Watch
0
0
Fork
You've already forked hyperhive
0

swarm: show each agent's effective model and effort, and where they came from

Each agent now reports the model and effort it runs on, and where each
comes from (`swarm`, `agent_nix`, `local_file` or `default`), in its
turn-state header on `$SWARM.agent-state.<agent>`: `effort`,
`model_source` and `effort_source` join `model`. The shared
`swarm_queue_client::agent_inference::{Effective, Source}` types spell
those fields for both ends.

The Bus keeps a source next to the model and effort. `Bus::new` takes it
from the local fallback chain (`harness_state::local_model` /
`local_effort`, which now return the source with the value), a `/model`
or `/effort` pick sets `local_file`, and the swarm poller sets `swarm`
or, on a clear, the local chain's source. A swarm value equal to the one
the agent already runs is now applied once, so the source moves to
`swarm` and the header is republished; before, `next()` skipped it as
unchanged.

swarm-controller subscribes to every agent's header with the reader
grant it already holds for the state relay, and keeps the latest
inference fields per agent in memory (`inference::Reported`).
`GET /api/agents/{name}/inference` now answers
`{configured, effective}`, `effective` being `null` until the agent's
first header with these fields since the controller started.
`swarmctl agent inference get` prints both; `set` reads `configured`.

Refs #5034
This commit is contained in:
atlas 2026-10-10 00:00:25 +02:00 • committed by mara
commit d723fac0be
20 changed files with 655 additions and 113 deletions

