Files
chanora/crates/chanora_audio/examples/compare_baseline.rs
EdisonJwa 7188a5a69d feat(perf,benchmark-infra): criterion bench harness + advisory CI workflows (SDD-120)
Implementation of SDD-120 §1-§8:

Bench harness (crates/chanora_audio/benches/):
- common.rs: deterministic synthetic audio (440 Hz sine, no RNG).
- realtime_capture.rs: bench_capture_alloc_count (dhat) +
  bench_capture_callback_wall_clock (criterion).
- opus_codec.rs: bench_opus_encode_latency + bench_opus_decode_latency
  (direct audiopus, not AudioHandler — SDD-120 §3 item 4).
- resampler.rs: bench_resampler_throughput across 44.1->48 /
  16->48 / 48->48 passthrough.

CI tooling (crates/chanora_audio/examples/):
- emit_baseline.rs: aggregates criterion estimates.json outputs
  into the SRS-217 baseline schema.
- compare_baseline.rs: applies SRS-219 tolerance, renders markdown
  table with 🟢/🟡/🔴 markers + yellow simpler-form realization per
  SDD-120 §8.

  Deviation from SDD-120 §2 / §5 / §7 placement: these tools live
  under examples/, not benches/ or src/bin/. Rationale: they must
  consume serde_json (a dev-only dep — production builds must not
  pull it). Cargo only resolves dev-dependencies for [[test]],
  [[bench]], and [[example]] targets; [[bin]] targets under
  src/bin/ see only regular [dependencies]. examples/ keeps the
  binaries out of the production dep tree while still giving them
  cargo run --example invocation. An SDD-120 amendment should
  reflect this.

Workflows (.github/workflows/):
- bench-advisory.yml: PR + push triggers; runs benches; posts a
  sticky PR comment via actions/github-script@v7; job status is
  always success (SRS-218 clause 4 — non-blocking).
- bench-baseline-update.yml: workflow_dispatch only; runs benches;
  opens PR via peter-evans/create-pull-request@v6 (sole writer of
  the SAD-089 baseline JSON).

Cargo.toml additions ([dev-dependencies] only — verified excluded
from --release builds): criterion 0.5, dhat 0.3, serde_json 1.

Source-code seam: minimal pub-but-#[doc(hidden)] bench_seam module
in chanora_audio (engine.rs + lib.rs re-export) so the criterion
bench harness can construct a CaptureState and drive
CaptureState::ingest without re-implementing the engine (SDD-120
§3). Non-iOS targets only — CaptureState itself is iOS-gated.

Initial baseline seed: crates/chanora_audio/benches/baselines/
x86_64-unknown-linux-gnu.json = {}. compare_baseline handles the
missing-baseline case gracefully and emits a 'no red markers'
report; the first manual dispatch of bench-baseline-update.yml
after merge establishes the real values.

Out of scope per SDD-120 §10: production telemetry export,
build-failing hard CI gate, multi-host benchmarking, IDE
integration, Dart-side bridge round-trip bench.

Verification:
- cargo check --workspace --all-targets: PASS.
- cargo bench --bench realtime_capture --no-run: PASS.
- cargo bench --bench opus_codec --no-run: PASS.
- cargo bench --bench resampler --no-run: PASS.
- cargo build --example emit_baseline --example compare_baseline
  -p chanora_audio: PASS.
- cargo test --workspace: 106 passed, 0 failed, 3 ignored — no
  regression from prior count.
2026-05-18 13:52:15 +08:00

