rather than validating internally. + for bad in ["../argus", "dmatrix/../argus", "Dmatrix", "d matrix", ""] { + assert!(Ident::parse(bad).is_err(), "{bad:?} must be refused"); + } + // The control: without it, a parser that rejected everything would + // satisfy the loop above. + assert!(Ident::parse("dmatrix").is_ok()); + } +} diff --git a/hive-c0re/src/workers/mod.rs b/hive-c0re/src/workers/mod.rs index da62baaa..bc6f232b 100644 --- a/hive-c0re/src/workers/mod.rs +++ b/hive-c0re/src/workers/mod.rs @@ -8,6 +8,7 @@ pub mod agent_sockets; pub mod auto_update; pub mod crash_watch; +pub mod credential; pub mod knowledge; pub mod mcp_sockets; pub mod scheduled_prompts_worker; diff --git a/nix/host-modules/hive-c0re/default.nix b/nix/host-modules/hive-c0re/default.nix index 87482bc9..ee8a9f1c 100644 --- a/nix/host-modules/hive-c0re/default.nix +++ b/nix/host-modules/hive-c0re/default.nix @@ -13,6 +13,13 @@ let cfg = config.services.hyperhive.c0re; + baoDeploy = config.services.hyperhive.deploy.bao; + # Held in one place because the LoadCredential below and the `BAO_*` + # environment in ./environment.nix have to agree on when they exist: a + # credential with no reader is dead weight, and an environment naming a + # credential nobody loaded is a daemon that fails at the TLS handshake. + baoClientIdentity = baoDeploy.clientCertFile != null && baoDeploy.clientKeyFile != null; + caTrust = import ../lib/hive-ca-trust.nix { inherit lib; tlsCfg = config.services.hyperhive.deploy.hive-controller.tls; @@ -309,7 +316,23 @@ in # delivers into a container, across a filesystem boundary.) lib.optional ( config.services.hyperhive.swarm.statusPublish.clientSecretFile != null - ) "swarm-status-client.secret:${config.services.hyperhive.swarm.statusPublish.clientSecretFile}"; + ) "swarm-status-client.secret:${config.services.hyperhive.swarm.statusPublish.clientSecretFile}" + # The secret store's client identity, on the same reasoning one + # paragraph up — with a sharper edge: ./glue-bao-tls.nix mints the + # key `0600` inside a `0700` directory, so hive-core cannot read it + # at all. Loading it as a credential is what makes the store + # reachable from an unprivileged daemon without widening either. + # The gate is the identity, never `deploy.bao.enable`: a hive that + # reads a store on another machine holds one of these and runs no + # store. ./glue-matrix-bao-token.nix gates its own reader the same + # way. + ++ lib.optionals baoClientIdentity [ + "bao-client.pem:${baoDeploy.clientCertFile}" + "bao-client-key.pem:${baoDeploy.clientKeyFile}" + ] + ++ lib.optional ( + baoClientIdentity && baoDeploy.serverCaFile != null + ) "bao-ca.pem:${baoDeploy.serverCaFile}"; # Sandboxing. hive-c0re is unprivileged (runs as hive-core, never # setuid), makes HTTP requests to forge/matrix/Anthropic (keeps INET), # and delegates all privileged ops to hive-priv via a Unix socket. diff --git a/nix/host-modules/hive-c0re/environment.nix b/nix/host-modules/hive-c0re/environment.nix index 3345bd06..8539e6b4 100644 --- a/nix/host-modules/hive-c0re/environment.nix +++ b/nix/host-modules/hive-c0re/environment.nix @@ -9,6 +9,13 @@ }: let cfg = config.services.hyperhive.c0re; + baoDeploy = config.services.hyperhive.deploy.bao; + baoCfg = config.services.hyperhive.swarm.bao; + # The same test ../glue-matrix-bao-token.nix applies, and for the same + # reason: a reader is defined by holding a certificate the store accepts, + # not by sharing a host with the store. Deriving this from + # `deploy.bao.enable` would be the co-location assumption itself. + haveBaoClientIdentity = baoDeploy.clientCertFile != null && baoDeploy.clientKeyFile != null; in { # nix (the prebuild `nix build`, flake-check, and meta eval) writes @@ -263,3 +270,23 @@ in # ./default.nix. The daemon reads a path, never a value. HIVE_C0RE_OIDC_CLIENT_SECRET_FILE = "%d/swarm-status-client.secret"; } +// + # Where the swarm's secret store is, and the identity this hive presents to + # it (hive-c0re::workers::credential). `swarm_secret_client` reads these + # spellings explicitly rather than vaultrs's `VAULT_*` defaults — falling + # through to those would build a client with no