vinzenz/hyperhive
vinzenz/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Activity

review classifier: commit shas and index lines stay out of the prompt

Browse source 
Every classification's shared context began with the PR's head sha,
headed each commit with its sha, and carried each file's
`index <hash>..<hash>` line in the diff. A push or rebase rewrites all
of those, so the provider's prompt cache missed from the first line of
the user message even when the commit messages and hunks were
unchanged (#5245: "cache hits show as 0.1x").

The header now names only repo#pr, each commit is headed by its
position, and the diff drops `index` lines before lockfiles collapse.
The `diff --git` paths and every hunk stay. The TryOut's head_sha is
untouched: the controller still posts the review against it, and the
journal line still logs it.

On the ACP runtime the cost sink also adds each classification's tokens
to `hyperhive.review_classifier.token.usage`, typed input / output /
cacheRead / cacheCreation like claude's own `claude_code.token.usage`,
so the hit rate is a number in the metrics store on both runtimes.
This commit is contained in:
atlas 2026-10-14 10:43:41 +02:00 • committed by mara
commit 74b63dd031
4 changed files with 190 additions and 35 deletions
Download patch file Download diff file Expand all files Collapse all files

137
swarm-review-classifier/src/cost.rs
View file

@ -1,6 +1,11 @@
//! What a classification on the ACP runtime cost, exported as the counter
//! `hyperhive.review_classifier.cost.usage` with the run's `repo`, `pr`,
//! `model` and `currency`. On the claude runtime `claude` exports its own.
//! `model` and `currency`, and the tokens it used, as the counter
//! `hyperhive.review_classifier.token.usage` with the same labels bar
//! `currency` and a `type` of `input`, `output`, `cacheRead` or
//! `cacheCreation`. Those are `claude_code.token.usage`'s types, which
//! `claude` exports for itself on the claude runtime, so the cache hit rate is
//! `cacheRead` over the three input types on either runtime.
//!
//! The amount is computed here from the prices the run carries and the
//! tokens the agent reports, so it does not depend on how, or whether, the
@ -26,7 +31,7 @@ pub const CURRENCY: &str = "USD";
/// How often the counter is exported.
const INTERVAL: Duration = Duration::from_mins(1);
/// One classification's cost, and what it is labelled with.
/// One classification's cost and tokens, and what they are labelled with.
#[derive(Debug, Clone, PartialEq)]
pub struct Cost {
pub repo: String,
@ -34,6 +39,7 @@ pub struct Cost {
pub model: String,
/// In [`CURRENCY`].
pub amount: f64,
pub usage: TokenUsage,
}
/// Where a classification's cost goes: the metrics store in production, a
@ -57,43 +63,67 @@ pub fn amount(prices: &Prices, usage: &TokenUsage) -> f64 {
* per_token(prices.cache_write.unwrap_or(prices.input))
}
/// The counter in the metrics store.
/// The counters in the metrics store.
pub struct Otel;
impl CostSink for Otel {
fn record(&self, cost: &Cost) {
static COUNTER: OnceLock<Option<(SdkMeterProvider, Counter<f64>)>> = OnceLock::new();
let Some((_, counter)) = COUNTER.get_or_init(build) else {
static COUNTERS: OnceLock<Option<(SdkMeterProvider, Counters)>> = OnceLock::new();
let Some((_, counters)) = COUNTERS.get_or_init(build) else {
return;
};
add(counter, cost);
add(counters, cost);
}
}
/// The counter on `provider`.
fn cost_counter(provider: &SdkMeterProvider) -> Counter<f64> {
provider
.meter("hyperhive.review_classifier")
.f64_counter("hyperhive.review_classifier.cost.usage")
.build()
/// The cost counter, and the token counter beside it.
struct Counters {
cost: Counter<f64>,
tokens: Counter<u64>,
}
/// Adds `cost` to `counter` with the run's labels.
fn add(counter: &Counter<f64>, cost: &Cost) {
counter.add(
cost.amount,
&[
KeyValue::new("repo", cost.repo.clone()),
KeyValue::new("pr", i64::try_from(cost.pr).unwrap_or(i64::MAX)),