241 lines
7.3 KiB
Rust

// SDD-120 §8 — PR-vs-baseline comparator binary.
//
// Reads `current.json` (from §5 emit_baseline) and `baseline.json`
// (extracted from the SAD-089 path at the merge-base by the §6
// workflow) and emits a markdown report applying:
//
// - Zero-tolerance metrics (SRS-219 clause a — capture_alloc_count):
// 🔴 if c != 0 else 🟢. Yellow does not apply.
// - Otherwise (t > 0):
// delta_pct = (c - b) / b (or 0 if b == 0)
// 🔴 if delta_pct > t
// 🟡 if 0.5*t < delta_pct ≤ t
// 🟢 otherwise (including improvements, delta_pct < 0)
//
// Always exits 0 — regression detection is rendered as a 🔴 marker
// inside the markdown comment, NOT as a non-zero exit code
// (SRS-218 clause 4).
//
// CLI:
// cargo run --bin compare_baseline -- \
// --current ./current.json \
// --baseline ./baseline.json \
// --output ./report.md
use std::collections::HashMap;
use std::fs;
use std::path::PathBuf;
use std::process::ExitCode;
use serde_json::Value;
struct Args {
current: PathBuf,
baseline: PathBuf,
output: PathBuf,
}
fn parse_args() -> Args {
let mut current = PathBuf::from("current.json");
let mut baseline = PathBuf::from("baseline.json");
let mut output = PathBuf::from("report.md");
let mut it = std::env::args().skip(1);
while let Some(a) = it.next() {
match a.as_str() {
"--current" => current = PathBuf::from(it.next().unwrap_or_default()),
"--baseline" => baseline = PathBuf::from(it.next().unwrap_or_default()),
"--output" => output = PathBuf::from(it.next().unwrap_or_default()),
_ => {}
}
}
Args {
current,
baseline,
output,
}
}
fn read_metrics(path: &PathBuf) -> (Option<Value>, HashMap<String, MetricRow>) {
let mut out = HashMap::new();
let text = match fs::read_to_string(path) {
Ok(t) => t,
Err(_) => return (None, out),
};
if text.trim().is_empty() || text.trim() == "{}" {
return (None, out);
}
let v: Value = match serde_json::from_str(&text) {
Ok(v) => v,
Err(_) => return (None, out),
};
let metrics = v.get("metrics").and_then(|m| m.as_array()).cloned();
if let Some(arr) = metrics {
for m in arr {
let name = m
.get("metric")
.and_then(|s| s.as_str())
.unwrap_or("")
.to_string();
let unit = m
.get("unit")
.and_then(|s| s.as_str())
.unwrap_or("")
.to_string();
let value = m.get("value").and_then(|n| n.as_f64());
let tolerance = m
.get("tolerance_pct")
.and_then(|n| n.as_f64())
.unwrap_or(0.0);
if !name.is_empty() {
out.insert(
name.clone(),
MetricRow {
metric: name,
unit,
value,
tolerance_pct: tolerance,
},
);
}
}
}
(Some(v), out)
}
#[derive(Clone)]
struct MetricRow {
metric: String,
unit: String,
value: Option<f64>,
tolerance_pct: f64,
}
fn fmt_value(v: Option<f64>) -> String {
match v {
Some(x) if x.is_finite() => {
if x.abs() >= 1_000_000.0 {
format!("{:.3e}", x)
} else if x.abs() >= 1.0 {
format!("{:.3}", x)
} else {
format!("{:.6}", x)
}
}
_ => "n/a".to_string(),
}
}
fn marker(b: Option<f64>, c: Option<f64>, t: f64) -> (String, String) {
// Returns (marker, delta_str)
let (b, c) = match (b, c) {
(Some(b), Some(c)) => (b, c),
_ => return ("⚪".to_string(), "n/a".to_string()),
};
if t == 0.0 {
// Zero-tolerance metric (SRS-219 clause a).
if c != 0.0 {
return ("🔴".to_string(), format!("{:+}", c as i64));
} else {
return ("🟢".to_string(), "+0".to_string());
}
}
let delta_pct = if b > 0.0 { (c - b) / b } else { 0.0 };
let delta_str = format!("{:+.2}%", delta_pct * 100.0);
let m = if delta_pct > t {
"🔴"
} else if delta_pct > 0.5 * t {
"🟡"
} else {
"🟢"
};
(m.to_string(), delta_str)
}
fn main() -> ExitCode {
let args = parse_args();
let (cur_doc, cur) = read_metrics(&args.current);
let (base_doc, base) = read_metrics(&args.baseline);
let mut md = String::new();
md.push_str("<!-- chanora-bench-advisory -->\n");
md.push_str("### Chanora realtime-audio benchmark advisory (SDD-120)\n\n");
if cur_doc.is_none() {
md.push_str("_No `current.json` found — bench harness did not produce results._\n");
fs::write(&args.output, &md).expect("write report");
return ExitCode::SUCCESS;
}
if base.is_empty() {
md.push_str(
"_Baseline not yet established at merge-base; first dispatch of \
`bench-baseline-update.yml` on the default branch will establish \
it. No red markers emitted on this first run._\n\n",
);
md.push_str("| Metric | Unit | Current |\n");
md.push_str("|---|---|---|\n");
let mut keys: Vec<&String> = cur.keys().collect();
keys.sort();
for k in keys {
let row = &cur[k];
md.push_str(&format!(
"| `{}` | {} | {} |\n",
row.metric,
row.unit,
fmt_value(row.value)
));
}
fs::write(&args.output, &md).expect("write report");
return ExitCode::SUCCESS;
}
if let Some(d) = base_doc.as_ref() {
if let Some(sha) = d.get("git_sha").and_then(|s| s.as_str()) {
md.push_str(&format!("Baseline `git_sha`: `{}`\n\n", sha));
}
}
md.push_str("| Metric | Unit | Baseline | Current | Δ | Tolerance | Status |\n");
md.push_str("|---|---|---|---|---|---|---|\n");
// Iterate over the union of metric names, sorted.
let mut all: Vec<String> = cur.keys().chain(base.keys()).cloned().collect();
all.sort();
all.dedup();
for name in all {
let c = cur.get(&name);
let b = base.get(&name);
let unit = c
.map(|r| r.unit.clone())
.or_else(|| b.map(|r| r.unit.clone()))
.unwrap_or_default();
let tol = c
.map(|r| r.tolerance_pct)
.or_else(|| b.map(|r| r.tolerance_pct))
.unwrap_or(0.0);
let (m, delta) = marker(b.and_then(|r| r.value), c.and_then(|r| r.value), tol);
md.push_str(&format!(
"| `{}` | {} | {} | {} | {} | {} | {} |\n",
name,
unit,
fmt_value(b.and_then(|r| r.value)),
fmt_value(c.and_then(|r| r.value)),
delta,
if tol == 0.0 {
"0 (zero-tolerance)".to_string()
} else {
format!("{:.1}%", tol * 100.0)
},
m,
));
}
md.push_str(
"\n_Advisory only — this workflow never fails a check on regression \
(SRS-218 clause 4)._\n",
);
fs::write(&args.output, &md).expect("write report");
ExitCode::SUCCESS
}