06e8a9a09e
Nine of the 38 .nix tokens mentioned anywhere in *.rs did not name anything that exists. Twelve mentions, five distinct targets: hive-c0re.nix, hive-gateway.nix and hive-forge.nix are all directories now; nix/modules/ is not a directory we have; hive-forge-tools.nix was a bash script the binary replaced and is gone. Where the reference is load-bearing it is corrected rather than deleted, because the reference is the point: a comment saying a constant must match a nix literal is only useful if you can open the file it names. Where the module member was unambiguous the path now names it exactly. paths.rs's STATE_ROOT marker was the worst of them: it claimed the value came from services.hyperhive.c0re.statePath, in hive-c0re.nix. Neither exists. The option is not declared anywhere and the file is a directory, so a "must match" contract pointed at two things that cannot be opened. /var/lib/hyperhive is hardcoded on both sides, which is what the comment now says. hive-forge-tools.nix keeps no replacement: naming a file that was deliberately deleted helps nobody, and "replaces a prior bash script" is complete without it. Measured before and after with the same command: 9 unresolved of 38 before, 4 of 35 after. The remaining four are an example path in a doc comment, an upstream nixpkgs path, and two from one synthetic test fixture.
360 lines
16 KiB
Rust
360 lines
16 KiB
Rust
//! `ContainerView` + the snapshot builder that turns
|
|
//! `nixos-container list` (plus per-agent state on disk) into the row
|
|
//! shape the dashboard renders. Extracted from `dashboard.rs` so the
|
|
//! coordinator's rescan-and-emit helper can build the same view and
|
|
//! diff against the last snapshot to fire
|
|
//! `ContainerStateChanged` / `ContainerRemoved` events.
|
|
|
|
use std::collections::HashMap;
|
|
use std::path::Path;
|
|
|
|
use serde::Serialize;
|
|
|
|
use crate::coordinator::Coordinator;
|
|
use crate::lifecycle::{self, AGENT_PREFIX, UnitState};
|
|
|
|
// Independent per-agent flags, each its own badge on the dashboard card
|
|
// and each diffed separately by `rescan_containers_and_emit`. Grouping
|
|
// them into nested structs would need `serde(flatten)` to keep the JSON
|
|
// the frontend already consumes, for no readability gain — same
|
|
// rationale as `LifecycleScope` in hive-host-sock.
|
|
#[allow(
|
|
clippy::struct_excessive_bools,
|
|
reason = "flat wire projection of independent per-agent flags"
|
|
)]
|
|
#[derive(Serialize, Clone, PartialEq, Eq, Debug)]
|
|
pub struct ContainerView {
|
|
/// Logical agent name (no `h-` prefix). Used in action URLs.
|
|
pub name: String,
|
|
/// Container name as nixos-container sees it (`h-foo`). Internal only;
|
|
/// not serialized to API responses since the dashboard no longer displays it.
|
|
#[serde(skip)]
|
|
pub container: String,
|
|
pub port: u16,
|
|
pub running: bool,
|
|
/// The container's unit is in systemd's `failed` state — it exhausted
|
|
/// its bounded restarts and gave up, rather than being stopped
|
|
/// deliberately.
|
|
///
|
|
/// Orthogonal to `running` rather than a variant of it: a failed unit
|
|
/// is not running, but a not-running unit is usually just *off*. That
|
|
/// distinction is the whole point — without it a container that gave
|
|
/// up is indistinguishable from one an operator stopped on purpose.
|
|
#[serde(default)]
|
|
pub failed: bool,
|
|
pub needs_update: bool,
|
|
pub needs_login: bool,
|
|
/// First 12 chars of the sha the meta flake currently has locked
|
|
/// for this agent's input.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub deployed_sha: Option<String>,
|
|
/// Name of this agent's parent in the agent hierarchy. `None`
|
|
/// marks the agent as root-level; the dashboard renders it without
|
|
/// indentation. Sourced from `meta/topology.json` (single source of
|
|
/// truth, hive-c0re-owned) — NOT from per-agent agent.nix, because
|
|
/// an agent shouldn't be able to unilaterally declare its own place
|
|
/// in the tree. See `docs/agent-hierarchy.md::Current state`.
