hyperhive/hive-subagent-mcp/src/session.rs

486 lines
18 KiB
Rust

//! The claude-facing half of this daemon: spawn a subagent turn, track it
//! only while it's alive, and push exactly one todo when it finishes.
//!
//! **No task files, no restart recovery.** The daemon's only state is an
//! in-memory `name -> Option<Cancel>` map (see `State`'s own doc for what
//! the `None`/`Some` split is for), live for exactly as long as the process
//! is — a daemon restart means whatever was running gets killed with it
//! (`tokio`'s own child-process drop semantics), not adopted. The durable
//! record of a subagent's existence is `hive_claude::SessionStore` — claude's
//! own on-disk session, found again by name. `continue` is how a caller
//! reattaches to it, whether that's "give it a new turn" or "the daemon
//! restarted and I want to pick this back up."
//!
//! **No mid-turn compaction.** Building on `hive_claude::Claude::spawn` +
//! `RunningClaude::wait` directly (not `InfiniteSession::run`) is what makes
//! `interrupt` possible at all — `InfiniteSession` has no cancel handle to
//! reach in from the outside, only `RunningClaude::cancel_handle` does. The
//! trade: this daemon doesn't get `InfiniteSession`'s reactive-compact-on-
//! overflow or proactive-checkpoint-compact for free: a turn that overflows
//! the context window surfaces as a plain `Error::PromptTooLong` to the
//! caller instead of self-healing. Subagents are meant to be bounded,
//! single-batch work (see the `base:claude-subagents` skill), not sessions
//! long-lived enough to need in-place compaction — a real follow-up if that
//! assumption stops holding, not shipped here.
use std::collections::HashMap;
use std::path::PathBuf;
use std::sync::{Arc, Mutex, PoisonError};
use hive_claude::{Attach, Cancel, Claude, Config, NoopSink, SessionStore};
/// This daemon's whole state: which names currently have a live process or
/// a reservation in flight, and where to push the completion todo.
/// `Arc`-wrapped so the background task that drives a turn to completion
/// can outlive the tool call that started it.
///
/// The map value is `Option<Cancel>`: `None` means `name` is reserved for
/// an in-flight `start`/`continue` that hasn't reached a confirmed
/// `Claude::spawn` yet; `Some(cancel)` means a real process is tracked and
/// interruptible. The `None` state exists to close a real TOCTOU window a
/// reviewer caught in the original check-then-insert version: checking "is
/// `name` free" and committing to it are two different lock acquisitions
/// unless the check *is* the reservation — see `reserve`.
pub struct State {
running: Mutex<HashMap<String, Option<Cancel>>>,
socket: PathBuf,
}
impl State {
#[must_use]
pub fn new(socket: PathBuf) -> Self {
Self {
running: Mutex::new(HashMap::new()),
socket,
}
}
/// `Some(true)` — a live process is tracked, interruptible. `Some(false)`
/// — reserved for an in-flight start/continue, not yet a confirmed
/// spawn. `None` — nothing tracked under `name` at all.
fn occupancy(&self, name: &str) -> Option<bool> {
self.running
.lock()
.unwrap_or_else(PoisonError::into_inner)
.get(name)
.map(Option::is_some)
}
/// Atomically claim `name` for an in-flight start/continue: check
/// "is anything tracked under this name" and "commit to this call
/// owning it" in the *same* lock acquisition, so two calls racing the
/// same name can't both pass a check before either commits (the exact
/// same-name concurrent-run hazard this module's doc warns about).
/// Returns `false` (reserving nothing) if `name` is already reserved
/// or running.
fn reserve(&self, name: &str) -> bool {
let mut running = self.running.lock().unwrap_or_else(PoisonError::into_inner);
if running.contains_key(name) {
return false;
}
running.insert(name.to_owned(), None);
true
}
/// Release a reservation that never made it to a real spawn (an error
/// on the slow path between `reserve` and `Claude::spawn` succeeding).
