The poller was a `tokio::spawn` inside the `hive-agent` serve loop. It never needed anything from that loop except a socket path, so being in-process bought nothing and cost two things: a harness restart took forge notifications down with it, and the whole forge/HTTP dependency tree was linked into the serve-loop binary. It is now `hive-forge-notify`, a per-agent daemon with its own systemd unit, a sibling of `hive-bash-daemon` and `hive-matrix-daemon`. Same contract as those two: it reaches the harness only by upserting todos on the in-agent socket, and nowhere else. The module moves verbatim (`notify.rs`) — the formatters, the activation gates, the dedupe map and all 33 tests are unchanged. Only the socket call sites are rewritten, onto a small local `todo_client` rather than the harness's. That mirrors what both sibling daemons already do, and the etiquette differs on purpose: the harness's client carries a 60s backoff schedule sized to ride out a hive-c0re restart, which its callers need because they have no retry of their own. This poller's two call sites both sit inside the 30s poll loop and both treat a failure as "leave the thread unread, try next tick", so the poll interval already is the retry; a second backoff would only stack sleeps and delay the rest of the batch. The unit is `Restart=on-failure`, not `always`. An agent with no forge account is a supported configuration and the poller reports it by logging why and exiting 0 — under `always` that clean exit would be a restart loop on every forge-less agent. `forgejo-api`, `url` and `time` drop out of `hive-agent`'s dependencies with the module. Also corrects docs that outlived the code they described: the persisted `forge_cursor` field is long gone (forge's own read-state is the durable record of what has been delivered), but `docs/persistence.md` and the `harness_state` module docs still documented it as live.
271 lines
10 KiB
Rust
271 lines
10 KiB
Rust
//! File-backed harness state, split out of [`crate::events`] (which owns
|
|
//! the live event bus + sqlite store). This module holds the runtime
|
|
//! model/effort selection and the consolidated `hyperhive-harness.json`
|
|
//! state file — the persisted knobs the harness reads/writes across
|
|
//! turns, none of which are about the live event stream.
|
|
|
|
use std::path::PathBuf;
|
|
|
|
/// Path to the persisted model file. Overridable via `HYPERHIVE_MODEL_FILE`
|
|
/// for dev / tests; otherwise derived from the agent's harness dir.
|
|
fn model_file_path() -> PathBuf {
|
|
std::env::var_os("HYPERHIVE_MODEL_FILE").map_or_else(
|
|
|| crate::paths::harness_dir().join("hyperhive-model"),
|
|
PathBuf::from,
|
|
)
|
|
}
|
|
|
|
pub(crate) fn load_model() -> Option<String> {
|
|
let s = std::fs::read_to_string(model_file_path()).ok()?;
|
|
let name = s.trim();
|
|
if name.is_empty() {
|
|
None
|
|
} else {
|
|
Some(name.to_owned())
|
|
}
|
|
}
|
|
|
|
pub(crate) fn persist_model(name: &str) -> std::io::Result<()> {
|
|
let path = model_file_path();
|
|
if let Some(parent) = path.parent() {
|
|
let _ = std::fs::create_dir_all(parent);
|
|
}
|
|
std::fs::write(path, format!("{name}\n"))
|
|
}
|
|
|
|
/// Path to the persisted effort-level file. Sibling of `hyperhive-model`,
|
|
/// overridable via `HYPERHIVE_EFFORT_FILE` for dev / tests; otherwise
|
|
/// derived from the agent's harness dir.
|
|
fn effort_file_path() -> PathBuf {
|
|
std::env::var_os("HYPERHIVE_EFFORT_FILE").map_or_else(
|
|
|| crate::paths::harness_dir().join("hyperhive-effort"),
|
|
PathBuf::from,
|
|
)
|
|
}
|
|
|
|
pub(crate) fn load_effort() -> Option<String> {
|
|
let s = std::fs::read_to_string(effort_file_path()).ok()?;
|
|
let level = s.trim();
|
|
if level.is_empty() {
|
|
None
|
|
} else {
|
|
Some(level.to_owned())
|
|
}
|
|
}
|
|
|
|
pub(crate) fn persist_effort(level: &str) -> std::io::Result<()> {
|
|
let path = effort_file_path();
|
|
if let Some(parent) = path.parent() {
|
|
let _ = std::fs::create_dir_all(parent);
|
|
}
|
|
std::fs::write(path, format!("{level}\n"))
|
|
}
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Consolidated harness state file
|
|
// ---------------------------------------------------------------------------
|
|
//
|
|
// `hyperhive-harness.json` replaces the two legacy boolean sentinel files
|
|
// (`hyperhive-rate-limited`, `hyperhive-needs-login`) that grew organically
|
|
// and had no shared schema. A single JSON file is self-documenting, atomic
|
|
// to write, and cheaper for hive-c0re to read on each sweep (one fopen vs
|
|
// two stat calls). See `docs/persistence.md::Harness state files`.