|
|
#[serde(default, skip_serializing_if = "Option::is_none")]
|
|
pub parent: Option<String>,
|
|
/// The Claude model the agent's harness is currently using, read from
|
|
/// `state/hyperhive-harness.json["active_model"]`. `None` when the
|
|
/// agent has never started a turn or the field is absent. Only
|
|
/// meaningful when `running` is true; the dashboard skips the badge
|
|
/// for stopped containers.
|
|
#[serde(default, skip_serializing_if = "Option::is_none")]
|
|
pub active_model: Option<String>,
|
|
/// The agent's turn loop is parked: the container is up and still
|
|
/// serving its web UI / MCP daemons, but it drives no turns and its
|
|
/// inbox messages queue unacked until it resumes. Sourced from the
|
|
/// pause marker in the harness dir (`Coordinator::is_paused`), so it
|
|
/// stays true across a container restart — and, unlike `needs_login`,
|
|
/// is reported for stopped containers too: pausing a stopped agent is
|
|
/// a legitimate way to keep it idle when it next boots.
|
|
#[serde(default)]
|
|
pub paused: bool,
|
|
/// Effective systemd `CPUQuota=` for this container (e.g. `"400%"`) —
|
|
/// the per-agent override from `meta/resource-limits.json` when set,
|
|
/// otherwise the hive-wide `agentCpuQuota`. Always populated: there
|
|
/// is no "unset" state to render, only "same as everyone else".
|
|
/// Reflects what the *drop-in says*, which is what the next start
|
|
/// will enforce — not a live cgroup reading.
|
|
pub cpu_quota: String,
|
|
/// Effective systemd `MemoryMax=` for this container (e.g. `"8G"`).
|
|
/// Same resolution + caveat as [`ContainerView::cpu_quota`].
|
|
pub memory_max: String,
|
|
}
|
|
|
|
/// Build the full container list. Wraps `lifecycle::list()` and
|
|
/// resolves every per-agent attribute the dashboard surfaces.
|
|
///
|
|
/// Takes `hive` because the effective resource limits are a per-field
|
|
/// fallback onto the hive-wide `agent_cpu_quota` / `agent_memory_max`,
|
|
/// and those live on [`crate::coordinator::HiveEnv`], not on disk. Both callers already
|
|
/// hold a `Coordinator`, so this is a parameter rather than a global.
|
|
pub async fn build_all(hive: &crate::coordinator::HiveEnv) -> Vec<ContainerView> {
|
|
let raw = lifecycle::list().await.unwrap_or_default();
|
|
let locked = read_meta_locked_revs();
|
|
// Pull the topology map once and look up each agent's parent below.
|
|
// Empty / absent topology.json → every agent root-level (safe
|
|
// degradation for fresh installs that haven't run sync_agents yet).
|
|
let topology = crate::topology::read();
|
|
// Same once-per-scan treatment as the topology map: the override file
|
|
// is read here and resolved per agent below, rather than re-read for
|
|
// every container on every SSE scan.
|
|
let limits = crate::resource_limits::read();
|
|
let mut out = Vec::new();
|
|
for c in &raw {
|
|
let Some(logical) = c.strip_prefix(AGENT_PREFIX) else {
|
|
continue;
|
|
};
|
|
// Parse the nspawn machine suffix into an Ident once at this
|
|
// enumeration origin; a suffix that isn't a valid ident isn't one
|
|
// of our agents, so skip it.