identity and fail at the TLS + # handshake, naming neither. + lib.optionalAttrs haveBaoClientIdentity { + BAO_ADDR = "https://${baoCfg.domain}:${toString baoCfg.port}"; + # `%d`, not the paths themselves: the key is `0600` root-owned and this + # daemon runs as hive-core, so it never gets read access to the original. + # See the LoadCredential in ./default.nix. + BAO_CLIENT_CERT = "%d/bao-client.pem"; + BAO_CLIENT_KEY = "%d/bao-client-key.pem"; + } +// lib.optionalAttrs (haveBaoClientIdentity && baoDeploy.serverCaFile != null) { + # Absent means the system trust store — right for a deployment with a real + # CA, wrong for the self-signed one ../glue-bao-tls.nix mints, which is why + # that file names this path rather than leaving it to a default. + BAO_CACERT = "%d/bao-ca.pem"; +} diff --git a/nix/host-modules/swarm-bao.nix b/nix/host-modules/swarm-bao.nix index 6ba6e96f..f1031f53 100644 --- a/nix/host-modules/swarm-bao.nix +++ b/nix/host-modules/swarm-bao.nix @@ -245,10 +245,17 @@ in { # One service, two namespaces, and the split decides who may set what. # - # `deploy.bao.*` is what the host RUNNING the store decides: whether to run - # it (`enable`, declared in ./deploy.nix with its siblings), which build, - # how the root key is sealed, what it listens on. None of it means anything - # on a host that only reads secrets. + # `deploy.bao.*` is mostly what the host RUNNING the store decides: whether + # to run it (`enable`, declared in ./deploy.nix with its siblings), which + # build, how the root key is sealed, what it listens on. + # + # ⚠️ Except the reader's own identity. `clientCertFile`, `clientKeyFile` and + # `serverCaFile` live here too, and they are set by whoever authenticates TO + # the store — which includes a host that runs none of it. A reader is defined + # by holding a certificate the store accepts, never by sharing a host with + # one; ./glue-matrix-bao-token.nix gates on exactly that and not on `enable`. + # Reading this block as store-runner-only is what makes an off-host reader + # look inexpressible when it is already supported. # # `swarm.bao.*` below is what every host in the swarm has to agree on — the # name the store answers to, its port, its container. A host that is purely @@ -378,9 +385,7 @@ in Certificate a **reader on this machine** presents to the store. The counterpart to {option}`services.hyperhive.deploy.bao.clientCaFile`, - which is the store's side of the same handshake. Only the store's side - was declarable, so a hive that did not run the store had no way to be - pointed at a certificate even when one was placed for it. + which is the store's side of the same handshake. On a hive that runs the store, a glue module supplies the leaf it minted, as a `mkDefault`. Everywhere else this is the credential an operator diff --git a/nix/module-eval.nix b/nix/module-eval.nix index 3ca034d1..49678d98 100644 --- a/nix/module-eval.nix +++ b/nix/module-eval.nix @@ -483,6 +483,58 @@ let in s ? swarm-bao-matrix-token && s.swarm-bao-matrix-token.requires == [ "swarm-bao-pki.service" ]; } + { + # hive-c0re runs as hive-core and the client key is `0600` root-owned + # inside a `0700` directory, so the identity reaches the daemon as a + # systemd credential and the environment names `%d` rather than the + # file. Both halves are asserted together because either alone is a + # daemon that fails at the TLS handshake, naming neither. + name = "a reader hands hive-c0re a store identity the daemon cannot open itself"; + ok = + let + s = baoRemoteReader.systemd.services; + in + s ? hive-c0re + && (s.hive-c0re.environment.BAO_CLIENT_CERT or null) == "%d/bao-client.pem" + && (s.hive-c0re.environment.BAO_CLIENT_KEY or null) == "%d/bao-client-key.pem" + && builtins.elem "bao-client.pem:/etc/pki/bao-client.pem" s.hive-c0re.serviceConfig.LoadCredential + && builtins.elem "bao-client-key.pem:/etc/pki/bao-client-key.pem" s.hive-c0re.serviceConfig.LoadCredential; + } + { + # Absence arm for the case above. A hive with no client identity gets no + # store environment at all — the daemon reports a queue it cannot serve + # rather than a handshake it cannot explain. + name = "a hive with no client identity gives hive-c0re no store environment"; + ok = + let + s = matrixNoBaoIdentity.systemd.services; + in + s ? hive-c0re + && !