|
|
//
|
|
// Legacy sentinel files written by older harness builds are still honoured
|
|
// by `read_harness_state` so in-place upgrades don't lose state (the new
|
|
// harness re-normalises on first write). Old files are not deleted — they
|
|
// expire naturally when the state dir is purged. `hive-c0re::container_view`
|
|
// also checks the legacy paths as a fallback during the transition window.
|
|
|
|
const HARNESS_JSON: &str = "hyperhive-harness.json";
|
|
|
|
fn harness_json_path() -> PathBuf {
|
|
crate::paths::state_dir().join(HARNESS_JSON)
|
|
}
|
|
|
|
// Serialises the read-modify-write of `hyperhive-harness.json`. Every
|
|
// writer merges into the existing object rather than reconstructing it,
|
|
// so a future second writer preserves fields it doesn't own; the lock
|
|
// closes the lost-update window between a writer's read and its rename.
|
|
// (The forge poller used to be that second writer, for a delivery-dedupe
|
|
// cursor. It no longer persists one — forge's own read-state is the
|
|
// durable record — and it is a separate process now, which an
|
|
// in-process mutex could not have serialised anyway.)
|
|
static HARNESS_JSON_LOCK: std::sync::Mutex<()> = std::sync::Mutex::new(());
|
|
|
|
/// Read the consolidated state file as a JSON object, or an empty object
|
|
/// when it is missing / unparseable / not an object.
|
|
fn read_harness_json() -> serde_json::Value {
|
|
std::fs::read_to_string(harness_json_path())
|
|
.ok()
|
|
.and_then(|raw| serde_json::from_str::<serde_json::Value>(&raw).ok())
|
|
.filter(serde_json::Value::is_object)
|
|
.unwrap_or_else(|| serde_json::json!({}))
|
|
}
|
|
|
|
/// Atomically overwrite the state file (`.tmp` + rename) so hive-c0re
|
|
/// never reads a partial file.
|
|
fn write_harness_json(v: &serde_json::Value) {
|
|
let path = harness_json_path();
|
|
let tmp = path.with_extension("json.tmp");
|
|
if std::fs::write(&tmp, v.to_string()).is_ok() {
|
|
let _ = std::fs::rename(&tmp, &path);
|
|
}
|
|
}
|
|
|
|
pub(crate) fn read_harness_state() -> (bool, bool, Option<String>) {
|
|
// Try the new consolidated file first.
|
|
if let Ok(raw) = std::fs::read_to_string(harness_json_path())
|
|
&& let Ok(v) = serde_json::from_str::<serde_json::Value>(&raw)
|
|
{
|
|
let rate_limited = v
|
|
.get("rate_limited")
|
|
.and_then(serde_json::Value::as_bool)
|
|
.unwrap_or(false);
|
|
let needs_login = v
|
|
.get("needs_login")
|
|
.and_then(serde_json::Value::as_bool)
|
|
.unwrap_or(false);
|
|
let active_model = v
|
|
.get("active_model")
|
|
.and_then(serde_json::Value::as_str)
|
|
.filter(|s| !s.is_empty())
|
|
.map(str::to_owned);
|
|
return (rate_limited, needs_login, active_model);
|
|
}
|
|
// Fall back to legacy sentinel files written by older harness builds.
|
|
let state_dir = crate::paths::state_dir();
|
|
let rate_limited = state_dir.join("hyperhive-rate-limited").exists();
|
|
let needs_login = state_dir.join("hyperhive-needs-login").exists();
|
|
(rate_limited, needs_login, None)
|
|
}
|
|
|
|
/// Write the turn-loop's harness state fields via a read-modify-write so
|
|
/// any other writer's fields in the consolidated state file survive.
|
|
/// Pass `active_model: Some(s)` to update the resolved model (surfaced in
|
|
/// the dashboard badge); `None` leaves the stored value untouched.
|
|
pub(crate) fn write_harness_state(
|
|
rate_limited: bool,
|
|
needs_login: bool,
|
|
active_model: Option<&str>,
|
|
) {
|
|
let _guard = HARNESS_JSON_LOCK
|
|
.lock()
|
|
.unwrap_or_else(std::sync::PoisonError::into_inner);
|
|
let mut v = read_harness_json();
|
|
v["rate_limited"] = rate_limited.into();
|
|
v["needs_login"] = needs_login.into();
|
|
if let Some(model) = active_model {
|
|
v["active_model"] = model.into();
|
|
}
|
|
write_harness_json(&v);
|
|
}
|
|
|
|
/// Compiled-in fallback model used when neither `HIVE_DEFAULT_MODEL` nor a
|
|
/// persisted runtime override is present.
|
|
pub const DEFAULT_MODEL: &str = "haiku";
|
|
|
|
/// Return the model declared in `HIVE_DEFAULT_MODEL` (set from
|
|
/// `hyperhive.model` in `agent.nix`), or `None` if the env var is absent /
|
|
/// empty. When `Some`, this takes precedence over any persisted runtime
|
|
/// override so that nix config changes always take effect on rebuild.
|
|
#[must_use]
|
|
pub fn configured_model() -> Option<&'static str> {
|
|
// Leak once at startup — acceptable for a single config value.