/// A no-op if the entry was already upgraded to `Some` — this only ever
/// clears a still-`None` placeholder, never a live process.
fn release_reservation(&self, name: &str) {
let mut running = self.running.lock().unwrap_or_else(PoisonError::into_inner);
if matches!(running.get(name), Some(None)) {
running.remove(name);
}
}
}
/// A caller-chosen name, validated the same way `hive-bash-mcp`'s task ids
/// are: a single safe [`hive_types::Ident`] segment, which doubles as
/// claude's own `--name`/`--resume` session title.
fn validate_name(name: &str) -> anyhow::Result<()> {
hive_types::Ident::parse(name)
.map(|_| ())
.map_err(|e| anyhow::anyhow!("invalid subagent name {name:?}: {e}"))
}
/// Extend the ambient `OTEL_RESOURCE_ATTRIBUTES` with a `subagent=<name>`
/// attribute, so every token/cost/tool-call data point this subagent's own
/// claude process emits carries it alongside the parent's `agent=<name>`
/// label. `Config.env` applies after the inherited environment, so this one
/// entry overriding the ambient value is the intended shape, not a
/// wholesale replacement.
fn subagent_otel_attrs(name: &str) -> String {
match std::env::var("OTEL_RESOURCE_ATTRIBUTES") {
Ok(existing) if !existing.is_empty() => format!("{existing},subagent={name}"),
_ => format!("subagent={name}"),
}
}
/// Build the `Config` one subagent turn runs against. `prompt_file`, when
/// given, becomes `--append-system-prompt-file` — the subagent's task
/// instructions. Always `--dangerously-skip-permissions --strict-mcp-config`
/// (no `--mcp-config` override — a safety property, not a knob).
fn build_config(name: &str, model: Option<String>, prompt_file: Option<&str>) -> Config {
let mut extra_args = vec!["--dangerously-skip-permissions".to_owned()];
if let Some(path) = prompt_file {
extra_args.push("--append-system-prompt-file".to_owned());
extra_args.push(path.to_owned());
}
Config {
model,
strict_mcp_config: true,
extra_args,
env: vec![(
"OTEL_RESOURCE_ATTRIBUTES".to_owned(),
subagent_otel_attrs(name),
)],
..Default::default()
}
}
/// The [`SessionStore`] a subagent's turn actually runs against — same
/// resolution `hive_claude::Claude` itself uses, so a lookup here can't
/// disagree with what the driver does a moment later.
fn build_store(config: &Config) -> std::io::Result<SessionStore> {
Ok(SessionStore::new(
config.resolved_claude_home()?,
config.resolved_cwd()?,
))
}
/// Start a fresh subagent under `name`. A prior *finished* session under
/// the same name is archived first (so this is a real fresh start, not a
/// silent resume of old history) — a *currently running* one is refused
/// outright, since `hive_claude::InfiniteSession`'s own docs warn that two
/// concurrent runs against the same name corrupt both.
///
/// # Errors
///
/// A name already running, an invalid name, an archive failure, or the
/// underlying `Claude::spawn` failing (binary missing, etc.) — the last
/// case is the only one that can happen *after* commit-to-run, and it's
/// exactly why nothing is registered in `running` until spawn actually
/// succeeds.
pub fn start(
state: &Arc<State>,
name: &str,
model: Option<String>,
prompt_file: &str,
trigger: String,
) -> anyhow::Result<String> {
validate_name(name)?;
if !state.reserve(name) {
anyhow::bail!("subagent `{name}` is already running — use `continue` or `interrupt`");
}
let result = start_reserved(state, name, model, prompt_file, trigger);
if result.is_err() {
state.release_reservation(name);
}
result
}
/// The slow, fallible part of `start`, run only after `reserve` has
/// already closed the TOCTOU window — split out so `start` can release the
/// reservation on any error path here without duplicating that logic per
/// failure site.
fn start_reserved(
state: &Arc<State>,
name: &str,
model: Option<String>,
prompt_file: &str,
trigger: String,
) -> anyhow::Result<String> {
let config = build_config(name, model, Some(prompt_file));
let store = build_store(&config)?;
if store.find_by_title(name).is_some() {
tracing::info!(
name,
"start: archiving a finished prior session for a fresh start"
);
store
.archive_by_title(name)
.map_err(|e| anyhow::anyhow!("archiving the prior `{name}` session failed: {e}"))?;
}
spawn_and_track(
state,
name,
&config,
&Attach::Create(name.to_owned()),
trigger,
)
}
/// Give an existing named session a new turn — resuming it whether that
/// means "the previous turn finished, here's the next instruction" or "the
/// daemon restarted, reattaching." Refuses a name with no session on disk
/// at all (nothing to continue) or one already running (same
/// concurrent-run hazard as `start`).