(s.hive-c0re.environment ? BAO_ADDR) + && !(lib.any (c: lib.hasPrefix "bao-" c) s.hive-c0re.serviceConfig.LoadCredential); + } + { + # The CA is its own arm: absent means the system trust store, which is + # right for a deployment with a real CA and wrong for a self-signed one. + name = "a reader that names no store CA falls through to the system trust store"; + ok = + let + s = baoRemoteReader.systemd.services; + in + s ? hive-c0re && !(s.hive-c0re.environment ? BAO_CACERT); + } + { + # Presence control for the arm above: the CA is conditional, not gone. + # Co-located, ./host-modules/glue-bao-tls.nix mints one and names it. + name = "a reader beside a self-signed store is given that store's CA"; + ok = + let + s = baoWithMatrix.systemd.services; + in + s ? hive-c0re + && (s.hive-c0re.environment.BAO_CACERT or null) == "%d/bao-ca.pem" + && lib.any (c: lib.hasPrefix "bao-ca.pem:" c) s.hive-c0re.serviceConfig.LoadCredential; + } { # The name a reader dials has to resolve where the store runs; a # multi-host swarm resolves it upstream instead. diff --git a/swarm-nats-auth/src/policy.rs b/swarm-nats-auth/src/policy.rs index 4a0b5520..2383f2e0 100644 --- a/swarm-nats-auth/src/policy.rs +++ b/swarm-nats-auth/src/policy.rs @@ -352,6 +352,17 @@ impl Policy { // admission). Same failure mode as the knowledge event above: a // refused publish reaches the client as a timeout. swarm_queue_client::DEPLOY_SUBJECT_WILDCARD.to_owned(), + // The credential notices: same per-hive family and same wildcard + // reasoning as the deploy events, and the same timeout-not-error + // failure if this line is missing. + // + // 🔑 Worth being explicit that this grant is not a confidentiality + // boundary, because it looks like one. `sub` is unrestricted, so + // any hive could subscribe to another's notices — which is exactly + // why the payload names a credential and never carries one. What + // scopes the secret is the store's own policy at read time, under + // the reading hive's certificate. + swarm_queue_client::CREDENTIAL_SUBJECT_WILDCARD.to_owned(), // The wanted-state buckets — one per hive, all created and written // by this single client. // @@ -581,6 +592,36 @@ mod tests { ); } + #[test] + fn a_reader_may_publish_a_credential_notice_to_any_hive() { + let p = policy().permissions("swarm-controller").expect("a reader"); + assert!( + p.publish + .contains(&swarm_queue_client::CREDENTIAL_SUBJECT_WILDCARD.to_owned()), + "without this grant the controller's publish is refused, and a \ + refusal arrives as a timeout — a hive that silently never receives \ + a credential, with nothing in either log saying why" + ); + } + + #[test] + fn a_hive_may_not_publish_a_credential_notice() { + // A forged notice cannot leak a secret — the payload carries none — but + // it can make a hive fetch and overwrite an agent's token file with + // whatever the store holds for a name the forger chose. + let p = policy() + .permissions("hive-alpha") + .expect("a hive is admitted"); + assert!( + !p.publish + .iter() + .any(|s| s == swarm_queue_client::CREDENTIAL_SUBJECT_WILDCARD + || s == &swarm_queue_client::credential_subject("hive-alpha")), + "a hive must not publish credential notices, its own included: {:?}", + p.publish + ); + } + #[test] fn a_hive_may_not_publish_a_deploy_event_to_anyone_including_itself() { // Same arm as the knowledge event's, and it matters more here: a forged diff --git a/swarm-queue-client/src/lib.rs b/swarm-queue-client/src/lib.rs index f1098326..809304ff 100644 --- a/swarm-queue-client/src/lib.rs +++ b/swarm-queue-client/src/lib.rs @@ -212,6 +212,42 @@ pub const DEPLOY_SUBJECT_WILDCARD: &str = "$SWARM.deploy.