View file

@ -14,6 +14,9 @@
//! [`crate::harness_state::local_effort`]). A field that was set and then
//! cleared goes back to that local value, read again at that moment.
//!
//! Each value is applied with its [`Source`], which the agent's turn-state
//! header (`crate::swarm_agent_state`) carries to the swarm.
//!
//! A failed read changes nothing. Until the first successful read after a
//! start, the agent runs on its local values.
//!
@ -21,7 +24,7 @@
use std::time::Duration;
use swarm_queue_client::agent_inference::{AgentInference, Effort, Read, read_own};
use swarm_queue_client::agent_inference::{AgentInference, Effort, Read, Source, read_own};
use crate::events::Bus;
use crate::harness_state::{configured_effort, configured_model, local_effort, local_model};
@ -32,12 +35,12 @@ const POLL_INTERVAL: Duration = Duration::from_secs(10);
/// Where the settings are applied, and where the local values come from.
trait Target {
fn model(&self) -> String;
fn effort(&self) -> String;
fn apply_model(&self, value: String);
fn apply_effort(&self, value: String);
fn local_model(&self) -> String;
fn local_effort(&self) -> String;
fn model(&self) -> (String, Source);
fn effort(&self) -> (String, Source);
fn apply_model(&self, value: String, source: Source);
fn apply_effort(&self, value: String, source: Source);
fn local_model(&self) -> (String, Source);
fn local_effort(&self) -> (String, Source);
}
/// The harness's Bus, with the nix values read once at start.
@ -48,22 +51,22 @@ struct Harness {
}
impl Target for Harness {
fn model(&self) -> String {
self.bus.model()
fn model(&self) -> (String, Source) {
(self.bus.model(), self.bus.model_source())
}
fn effort(&self) -> String {
self.bus.effort()
fn effort(&self) -> (String, Source) {
(self.bus.effort(), self.bus.effort_source())
}
fn apply_model(&self, value: String) {
self.bus.apply_model(value);
fn apply_model(&self, value: String, source: Source) {
self.bus.apply_model(value, source);
}
fn apply_effort(&self, value: String) {
self.bus.apply_effort(value);
fn apply_effort(&self, value: String, source: Source) {
self.bus.apply_effort(value, source);
}
fn local_model(&self) -> String {
fn local_model(&self) -> (String, Source) {
local_model(self.nix_model)
}
fn local_effort(&self) -> String {
fn local_effort(&self) -> (String, Source) {
local_effort(self.nix_effort)
}
}
@ -75,46 +78,47 @@ struct Overridden {
effort: bool,
}
/// What one field should become: the swarm's value while it sets one, the
/// local value on the read after it stops, and otherwise `None` (left alone).
/// Also `None` when the value is already what it should be.
/// What one field and its source should become: the swarm's value while it
/// sets one, the local value on the read after it stops, and otherwise
/// `None` (left alone). Also `None` when both are already what they should
/// be; a swarm value equal to the current one still changes the source.
fn next(
swarm: Option<&str>,
overridden: &mut bool,
current: &str,
local: impl FnOnce() -> String,
) -> Option<String> {
current: &(String, Source),
local: impl FnOnce() -> (String, Source),
) -> Option<(String, Source)> {
let wanted = match swarm {
Some(value) => {
*overridden = true;
value.to_owned()
(value.to_owned(), Source::Swarm)
}
None if std::mem::take(overridden) => local(),
None => return None,
};
(wanted != current).then_some(wanted)
(wanted != *current).then_some(wanted)
}
impl Overridden {
/// Apply one read of the key to `target`.
fn apply(&mut self, read: &AgentInference, target: &impl Target) {
if let Some(model) = next(
if let Some((model, source)) = next(
read.model.as_deref(),
&mut self.model,
&target.model(),
|| target.local_model(),
) {
tracing::info!(%model, swarm = self.model, "inference: switching model");
target.apply_model(model);
tracing::info!(%model, ?source, "inference: switching model");
target.apply_model(model, source);
}
if let Some(effort) = next(
if let Some((effort, source)) = next(
read.effort.map(Effort::as_str),
&mut self.effort,
&target.effort(),
|| target.local_effort(),
) {
tracing::info!(%effort, swarm = self.effort, "inference: switching effort");
target.apply_effort(effort);
tracing::info!(%effort, ?source, "inference: switching effort");
target.apply_effort(effort, source);
}
}
}
@ -166,10 +170,12 @@ mod tests {
use super::*;
/// A Bus stand-in recording every apply.
/// A Bus stand-in recording every apply. Starts on its local values:
/// the model from agent.nix, the effort from the file.
struct Fake {
model: RefCell<String>,
effort: RefCell<String>,
sources: RefCell<(Source, Source)>,
local_model: RefCell<String>,
local_effort: String,
applies: RefCell<usize>,
@ -180,6 +186,7 @@ mod tests {
Self {
model: RefCell::new("sonnet".to_owned()),
effort: RefCell::new("medium".to_owned()),
sources: RefCell::new((Source::AgentNix, Source::LocalFile)),
local_model: RefCell::new("sonnet".to_owned()),
local_effort: "medium".to_owned(),
applies: RefCell::new(0),
@ -191,25 +198,27 @@ mod tests {
}
impl Target for Fake {
fn model(&self) -> String {
self.model.borrow().clone()
fn model(&self) -> (String, Source) {
(self.model.borrow().clone(), self.sources.borrow().0)
}
fn effort(&self) -> String {
self.effort.borrow().clone()
fn effort(&self) -> (String, Source) {
(self.effort.borrow().clone(), self.sources.borrow().1)
}
fn apply_model(&self, value: String) {
fn apply_model(&self, value: String, source: Source) {
*self.applies.borrow_mut() += 1;
*self.model.borrow_mut() = value;
self.sources.borrow_mut().0 = source;
}
fn apply_effort(&self, value: String) {
fn apply_effort(&self, value: String, source: Source) {
*self.applies.borrow_mut() += 1;
*self.effort.borrow_mut() = value;
self.sources.borrow_mut().1 = source;
}
fn local_model(&self) -> String {
self.local_model.borrow().clone()
fn local_model(&self) -> (String, Source) {
(self.local_model.borrow().clone(), Source::AgentNix)
}
fn local_effort(&self) -> String {
self.local_effort.clone()
fn local_effort(&self) -> (String, Source) {
(self.local_effort.clone(), Source::LocalFile)
}
}
@ -279,6 +288,34 @@ mod tests {
assert_eq!(fake.now(), pair("sonnet", "medium"));
}
/// A swarm value equal to what the agent runs is still applied once, so
/// the source moves to the swarm and the header is republished.
#[test]
fn a_swarm_value_equal_to_the_current_one_is_applied_once() {
let fake = Fake::new();
let mut o = Overridden::default();
o.apply(&set(Some("sonnet"), Some(Effort::Medium)), &fake);
assert_eq!(fake.now(), pair("sonnet", "medium"));
assert_eq!(*fake.applies.borrow(), 2);
o.apply(&set(Some("sonnet"), Some(Effort::Medium)), &fake);
assert_eq!(*fake.applies.borrow(), 2);
}
#[test]
fn the_source_follows_the_swarm_value() {
let fake = Fake::new();
let mut o = Overridden::default();
o.apply(&set(Some("opus"), Some(Effort::High)), &fake);
assert_eq!(*fake.sources.borrow(), (Source::Swarm, Source::Swarm));
o.apply(&set(None, Some(Effort::High)), &fake);
assert_eq!(*fake.sources.borrow(), (Source::AgentNix, Source::Swarm));
o.apply(&AgentInference::default(), &fake);
assert_eq!(
*fake.sources.borrow(),
(Source::AgentNix, Source::LocalFile)
);
}
/// On the real Bus: the swarm's value reaches the Bus but not the
/// persisted files, so clearing it, or a restart, finds the local value.
#[test]
@ -298,12 +335,14 @@ mod tests {
let mut o = Overridden::default();
o.apply(&set(Some("opus"), Some(Effort::Max)), &target);
let swarm = (bus.model(), bus.effort());
let swarm_sources = (bus.model_source(), bus.effort_source());
let files = (
crate::harness_state::load_model(),
crate::harness_state::load_effort(),
);
o.apply(&AgentInference::default(), &target);
let cleared = (bus.model(), bus.effort());
let cleared_sources = (bus.model_source(), bus.effort_source());
match prev {
// SAFETY: as above.
Some(v) => unsafe { std::env::set_var("HYPERHIVE_HARNESS_DIR", v) },
@ -312,5 +351,7 @@ mod tests {
assert_eq!(swarm, pair("opus", "max"));
assert_eq!(files, (Some("sonnet".to_owned()), Some("low".to_owned())));
assert_eq!(cleared, pair("sonnet", "low"));
assert_eq!(swarm_sources, (Source::Swarm, Source::Swarm));
assert_eq!(cleared_sources, (Source::LocalFile, Source::LocalFile));
}
}