|
|
let Ok(logical) = hive_types::Ident::parse(logical) else {
|
|
continue;
|
|
};
|
|
let deployed_full = locked
|
|
.get(&format!("agent-{logical}"))
|
|
.map(std::string::String::as_str);
|
|
let needs_update =
|
|
crate::auto_update::agent_config_pending(logical.as_str(), deployed_full).await;
|
|
let deployed_sha = deployed_full.map(|s| s[..s.len().min(12)].to_owned());
|
|
let parent = topology.get(logical.as_str()).cloned().flatten();
|
|
// One `systemctl` call for both facts: `unit_state` is the same
|
|
// shell-out `is_running` makes, minus `--quiet`. Asking twice would
|
|
// double the per-agent subprocess count on every SSE scan.
|
|
let state = lifecycle::unit_state(logical.as_str()).await;
|
|
let running = state == UnitState::Active;
|
|
let failed = state == UnitState::Failed;
|
|
// needs_login fires when EITHER the claude session dir is missing
|
|
// (boot-time / fresh container) OR the harness wrote the auth-failed
|
|
// sentinel because a turn hit 401. Cleared for stopped containers —
|
|
// stale sentinel state is not meaningful when the harness isn't up.
|
|
//
|
|
// The first half doesn't apply to an api-key agent
|
|
// (`hyperhive.useApiKey`, stamped as `api_key_mode` in the
|
|
// consolidated state file by `hive_agent::harness_state::write_api_key_mode`):
|
|
// its `~/.claude/` is empty by design (no OAuth flow to complete),
|
|
// so an empty dir there means nothing — only the auth-failed
|
|
// sentinel (a real 401, meaning the configured key itself is bad)
|
|
// still counts.
|
|
//
|
|
// One `read_harness_flags` call for both fields, not a wrapper per
|
|
// field: this is the only call site that needs more than one, and
|
|
// a wrapper each would read the file twice per agent per sweep for
|
|
// no reason.
|
|
let (_, needs_login_sentinel, is_api_key) = read_harness_flags(&logical);
|
|
let needs_login = running
|
|
&& ((!is_api_key && !claude_has_session(&Coordinator::agent_claude_dir(&logical)))
|
|
|| needs_login_sentinel);
|
|
// Read the active model from the harness state file. Only surfaced
|
|
// when the container is running — stale model info from a stopped
|
|
// agent is misleading (the model may change on next boot).
|
|
let active_model = if running {
|
|
read_active_model(&logical)
|
|
} else {
|
|
None
|
|
};
|
|
let paused = Coordinator::is_paused(&logical);
|
|
let (cpu_quota, memory_max) = crate::resource_limits::effective_from(
|
|
&limits,
|
|
logical.as_str(),
|
|
&hive.agent_cpu_quota,
|
|
&hive.agent_memory_max,
|
|
);
|
|
out.push(ContainerView {
|
|
port: lifecycle::agent_web_port(logical.as_str()),
|
|
running,
|
|
failed,
|
|
container: c.clone(),
|
|
name: logical.into_string(),
|
|
needs_update,
|
|
needs_login,
|
|
deployed_sha,
|
|
parent,
|
|
active_model,
|
|
paused,
|
|
cpu_quota,
|
|
memory_max,
|
|
});
|
|
}
|
|
out
|
|
}
|
|
|
|
/// Host-side mirror of `hive_agent::login::has_session`. Returns true
|
|
/// if the agent's bound `~/.claude/` dir on disk contains any regular
|
|
/// file. Reads each `build_all()` so a login driven from the agent's
|
|
/// own web UI reflects on the next snapshot.
|
|
pub fn claude_has_session(dir: &Path) -> bool {
|
|
let Ok(entries) = std::fs::read_dir(dir) else {
|
|
return false;
|
|
};
|
|
entries
|
|
.flatten()
|
|
.any(|e| e.file_type().is_ok_and(|t| t.is_file()))
|
|
}
|
|
|
|
/// Read `rate_limited` + `needs_login` (auth-failed sentinel) +
|
|
/// `api_key_mode` from the consolidated `hyperhive-harness.json`. Falls
|
|
/// back to the legacy individual sentinel files written by older harness
|
|
/// builds so in-place upgrades don't lose state during the transition
|
|
/// window — `api_key_mode` has no legacy equivalent (it postdates the
|
|
/// consolidated file), so that fallback just says `false`, the correct
|
|
/// answer for any harness build old enough to have never written it.