*"; /// cannot drift into naming different families. const DEPLOY_SUBJECT_PREFIX: &str = "$SWARM.deploy"; +/// The subject the controller publishes on to tell `hive` that a credential +/// for one of its agents is waiting in the secret store. Same per-hive family +/// as [`deploy_subject`], here for the same three-crate reason. +/// +/// 🔑 **The message NAMES a credential and never carries one**, and the note +/// on [`deploy_subject`] is why: the family split buys quiet, not +/// confidentiality — the auth-callout responder scopes `pub` and leaves `sub` +/// unrestricted, so any hive that wanted another's messages could subscribe to +/// them. A secret in this payload would be readable swarm-wide. The hive reads +/// the value from the store under its own identity instead, where the store's +/// policy is the thing that actually scopes it. +#[must_use] +pub fn credential_subject(hive: &str) -> String { + format!("{CREDENTIAL_SUBJECT_PREFIX}.{hive}") +} + +/// The publish grant covering every [`credential_subject`] — a wildcard for +/// the same no-roster reason as [`DEPLOY_SUBJECT_WILDCARD`]. +pub const CREDENTIAL_SUBJECT_WILDCARD: &str = "$SWARM.credential.*"; + +/// Shared by [`credential_subject`] and [`CREDENTIAL_SUBJECT_WILDCARD`] so the +/// two cannot drift into naming different families. +const CREDENTIAL_SUBJECT_PREFIX: &str = "$SWARM.credential"; + +/// What a [`credential_subject`] message says: which agent's credential +/// changed, and which account it belongs to. Deliberately the whole payload — +/// anything more would be either derivable by the reader or a secret that +/// must not be on the wire. +#[derive(Debug, Clone, PartialEq, Eq, serde::Serialize, serde::Deserialize)] +pub struct CredentialNotice { + /// The agent whose state dir receives the credential. + pub agent: String, + /// The external account the credential authenticates as. + pub account: String, +} + /// What a [`deploy_subject`] message carries. /// /// Only the agent: the subject already names the hive, and repeating it here diff --git a/swarm-secret-client/Cargo.toml b/swarm-secret-client/Cargo.toml new file mode 100644 index 00000000..bb59a56e --- /dev/null +++ b/swarm-secret-client/Cargo.toml @@ -0,0 +1,19 @@ +[package] +name = "swarm-secret-client" +version.workspace = true +edition.workspace = true + +[dependencies] +# `Identity` is re-exported by vaultrs, but the identity is built here (from +# the `BAO_*` files) rather than by its env defaults, so the dependency is +# direct rather than incidental. +reqwest.workspace = true +serde.workspace = true +thiserror.workspace = true +vaultrs.workspace = true + +[dev-dependencies] +serde_json.workspace = true + +[lints] +workspace = true diff --git a/swarm-secret-client/README.md b/swarm-secret-client/README.md new file mode 100644 index 00000000..273865aa --- /dev/null +++ b/swarm-secret-client/README.md @@ -0,0 +1,77 @@ +# swarm-secret-client + +Reading and writing a swarm credential in the secret store, over `vaultrs`. +The HTTP is that crate's job. What this one owns is the **agreements** both +ends of the store have to state identically: where a credential lives, which +field its bytes are in, and how this deployment's environment becomes a +logged-in client. + +The surrounding picture — which secret is minted where, and why delivery is a +copy rather than a bind mount — is [`docs/swarm/secrets.md`](../docs/swarm/secrets.md). + +## Why a crate and not a module per binary + +The store has two Rust ends and they are peers: the swarm controller writes a +credential, a hive reads it. Neither is senior to the other, so a path +formatted at each call site is an agreement with no owner — it holds right up +until one side is edited alone, and then it fails as a missing key rather than +as a mismatch. + +The third end is what settles it. `nix/host-modules/glue-matrix-bao-token.nix` +reads the store with `bao kv get -field=value`. That reader is a shell line in +a nix module: it cannot be renamed by the same refactor as a Rust struct, and +no Rust test reaches it. So the field name is pinned by a test against the +serialised literal rather than left to the struct definition. + +## The identity is a certificate, and the role is the hive's name + +Authentication is the store's `cert` auth method. +`nix/host-modules/glue-bao-tls.nix` mints the client certificate with its CN +set to the hive's name, because a cert-auth role matches on the CN. So +`cert_role` is not a free choice for the caller: a hive passes its own name, +and the policy attached to that role is what scopes what it may read. + +The listener's `tls_require_and_verify_client_cert` is a different thing and +not a substitute. It decides who may open a connection; it says nothing about +who the connection belongs to, and a store with the option set and no `cert` +mount configured refuses every login made here. That refusal is what +`Error::Vault` out of `connect` means. + +## Configuration + +`Settings::from_env` reads `BAO_ADDR`, `BAO_CLIENT_CERT`, `BAO_CLIENT_KEY`, +and the optional `BAO_CACERT`. + +**The `BAO_` spellings are read explicitly rather than left to `vaultrs`.