///
/// # Errors
///
/// No session under `name`, an invalid name, one already running, or
/// `Claude::spawn` failing.
pub fn continue_(
state: &Arc<State>,
name: &str,
prompt: String,
model: Option<String>,
) -> anyhow::Result<String> {
validate_name(name)?;
if !state.reserve(name) {
anyhow::bail!(
"subagent `{name}` is already running — use `interrupt` first if you meant to redirect it"
);
}
let result = continue_reserved(state, name, prompt, model);
if result.is_err() {
state.release_reservation(name);
}
result
}
/// The slow, fallible part of `continue_`, run only after `reserve` has
/// already closed the TOCTOU window — same split rationale as
/// `start_reserved`.
fn continue_reserved(
state: &Arc<State>,
name: &str,
prompt: String,
model: Option<String>,
) -> anyhow::Result<String> {
let config = build_config(name, model, None);
let store = build_store(&config)?;
if store.find_by_title(name).is_none() {
anyhow::bail!(
"no session named `{name}` exists — `continue` resumes an existing subagent, `start` \
creates one"
);
}
spawn_and_track(
state,
name,
&config,
&Attach::Resume(name.to_owned()),
prompt,
)
}
/// Spawn the child (synchronous — returns with a real pid the instant the
/// process exists, which *is* "confirmed running": there is no stronger
/// signal to wait for without slowing every call down for no reason), track
/// it in `running`, and hand the actual turn off to a background task so
/// the caller returns immediately instead of blocking on the whole turn.
/// Not `async` itself — `tokio::spawn` needs an active runtime to spawn
/// *onto*, not an `async` caller to spawn *from*.
fn spawn_and_track(
state: &Arc<State>,
name: &str,
config: &Config,
attach: &Attach,
prompt: String,
) -> anyhow::Result<String> {
let running = Claude::spawn(config, attach)
.map_err(|e| anyhow::anyhow!("starting the subagent process failed: {e}"))?;
// Upgrades the `None` reservation `reserve` already placed here to a
// real cancel handle — same key, so there's no window where `name`
// reads as unoccupied between the reservation and this insert.
state
.running
.lock()
.unwrap_or_else(PoisonError::into_inner)
.insert(name.to_owned(), Some(running.cancel_handle()));
let state = Arc::clone(state);
let task_name = name.to_owned();
tokio::spawn(async move {
let outcome = running.wait(&prompt, &NoopSink).await;
state
.running
.lock()
.unwrap_or_else(PoisonError::into_inner)
.remove(&task_name);
let summary = match outcome {
Ok(()) => "turn complete".to_owned(),
Err(e) => {
tracing::warn!(name = %task_name, error = %e, "subagent: turn failed");
format!("claude error: {e}")
}
};
push_completion_todo(&state.socket, &task_name, &summary).await;
});
Ok(format!("subagent `{name}` started"))
}
/// Report whether `name` is currently running — a zero-cost check that
/// never launches a process, unlike `continue`. Distinguishes four states:
/// running, starting (reserved, not yet a confirmed spawn — see `State`'s
/// doc), idle (a session exists but nothing is in flight), and no such
/// session at all.
///
/// # Errors
///
/// An invalid name, or no session — running or on disk — under `name`.
pub fn status(state: &State, name: &str) -> anyhow::Result<String> {
validate_name(name)?;
match state.occupancy(name) {
Some(true) => return Ok(format!("subagent `{name}` is running")),
Some(false) => {
return Ok(format!(
"subagent `{name}` is starting — not yet confirmed running"
));
}
None => {}
}
let config = build_config(name, None, None);
let store = build_store(&config)?;
if store.find_by_title(name).is_some() {
Ok(format!(
"subagent `{name}` is idle — its last turn finished; `continue` to give it another"
))
} else {
anyhow::bail!("no subagent named `{name}` exists — `start` creates one")
}
}
/// Signal `name`'s running process — `force` picks SIGKILL over SIGINT (see
/// `hive_claude::Cancel::cancel`). Refuses a name with nothing running: no
/// entry at all, or one still in the brief `reserve`d-but-not-yet-spawned
/// window (nothing to signal yet — the reservation is put back so a
/// concurrent `start`/`continue` for the same name still gets refused).
