Merge audit-2026-05-fix/oracle-sylpheed-n50m-n4b: ORACBUG-004 sylpheed_n50m oracle

This commit is contained in:
MechaCat02
2026-05-03 13:46:06 +02:00
4 changed files with 214 additions and 2 deletions

View File

@@ -226,6 +226,13 @@ enum Commands {
/// Optional golden digest JSON; `check` exits non-zero on mismatch
#[arg(long)]
expect: Option<String>,
/// Emit/compare only stable fields (excludes timing-sensitive counters
/// like `packets`, `interrupts_delivered`, `resolves`). Required for any
/// golden captured under `--parallel`; recommended for lockstep goldens
/// at -n ≥50M because `packets` has empirical ±28% jitter from a GPU
/// thread race.
#[arg(long)]
stable_digest: bool,
/// Force the threaded GPU backend (default at M1.9).
#[arg(long)]
gpu_thread: bool,
@@ -324,6 +331,7 @@ fn main() -> Result<()> {
max_instructions,
out,
expect,
stable_digest,
gpu_thread,
gpu_inline,
reservations_table,
@@ -333,6 +341,7 @@ fn main() -> Result<()> {
max_instructions,
out.as_deref(),
expect.as_deref(),
stable_digest,
gpu_thread,
gpu_inline,
reservations_table,
@@ -528,6 +537,7 @@ fn cmd_exec(
parallel,
None,
None,
false,
)
}
@@ -538,6 +548,7 @@ fn cmd_check(
max_instructions: u64,
out: Option<&str>,
expect: Option<&str>,
stable_digest: bool,
gpu_thread: bool,
gpu_inline: bool,
reservations_table: bool,
@@ -561,6 +572,7 @@ fn cmd_check(
parallel,
out,
expect,
stable_digest,
)
}
@@ -582,6 +594,7 @@ fn cmd_exec_inner(
parallel: bool,
digest_out: Option<&str>,
digest_expect: Option<&str>,
stable_digest: bool,
) -> Result<()> {
let started = Instant::now();
let data = load_xex_data(path)?;
@@ -1190,10 +1203,14 @@ fn cmd_exec_inner(
// catch any drift between runs.
if digest_out.is_some() || digest_expect.is_some() {
let digest = RunDigest::capture(path, &kernel, &stats);
let json = digest.to_json();
let json = if stable_digest {
digest.stable_fields_json()
} else {
digest.to_json()
};
if let Some(out_path) = digest_out {
std::fs::write(out_path, &json)?;
info!(out = out_path, "run digest written");
info!(out = out_path, stable = stable_digest, "run digest written");
} else {
println!("{json}");
}
@@ -1340,6 +1357,34 @@ impl RunDigest {
self.texture_decodes,
)
}
/// Stable-fields-only digest for goldens that need to survive non-determinism.
/// Excludes timing-sensitive counters: `packets` has documented ±2.58% lockstep
/// noise from a GPU thread race; `resolves`, `interrupts_delivered`,
/// `interrupts_dropped`, and `texture_decodes` are scheduling-sensitive under
/// `--parallel`. Also omits `path` (cwd-dependent). The remaining fields are
/// deterministic in lockstep at a fixed instruction budget. Use via
/// `--stable-digest`.
fn stable_fields_json(&self) -> String {
format!(
"{{\n \"instructions\": {},\n \
\"imports\": {},\n \
\"unimpl\": {},\n \
\"draws\": {},\n \
\"swaps\": {},\n \
\"unique_render_targets\": {},\n \
\"shader_blobs_live\": {},\n \
\"texture_cache_entries\": {}\n}}\n",
self.instructions,
self.imports,
self.unimpl,
self.draws,
self.swaps,
self.unique_render_targets,
self.shader_blobs_live,
self.texture_cache_entries,
)
}
}
fn escape_json_string(s: &str) -> String {