** Its +own defaults look for `VAULT_ADDR` / `VAULT_CLIENT_CERT` / `VAULT_CLIENT_KEY`, +which no unit in this tree sets. Falling through to them builds a client with +**no identity at all**, and that surfaces as a TLS handshake failure — a place +that names neither the variable nor the reason. + +**Empty is as absent as unset.** systemd renders an unset nix option as +`Environment=BAO_CACERT=`, so empty is the shape a missing value arrives in. + +**The certificate and key are paths, not values**, and are read at connect +time — same rule as every other credential in this tree, for the same reason: +a value in a nix expression is rendered into the world-readable store. + +Reading the environment is separate from connecting (`Settings::from_lookup`) +because every one of those failures is a misconfiguration an operator has to +read an error about, and none of them needs a reachable store to happen. + +## Names that arrive from elsewhere + +`path::matrix_account` is fallible, which for a string formatter needs saying: +its segments are an agent name from the topology and an account name from that +agent's own config. A `/` turns one agent's segment into another agent's +directory and `..` walks out of the prefix entirely, so the charset it accepts +is deliberately narrower than what the store would. + +## What this crate does not do + +It has no opinion on **what** a caller may read. That is the policy attached to +the cert role, and it lives in the store. + +It holds the token minted at login and renews nothing. A handle is built per +credential, so the login is the cheap part of a rare operation — a caller that +wanted to keep one alive across a token's lifetime would need more than this. diff --git a/swarm-secret-client/src/client.rs b/swarm-secret-client/src/client.rs new file mode 100644 index 00000000..d2f00a14 --- /dev/null +++ b/swarm-secret-client/src/client.rs @@ -0,0 +1,248 @@ +//! A logged-in handle on the store, built from this deployment's environment. + +use serde::{Deserialize, Serialize}; +use vaultrs::client::{Client, VaultClient, VaultClientSettingsBuilder}; + +use crate::{Error, path::MOUNT}; + +/// The store's address. +pub const ENV_ADDR: &str = "BAO_ADDR"; +/// PEM client certificate presented to the store's listener. +pub const ENV_CLIENT_CERT: &str = "BAO_CLIENT_CERT"; +/// PEM private key for [`ENV_CLIENT_CERT`]. +pub const ENV_CLIENT_KEY: &str = "BAO_CLIENT_KEY"; +/// CA bundle the store's own certificate is verified against. Optional: +/// absent means the system trust store, which is what a deployment with a +/// real CA wants and what a self-signed one must not be left with. +pub const ENV_CACERT: &str = "BAO_CACERT"; + +/// The auth mount a cert login goes through, unless a caller says otherwise. +pub const DEFAULT_CERT_MOUNT: &str = "cert"; + +#[derive(Serialize, Deserialize)] +struct Credential { + /// `glue-matrix-bao-token.nix` reads the store with + /// `bao kv get -field=value`, so this name is load-bearing for a reader + /// this crate does not control. Renaming it silently breaks that unit. + value: String, +} + +/// Where the store is and which identity we present to it. +/// +/// Separate from the connect so the environment can be checked without one: +/// every arm below is a misconfiguration an operator has to read an error +/// about, and none of them needs a reachable store to happen. +#[derive(Debug, PartialEq, Eq)] +pub struct Settings { + address: String, + cert_path: String, + key_path: String, + ca_path: Option, +} + +impl Settings { + /// Read the `BAO_*` variables from the process environment. + /// + /// # Errors + /// [`Error::MissingEnv`] naming the first variable that is unset or empty. + pub fn from_env() -> Result { + Self::from_lookup(|k| std::env::var(k).ok()) + } + + /// [`Settings::from_env`] against an arbitrary lookup. + /// + /// [`vaultrs`]'s own defaults are deliberately not used: it looks for + /// `VAULT_ADDR` / `VAULT_CLIENT_CERT` / `VAULT_CLIENT_KEY`, and every unit + /// in this tree sets the `BAO_` spellings. Falling through to those + /// defaults yields a client with **no identity**, which fails at the TLS + /// handshake rather than anywhere that names the cause. + /// + /// # Errors + /// [`Error::MissingEnv`] naming the first variable that is unset or empty. + pub fn from_lookup(get: impl Fn(&str) -> Option) -> Result { + let required = |var: &'static str| -> Result { + get(var) + .filter(|v| !v.is_empty()) + .ok_or(Error::MissingEnv(var)) + }; + Ok(Self { + address: required(ENV_ADDR)?, + cert_path: required(ENV_CLIENT_CERT)?, + key_path: required(ENV_CLIENT_KEY)?, + ca_path: get(ENV_CACERT).filter(|v| !v.is_empty()), + }) + } +} + +/// A client that has already exchanged its certificate for a token. +pub struct SecretStore { + inner: VaultClient, +} + +fn read_file(var: &'static str, path: &str) -> Result, Error> { + std::fs::read(path).map_err(|source| Error::Identity { + var, + path: path.to_owned(), + source, + }) +} + +impl SecretStore { + /// Connect using the `BAO_*` environment and log in with the certificate + /// auth method, returning a handle that already holds a token. + /// + /// `cert_role` is the role configured on the store's `cert` mount; it + /// selects which policy the returned token carries. + /// + /// # Errors + /// As [`SecretStore::connect`], plus [`Error::MissingEnv`]. + pub async fn from_env(cert_role: &str) -> Result { + Self::connect(&Settings::from_env()?, cert_role, DEFAULT_CERT_MOUNT).await + } + + /// Present `settings`' identity to the store and log in at `cert_mount`. + /// + /// # Errors + /// [`Error::Identity`] when a named file cannot be read, [`Error::Tls`] + /// when the cert/key pair does not form a usable identity, + /// [`Error::Settings`] when the address will not parse, and + /// [`Error::Vault`] when the store refuses the login — which is what an + /// unconfigured `cert` mount looks like from here. + pub async fn connect( + settings: &Settings, + cert_role: &str, + cert_mount: &str, + ) -> Result { + // One PEM blob holding both, which is the shape `Identity::from_pem` + // wants; the two stay separate on disk because the key is the half + // that gets `0600`. + let mut pem = read_file(ENV_CLIENT_CERT, &settings.cert_path)?; + pem.push(b'\n'); + pem.extend_from_slice(&read_file(ENV_CLIENT_KEY, &settings.key_path)?); + let identity = reqwest::Identity::from_pem(&pem).map_err(Error::Tls)?; + + let mut builder = VaultClientSettingsBuilder::default(); + builder + .address(settings.address.clone()) + .identity(Some(identity)); + if let Some(ca) = &settings.ca_path { + builder.ca_certs(vec![ca.clone()]); + } + let built = builder + .build() + .map_err(|e| Error::Settings(e.to_string()))?; + + let mut inner = VaultClient::new(built)?; + let auth = vaultrs::auth::cert::login(&inner, cert_mount, cert_role).await?; + inner.set_token(&auth.client_token); + Ok(Self { inner }) + } + + /// Read the credential stored at `path`. + /// + /// # Errors + /// [`Error::Vault`] when the path does not exist, the token's policy does + /// not cover it, or the stored object has no `value` field. + pub async fn read(&self, path: &str) -> Result { + let c: Credential = vaultrs::kv2::read(&self.inner, MOUNT, path).await?; + Ok(c.value) + } + + /// Write `value` as the credential at `path`, creating a new version. + /// + /// # Errors + /// [`Error::Vault`] when the token's policy does not cover the path. + pub async fn write(&self, path: &str, value: &str) -> Result<(), Error> { + let body = Credential { + value: value.to_owned(), + }; + vaultrs::kv2::set(&self.inner, MOUNT, path, &body).await?; + Ok(()) + } +} + +#[cfg(test)] +mod tests { + use super::*; + + /// A lookup standing in for a fully-configured unit's environment. + fn full(k: &str) -> Option { + match k { + ENV_ADDR => Some("https://store.invalid:8200".to_owned()), + ENV_CLIENT_CERT => Some("/run/c.pem".to_owned()), + ENV_CLIENT_KEY => Some("/run/k.pem".to_owned()), + _ => None, + } + } + + #[test] + fn a_complete_environment_is_accepted() { + // The control: without this, every assertion below could be passing + // because `from_lookup` rejects everything. + let s = Settings::from_lookup(full).expect("every required variable is set"); + assert_eq!