|
|
fn read_harness_flags(name: &hive_types::Ident) -> (bool, bool, bool) {
|
|
let dir = Coordinator::agent_notes_dir(name);
|
|
if let Ok(raw) = std::fs::read_to_string(dir.join("hyperhive-harness.json"))
|
|
&& let Ok(v) = serde_json::from_str::<serde_json::Value>(&raw)
|
|
{
|
|
let rl = v
|
|
.get("rate_limited")
|
|
.and_then(serde_json::Value::as_bool)
|
|
.unwrap_or(false);
|
|
let nl = v
|
|
.get("needs_login")
|
|
.and_then(serde_json::Value::as_bool)
|
|
.unwrap_or(false);
|
|
let akm = v
|
|
.get("api_key_mode")
|
|
.and_then(serde_json::Value::as_bool)
|
|
.unwrap_or(false);
|
|
return (rl, nl, akm);
|
|
}
|
|
// Legacy fallback: presence of individual sentinel files.
|
|
let rate_limited = dir.join("hyperhive-rate-limited").exists();
|
|
let needs_login = dir.join("hyperhive-needs-login").exists();
|
|
(rate_limited, needs_login, false)
|
|
}
|
|
|
|
/// Read the agent's free-text status and the Unix timestamp when it was last set
|
|
/// (derived from the file's mtime). Returns `(None, None)` when the file is absent
|
|
/// or empty. `pub` so `socket_server` and `socket_server` can populate `AgentMeta`.
|
|
///
|
|
/// NB: callers building `AgentMeta` for a *stopped* container should
|
|
/// clear the result — the on-disk status is a stale snapshot from
|
|
/// before the stop. Use `read_agent_status_live` for that.
|
|
pub fn read_agent_status(name: &hive_types::Ident) -> (Option<String>, Option<i64>) {
|
|
let path = Coordinator::agent_notes_dir(name).join("hyperhive-status");
|
|
let meta = std::fs::metadata(&path).ok();
|
|
// Read at most STATUS_MAX_CHARS * 4 + 2 bytes: 4 is the max UTF-8 byte
|
|
// width per char, +2 for the trailing newline. Guards against a
|
|
// pathologically large file written outside the harness validation path.
|
|
let s = {
|
|
use std::io::Read as _;
|
|
std::fs::File::open(&path).ok().and_then(|f| {
|
|
let cap = (crate::limits::STATUS_MAX_CHARS * 4 + 2) as u64;
|
|
let mut buf = String::new();
|
|
f.take(cap).read_to_string(&mut buf).ok().map(|_| buf)
|
|
})
|
|
};
|
|
let text = s
|
|
.as_deref()
|
|
.map(str::trim)
|
|
.filter(|t| !t.is_empty())
|
|
.map(str::to_owned);
|
|
let mtime = meta.and_then(|m| {
|
|
m.modified().ok().and_then(|t| {
|
|
t.duration_since(std::time::UNIX_EPOCH)
|
|
.ok()
|
|
.and_then(|d| i64::try_from(d.as_secs()).ok())
|
|
})
|
|
});
|
|
if text.is_none() {
|
|
(None, None)
|
|
} else {
|
|
(text, mtime)
|
|
}
|
|
}
|
|
|
|
/// Wraps `read_agent_status` with the same "stopped containers have
|
|
/// stale state" gate `build_all` uses. Returns `(None, None, false)`
|
|
/// when the container isn't running so callers don't have to know
|
|
/// about the sentinel rules — they just hand back what we give them.
|
|
///
|
|
/// Returned tuple is `(status_text, status_set_at, running)`.
|
|
/// `name` is the logical agent name (same as the broker recipient).