KeyValue::new("model", cost.model.clone()),
KeyValue::new("currency", CURRENCY),
],
);
/// The counters on `provider`.
fn counters(provider: &SdkMeterProvider) -> Counters {
let meter = provider.meter("hyperhive.review_classifier");
Counters {
cost: meter
.f64_counter("hyperhive.review_classifier.cost.usage")
.build(),
tokens: meter
.u64_counter("hyperhive.review_classifier.token.usage")
.build(),
}
}
/// The provider, kept alive with the counter since it exports only while it
/// Adds `cost` to `counters` with the run's labels.
fn add(counters: &Counters, cost: &Cost) {
let labels = [
KeyValue::new("repo", cost.repo.clone()),
KeyValue::new("pr", i64::try_from(cost.pr).unwrap_or(i64::MAX)),
KeyValue::new("model", cost.model.clone()),
];
let with = |extra: KeyValue| {
let mut all = labels.to_vec();
all.push(extra);
all
};
counters
.cost
.add(cost.amount, &with(KeyValue::new("currency", CURRENCY)));
let usage = &cost.usage;
for (kind, n) in [
("input", usage.input_tokens),
("output", usage.output_tokens),
("cacheRead", usage.cache_read_input_tokens),
("cacheCreation", usage.cache_creation_input_tokens),
] {
counters.tokens.add(n, &with(KeyValue::new("type", kind)));
}
}
/// The provider, kept alive with the counters since it exports only while it
/// lives, or `None` when no collector is configured or the exporter failed.
fn build() -> Option<(SdkMeterProvider, Counter<f64>)> {
fn build() -> Option<(SdkMeterProvider, Counters)> {
if !std::env::var("OTEL_EXPORTER_OTLP_ENDPOINT").is_ok_and(|s| !s.trim().is_empty()) {
return None;
}
@ -114,8 +144,8 @@ fn build() -> Option<(SdkMeterProvider, Counter<f64>)> {
.with_interval(INTERVAL)
.build();
let provider = SdkMeterProvider::builder().with_reader(reader).build();
let counter = cost_counter(&provider);
Some((provider, counter))
let counters = counters(&provider);
Some((provider, counters))
}
#[cfg(test)]
@ -168,7 +198,7 @@ mod tests {
let exporter = InMemoryMetricExporter::default();
let reader = PeriodicReader::builder(exporter.clone()).build();
let provider = SdkMeterProvider::builder().with_reader(reader).build();
let counter = cost_counter(&provider);
let counters = counters(&provider);
let prices = Prices {
input: 3.0,
output: 15.0,
@ -180,8 +210,9 @@ mod tests {
pr: 5214,
model: "some-model".to_owned(),
amount: amount(&prices, &usage(1_000_000, 100_000, 0, 0)),
usage: usage(1_000_000, 100_000, 0, 0),
};
add(&counter, &cost);
add(&counters, &cost);
provider.force_flush().expect("flush");
let metrics = exporter.get_finished_metrics().expect("metrics");
@ -214,4 +245,52 @@ mod tests {
assert_eq!(label("currency"), Some(Value::from("USD")));
assert_eq!(labels.len(), 4);
}
#[test]
fn a_record_adds_each_token_class_under_its_type() {
let exporter = InMemoryMetricExporter::default();
let reader = PeriodicReader::builder(exporter.clone()).build();
let provider = SdkMeterProvider::builder().with_reader(reader).build();
let cost = Cost {
repo: "hyperhive/hyperhive".to_owned(),
pr: 5245,
model: "some-model".to_owned(),
amount: 0.0,
usage: usage(100, 20, 9_000, 400),
};
add(&counters(&provider), &cost);
provider.force_flush().expect("flush");
let metrics = exporter.get_finished_metrics().expect("metrics");
let metric = metrics
.iter()
.flat_map(ResourceMetrics::scope_metrics)
.flat_map(ScopeMetrics::metrics)
.find(|m| m.name() == "hyperhive.review_classifier.token.usage")
.expect("the token counter was exported");
let AggregatedMetrics::U64(MetricData::Sum(sum)) = metric.data() else {
panic!("not a u64 sum: {:?}", metric.data());
};
let mut by_type: Vec<(String, u64, usize)> = sum
.data_points()
.map(|point| {
let kind = point
.attributes()
.find(|kv| kv.key.as_str() == "type")
.map(|kv| kv.value.to_string())
.unwrap_or_default();
(kind, point.value(), point.attributes().count())
})
.collect();
by_type.sort();
assert_eq!(
by_type,
[
("cacheCreation".to_owned(), 400, 4),
("cacheRead".to_owned(), 9_000, 4),
("input".to_owned(), 100, 4),
("output".to_owned(), 20, 4),
]
);
}
}