///
/// # Errors
///
/// An invalid name, nothing tracked under `name`, or `name` is still
/// starting (reserved, not yet a confirmed spawn).
pub fn interrupt(state: &State, name: &str, force: bool) -> anyhow::Result<String> {
validate_name(name)?;
let mut running = state.running.lock().unwrap_or_else(PoisonError::into_inner);
match running.remove(name) {
None => anyhow::bail!("no subagent named `{name}` is currently running"),
Some(None) => {
running.insert(name.to_owned(), None);
anyhow::bail!(
"subagent `{name}` is still starting — not yet confirmed running, try again \
shortly"
);
}
Some(Some(cancel)) => {
drop(running);
cancel.cancel(force);
Ok(format!("interrupt sent to subagent `{name}`"))
}
}
}
/// Push `name`'s one-shot completion todo. Best-effort: a connect/write
/// failure is logged and swallowed, matching every other in-agent-socket
/// producer in this codebase — there's no retry queue to fall back to, and
/// the caller has already moved on by the time this fires.
async fn push_completion_todo(socket: &std::path::Path, name: &str, summary: &str) {
let req = hive_agent_sock::Request::UpsertTodo {
subsystem: "subagent".to_owned(),
key: Some(name.to_owned()),
summary: format!("subagent `{name}` finished: {summary}"),
source: None,
reopen_if_acked: false,
};
if let Err(e) = hive_sock_client::notify(socket, &req, hive_sock_client::Retry::None).await {
tracing::warn!(name, error = ?e, "subagent: completion todo push failed");
}
}
#[cfg(test)]
mod tests {
use super::*;
// `Cancel` can only be constructed from a real spawned process (no test
// fixture in `hive_claude` for it), so these exercise the reservation
// half of `State` directly — the actual TOCTOU-closure logic — rather
// than the full start/spawn path.
#[test]
fn reserve_is_exclusive_for_the_same_name() {
let state = State::new(PathBuf::from("/dev/null"));
assert!(state.reserve("dup"), "first reservation should succeed");
assert!(
!state.reserve("dup"),
"a second reservation for the same name must be refused — this is the exact race \
argus found: two calls both passing a check before either commits"
);
}
#[test]
fn reserve_does_not_cross_block_different_names() {
let state = State::new(PathBuf::from("/dev/null"));
assert!(state.reserve("a"));
assert!(
state.reserve("b"),
"unrelated names must not block each other"
);
}
#[test]
fn release_reservation_frees_the_name_for_reuse() {
let state = State::new(PathBuf::from("/dev/null"));
assert!(state.reserve("n"));
state.release_reservation("n");
assert!(
state.reserve("n"),
"releasing a still-`None` reservation must free the name again"
);
}
#[test]
fn occupancy_reflects_the_reserved_but_not_running_state() {
let state = State::new(PathBuf::from("/dev/null"));
assert_eq!(state.occupancy("never-reserved"), None);
state.reserve("n");
assert_eq!(
state.occupancy("n"),
Some(false),
"reserved-but-not-yet-spawned must read as occupied-but-not-running"
);
}
#[test]
fn otel_attrs_appends_when_ambient_var_is_set() {
// SAFETY: test-only env mutation, single-threaded within this fn's
// scope (no other test in this crate touches this var — checked).
unsafe {
std::env::set_var("OTEL_RESOURCE_ATTRIBUTES", "agent=damocles");
}
assert_eq!(
subagent_otel_attrs("batch-1"),
"agent=damocles,subagent=batch-1"
);
unsafe {
std::env::remove_var("OTEL_RESOURCE_ATTRIBUTES");
}
}
#[test]
fn otel_attrs_stands_alone_when_ambient_var_is_unset() {
unsafe {
std::env::remove_var("OTEL_RESOURCE_ATTRIBUTES");
}
assert_eq!(subagent_otel_attrs("batch-1"), "subagent=batch-1");
}
#[test]
fn build_config_only_appends_system_prompt_when_given() {
let with = build_config("n", None, Some("/tmp/p.md"));
assert!(
with.extra_args
.contains(&"--append-system-prompt-file".to_owned())
);
assert!(with.extra_args.contains(&"/tmp/p.md".to_owned()));
let without = build_config("n", None, None);
assert!(
!without
.extra_args
.contains(&"--append-system-prompt-file".to_owned())
);
}
}