|
|
pub async fn read_agent_status_live(
|
|
name: &hive_types::Ident,
|
|
) -> (Option<String>, Option<i64>, bool) {
|
|
if !lifecycle::is_running(name.as_str()).await {
|
|
return (None, None, false);
|
|
}
|
|
let (text, set_at) = read_agent_status(name);
|
|
(text, set_at, true)
|
|
}
|
|
|
|
/// Read the active Claude model from `hyperhive-harness.json` (the
|
|
/// consolidated harness state file in the agent's state dir). Written by
|
|
/// the harness on startup and on every `set_model` / `emit_status` call,
|
|
/// so it always reflects the resolved priority (nix config > runtime
|
|
/// override > default). Returns `None` when the field is absent or the
|
|
/// harness has not yet started a turn.
|
|
fn read_active_model(name: &hive_types::Ident) -> Option<String> {
|
|
let path = Coordinator::agent_notes_dir(name).join("hyperhive-harness.json");
|
|
let raw = std::fs::read_to_string(path).ok()?;
|
|
let v: serde_json::Value = serde_json::from_str(&raw).ok()?;
|
|
v.get("active_model")
|
|
.and_then(serde_json::Value::as_str)
|
|
.filter(|s| !s.is_empty())
|
|
.map(str::to_owned)
|
|
}
|
|
|
|
/// Host-side hive + swarm display names, read from the c0re service's
|
|
/// own process env. The hyperhive NixOS module sets these from
|
|
/// `services.hyperhive.hiveName` + `services.hyperhive.swarm.name`
|
|
/// (the hive names itself; the swarm it joins is named one level out).
|
|
/// The agent-side
|
|
/// `hive-agent::identity::{hive_name, swarm_name}` accessors read the
|
|
/// same env vars after they're forwarded into each sub-agent's
|
|
/// harness service environment by `meta::render_flake`; surfacing
|
|
/// them here from c0re's own env keeps the manager + agent
|
|
/// `GetAgentMeta` paths consistent without a round-trip to the
|
|
/// target container.
|
|
///
|
|
/// Returns `(hive_name, swarm_name)`. Each is `None` when the
|
|
/// corresponding env var is unset or empty.
|
|
#[must_use]
|
|
pub fn hive_swarm_names() -> (Option<String>, Option<String>) {
|
|
let read = |var: &str| -> Option<String> { std::env::var(var).ok().filter(|s| !s.is_empty()) };
|
|
(read("HYPERHIVE_HIVE_NAME"), read("HYPERHIVE_SWARM_NAME"))
|
|
}
|
|
|
|
/// Map of `agent-<n>` → locked sha from meta's flake.lock. Used to
|
|
/// render the `deployed:<sha12>` chip per container row.
|
|
fn read_meta_locked_revs() -> HashMap<String, String> {
|
|
let mut out = HashMap::new();
|
|
let Ok(raw) = std::fs::read_to_string(crate::paths::meta_flake_lock()) else {
|
|
return out;
|
|
};
|
|
let Ok(json) = serde_json::from_str::<serde_json::Value>(&raw) else {
|
|
return out;
|
|
};
|
|
let Some(nodes) = json.get("nodes").and_then(|v| v.as_object()) else {
|
|
return out;
|
|
};
|
|
let Some(root_name) = json.get("root").and_then(|v| v.as_str()) else {
|
|
return out;
|
|
};
|
|
let Some(root_inputs) = nodes
|
|
.get(root_name)
|
|
.and_then(|n| n.get("inputs"))
|
|
.and_then(|v| v.as_object())
|
|
else {
|
|
return out;
|
|
};
|
|
for alias in root_inputs.keys() {
|
|
let target_name = match root_inputs.get(alias) {
|
|
Some(serde_json::Value::String(s)) => s.clone(),
|
|
_ => continue,
|
|
};
|
|
if let Some(rev) = nodes
|
|
.get(&target_name)
|
|
.and_then(|n| n.get("locked"))
|
|
.and_then(|v| v.get("rev"))
|
|
.and_then(|v| v.as_str())
|
|
{
|
|
out.insert(alias.clone(), rev.to_owned());
|
|
}
|
|
}
|
|
out
|
|
}
|