|
|
std::env::var("HIVE_DEFAULT_MODEL")
|
|
.ok()
|
|
.filter(|s| !s.trim().is_empty())
|
|
.map(|s| &*Box::leak(s.into_boxed_str()))
|
|
}
|
|
|
|
/// Compiled-in fallback effort level — matches the `effortLevel` baked
|
|
/// into `prompts/claude-settings.json`.
|
|
pub const DEFAULT_EFFORT: &str = "medium";
|
|
|
|
/// Valid claude `--effort` levels, ascending. The operator picker is
|
|
/// constrained to these; [`is_valid_effort`] guards the persist path.
|
|
pub const EFFORT_LEVELS: [&str; 5] = ["low", "medium", "high", "xhigh", "max"];
|
|
|
|
/// True iff `level` is one of [`EFFORT_LEVELS`].
|
|
#[must_use]
|
|
pub fn is_valid_effort(level: &str) -> bool {
|
|
EFFORT_LEVELS.contains(&level)
|
|
}
|
|
|
|
/// Return the effort level declared in `HIVE_DEFAULT_EFFORT` (set from
|
|
/// `hyperhive.effortLevel` in `agent.nix`), or `None` if absent / empty.
|
|
/// Mirrors [`configured_model`]'s env shape. Unlike model, the persisted
|
|
/// runtime override takes precedence over this baseline (see `Bus::new`):
|
|
/// the operator's effort pick sticks across harness restart, with the nix
|
|
/// value only the default when no override was ever set.
|
|
#[must_use]
|
|
pub fn configured_effort() -> Option<&'static str> {
|
|
std::env::var("HIVE_DEFAULT_EFFORT")
|
|
.ok()
|
|
.filter(|s| !s.trim().is_empty())
|
|
.map(|s| &*Box::leak(s.into_boxed_str()))
|
|
}
|
|
|
|
/// Context-window size in tokens for a given model name.
|
|
///
|
|
/// Canonical per-model sizes are declared in the harness nix modules as
|
|
/// `hyperhive.contextWindowTokens` and injected as
|
|
/// `HIVE_CONTEXT_WINDOW_TOKENS_<KEY_UPPER>` env vars — so this function
|
|
/// normally just reads them. The Rust code carries no model knowledge;
|
|
/// updating model families only requires a Nix change.
|
|
///
|
|
/// Resolution order (first match wins):
|
|
/// 1. `HIVE_CONTEXT_WINDOW_TOKENS_<KEY>` — key (lowercased) is a
|
|
/// substring of the active model name. Populated by the Nix default
|
|
/// map for all known families; add/override in `agent.nix`.
|
|
/// 2. `HIVE_CONTEXT_WINDOW_TOKENS` — single global override (any model).
|
|
/// 3. Hard fallback: `200_000` (conservative; only hit outside NixOS).
|
|
#[must_use]
|
|
pub fn context_window_tokens(model: &str) -> u64 {
|
|
let m = model.to_ascii_lowercase();
|
|
// Per-model env vars set by `hyperhive.contextWindowTokens` in Nix.
|
|
for (key, val) in std::env::vars() {
|
|
if let Some(suffix) = key.strip_prefix("HIVE_CONTEXT_WINDOW_TOKENS_")
|
|
&& !suffix.is_empty()
|
|
&& m.contains(&suffix.to_ascii_lowercase())
|
|
&& let Ok(v) = val.trim().parse::<u64>()
|
|
&& v > 0
|
|
{
|
|
return v;
|
|
}
|
|
}
|
|
// Global override (single value, any model).
|
|
if let Ok(s) = std::env::var("HIVE_CONTEXT_WINDOW_TOKENS")
|
|
&& let Ok(v) = s.trim().parse::<u64>()
|
|
&& v > 0
|
|
{
|
|
return v;
|
|
}
|
|
// Hard fallback for dev/test outside NixOS where env vars aren't set.
|
|
200_000
|
|
}
|
|
|
|
#[cfg(test)]
|
|
mod tests {
|
|
use super::{DEFAULT_EFFORT, EFFORT_LEVELS, is_valid_effort};
|
|
|
|
#[test]
|
|
fn effort_validation_accepts_only_known_levels() {
|
|
for level in EFFORT_LEVELS {
|
|
assert!(is_valid_effort(level), "{level} should be valid");
|
|
}
|
|
// Out-of-set, empty, and wrong-case inputs are rejected so a bad
|
|
// picker POST never reaches `claude --effort`.
|
|
for bad in ["lowest", "", "MEDIUM", "ultra", "high "] {
|
|
assert!(!is_valid_effort(bad), "{bad:?} should be rejected");
|
|
}
|
|
}
|
|
|
|
#[test]
|
|
fn compiled_default_effort_is_selectable() {
|
|
// The fallback must itself be a valid level, and match the value
|
|
// baked into prompts/claude-settings.json.
|
|
assert!(EFFORT_LEVELS.contains(&DEFAULT_EFFORT));
|
|
assert_eq!(DEFAULT_EFFORT, "medium");
|
|
}
|
|
}
|