(s.address, "https://store.invalid:8200"); + assert_eq!(s.ca_path, None, "an absent CA is the system trust store"); + } + + #[test] + fn each_required_variable_is_named_when_it_is_the_missing_one() { + for var in [ENV_ADDR, ENV_CLIENT_CERT, ENV_CLIENT_KEY] { + let e = Settings::from_lookup(|k| if k == var { None } else { full(k) }) + .expect_err("one required variable is absent"); + assert!( + matches!(e, Error::MissingEnv(v) if v == var), + "dropping {var} should name {var}, got {e:?}" + ); + } + } + + #[test] + fn an_empty_variable_is_as_absent_as_an_unset_one() { + // systemd writes `Environment=BAO_CACERT=` for an unset nix option, so + // empty is the shape this actually arrives in. + let e = Settings::from_lookup(|k| { + if k == ENV_ADDR { + Some(String::new()) + } else { + full(k) + } + }) + .expect_err("an empty address is not an address"); + assert!(matches!(e, Error::MissingEnv(ENV_ADDR)), "got {e:?}"); + + let s = Settings::from_lookup(|k| { + if k == ENV_CACERT { + Some(String::new()) + } else { + full(k) + } + }) + .expect("an empty CA is optional, not fatal"); + assert_eq!(s.ca_path, None); + } + + #[test] + fn an_unreadable_cert_names_the_file_and_the_variable() { + let e = read_file(ENV_CLIENT_CERT, "/nonexistent/cert.pem") + .expect_err("the file does not exist"); + match e { + Error::Identity { var, ref path, .. } => { + assert_eq!(var, ENV_CLIENT_CERT); + assert_eq!(path, "/nonexistent/cert.pem"); + } + other => panic!("wanted an Identity error, got {other:?}"), + } + } + + #[test] + fn the_value_field_matches_what_the_nix_reader_asks_for() { + // The literal is the point: `bao kv get -field=value` is the other end + // of this agreement and lives in a file no Rust test can reach, so the + // name is pinned here rather than derived from the struct. + let json = serde_json::to_string(&Credential { + value: "t".to_owned(), + }) + .expect("a struct of one String serialises"); + assert_eq!(json, r#"{"value":"t"}"#); + } +} diff --git a/swarm-secret-client/src/lib.rs b/swarm-secret-client/src/lib.rs new file mode 100644 index 00000000..02fa1efd --- /dev/null +++ b/swarm-secret-client/src/lib.rs @@ -0,0 +1,68 @@ +//! The swarm's secret-store client: where a credential lives, and how both ends +//! reach it. +//! +//! The HTTP is [`vaultrs`]'s job. What this crate owns is the *agreements* — +//! the path a credential is written to and read from ([`path`]), the field its +//! bytes live in, and the translation from this deployment's environment into +//! a logged-in client ([`client`]). Each of those is a thing the controller and +//! a hive must say identically, so it is said once here. + +pub mod client; +pub mod path; + +pub use client::SecretStore; + +/// What can go wrong between "we have a client certificate" and "we have the +/// credential". +#[derive(Debug, thiserror::Error)] +pub enum Error { + /// A name that would have addressed something other than what the caller + /// meant. See [`path`]. + #[error("{kind} name {value:?} is not a single path segment of [A-Za-z0-9_-]")] + PathSegment { + /// Which name was rejected — `agent` or `account`. + kind: &'static str, + /// The offending value, quoted in the message because the caller + /// usually got it from config and needs to see which one. + value: String, + }, + + /// A variable the store's address or identity comes from is unset or + /// empty. Named rather than defaulted: a wrong store address fails much + /// later and much less clearly than a missing one. + #[error("{0} is unset or empty")] + MissingEnv(&'static str), + + /// A client-certificate file named by the environment could not be read. + #[error("reading {path} (from {var}): {source}")] + Identity { + /// The variable that named the file. + var: &'static str, + /// The path it named. + path: String, + /// The underlying IO failure. + source: std::io::Error, + }, + + /// The address would not parse into a URL the client can use. + #[error("the store's settings are unusable: {0}")] + Settings(String), + + /// The store refused us, was unreachable, or answered something we could + /// not parse. + #[error(transparent)] + Vault(#[from] Box), + + /// The client certificate and key did not form a usable identity, or the + /// CA bundle did not parse. + #[error("building the TLS identity: {0}")] + Tls(#[source] reqwest::Error), +} + +impl From for Error { + fn from(e: vaultrs::error::ClientError) -> Self { + // Boxed because `ClientError` is large enough that carrying it inline + // makes every `Result` in the crate pay for the rare arm. + Self::Vault(Box::new(e)) + } +} diff --git a/swarm-secret-client/src/path.rs b/swarm-secret-client/src/path.rs new file mode 100644 index 00000000..00116422 --- /dev/null +++ b/swarm-secret-client/src/path.rs @@ -0,0 +1,98 @@ +//! Where a credential lives, for both ends of the store. +//! +//! The controller writes and a hive reads, and neither is senior to the other, +//! so the path they must agree on is built here rather than formatted at each +//! call site. + +use crate::Error; + +/// The KV v2 mount every swarm secret lives under. +/// +/// A literal because the store's existing reader already hardcodes the same +/// one (`secret/swarm/matrix/registration-token`); an option nobody sets would +/// be two ways to say one thing. +pub const MOUNT: &str = "secret"; + +/// The prefix under [`MOUNT`] owned by per-agent credentials. +pub const AGENT_PREFIX: &str = "swarm/agents"; + +/// A path segment that cannot change the path's shape. +/// +/// The charset is deliberately narrower than what the store accepts: a `/` +/// turns one agent's segment into another agent's directory, and `..` walks +/// out of the prefix entirely. Both are names this crate receives from +/// elsewhere — an agent name from the topology, an account name from an +/// agent's own config — so neither is trusted to be well-formed here. +fn checked_segment(kind: &'static str, value: &str) -> Result<(), Error> { + if value.is_empty() { + return Err(Error::PathSegment { + kind, + value: value.to_owned(), + }); + } + if !value + .bytes() + .all(|b| b.is_ascii_alphanumeric() || b == b'-' || b == b'_') + { + return Err(Error::PathSegment { + kind, + value: value.to_owned(), + }); + } + Ok(()) +} + +/// The path holding `agent`'s token for the external matrix account `account`. +/// +/// # Errors +/// [`Error::PathSegment`] when either name contains anything but +/// `[A-Za-z0-9_-]`, which is what keeps one agent's name from addressing +/// another agent's secret. +pub fn matrix_account(agent: &str, account: &str) -> Result { + checked_segment("agent", agent)?; + checked_segment("account", account)?; + Ok(format!("{AGENT_PREFIX}/{agent}/matrix/{account}")) +} + +#[cfg(test)] +mod tests { + use super::*; + + #[test] + fn a_well_formed_pair_lands_under_the_agent_prefix() { + let p = matrix_account("atlas", "ops-relay").expect("both segments are legal"); + assert_eq!(p, "swarm/agents/atlas/matrix/ops-relay"); + assert!(p.starts_with(AGENT_PREFIX)); + } + + #[test] + fn a_segment_cannot_escape_its_own_directory() { + // Each of these is a *different* way to address another agent's tree, + // and the last two are the ones a charset check catches but a + // `contains("..")` check does not. + for bad in [ + "../argus", + "atlas/../argus", + "atlas/matrix", + "a b", + "a.b", + "", + ] { + assert!( + matrix_account(bad, "ops-relay").is_err(), + "agent segment {bad:?} must be refused" + ); + assert!( + matrix_account("atlas", bad).is_err(), + "account segment {bad:?} must be refused" + ); + } + } + + #[test] + fn the_legal_charset_is_actually_reachable() { + // The control for the test above: if `checked_segment` rejected + // everything, the escape cases would pass for the wrong reason. + assert!(matrix_account("a-b_C9", "d-e_F0").is_ok()); + } +}