View File

@@ -0,0 +1,72 @@
# Sylpheed regression goldens
These JSON files anchor `xenia-rs check` digest output for Project Sylpheed.
## Files
| File | -n | Mode | Captures |
|------|----|------|----------|
| `sylpheed_n2m.json` | 2_000_000 | full digest | early boot (swaps=0, no rendering) |
| `sylpheed_n50m.json` | 50_000_000 | stable-digest | first VdSwap pair (swaps=2 post-Phase-A) |
## Stable-digest mode
`sylpheed_n50m.json` is captured with `--stable-digest`, which omits
timing-sensitive counters: `packets` (±28% lockstep noise from a GPU thread
race), `resolves`, `interrupts_delivered`, `interrupts_dropped`,
`texture_decodes`. The remaining fields are byte-identical across repeated
lockstep runs at a fixed -n.
`sylpheed_n2m.json` predates the stable-digest flag and uses full-digest
compare. It still works because at -n 2M the GPU pipeline has not produced any
packets yet — `packets=0` is trivially deterministic.
## Circularity hazard
Per ORACBUG-001/002/003, these goldens were captured by running the same code
they validate. They detect **regression** from a known-good snapshot, not
**correctness**. When a planned fix intentionally moves the digest (e.g. a
shader fix landing `draws > 0` for the first time), re-baseline the golden as
a separate commit and reference the audit ID in the message.
## Re-baselining
```sh
cargo build --release -p xenia-app
target/release/xenia-rs check \
"$SYLPHEED_ISO" \
-n 50000000 \
--stable-digest \
--out crates/xenia-app/tests/golden/sylpheed_n50m.json
```
## Running the goldens
```sh
cargo test --release -p xenia-app --test sylpheed_oracles -- --ignored --nocapture
```
The tests are `#[ignore]`-gated because each run takes a few seconds, which is
unacceptable in the default `cargo test` cycle. The ISO path defaults to the
contributor's local `~/RE Project Sylpheed/Project Sylpheed*.iso` and can be
overridden via `SYLPHEED_ISO=/path/to/sylpheed.iso`.
## n4b canonical-invocation regression anchor (deferred)
The audit's recommended next sprint also called for a `sylpheed_n4b.json`
golden capturing the canonical reference invocation
`xenia-rs check sylpheed.iso -n 4_000_000_000 --parallel --reservations-table`.
This is **deferred** because:
1. The `--parallel --reservations-table` combination is empirically pathologically
slow at -n 100M (>32 min per run per the audit memory). At -n 4B the run cost
is many hours, not the single-session-friendly 515 min the original plan
estimated.
2. Each phase that intentionally moves rendering counters (C, D, E, F) would
need a re-baseline of n4b — a significant time cost compounding over the
sprint.
Once the renderer-unblock phases (C+D+E) land and `draws > 0` is confirmed at
-n 100M lockstep, an n4b artifact may be captured one-shot and stored under
`audit-runs/post-fix/` (not as a test golden) as a manual regression anchor for
the canonical invocation.

View File

@@ -0,0 +1,10 @@
{
"instructions": 50000008,
"imports": 407415,
"unimpl": 0,
"draws": 0,
"swaps": 2,
"unique_render_targets": 0,
"shader_blobs_live": 0,
"texture_cache_entries": 0
}

View File

@@ -0,0 +1,85 @@
//! Sylpheed boot-sequence regression oracles.
//!
//! These goldens trigger `xenia-rs check` against the Project Sylpheed ISO and
//! compare the resulting digest to a checked-in JSON file via `--stable-digest`,
//! which excludes timing-sensitive counters (`packets`, `interrupts_*`,
//! `resolves`, `texture_decodes`). The remaining fields are deterministic in
//! lockstep at a fixed instruction budget — verified empirically across 3
//! consecutive runs.
//!
//! Goldens are CIRCULAR per ORACBUG-001/002/003: they were captured by running
//! the same code they validate. Treat them as **regression anchors** (catch
//! drift from a known-good snapshot) not **correctness anchors** (no claim
//! about absolute behavior). When a planned fix intentionally moves the
//! digest (e.g. swap fix → `swaps` increments; renderer fix → `draws` becomes
//! non-zero), re-baseline the golden as a separate commit.
//!
//! Tests are `#[ignore]`-gated because the runs take ~4 seconds each, which
//! is unacceptable for the default `cargo test` cycle. Run explicitly:
//! cargo test --release -p xenia-app --test sylpheed_oracles -- --ignored --nocapture
//!
//! ISO path is read from the `SYLPHEED_ISO` env var, falling back to the
//! repo-relative default. CI/contributors without the ISO will see the test
//! skip gracefully.
use std::process::Command;
const ISO_DEFAULT: &str = "/home/fabi/RE Project Sylpheed/Project Sylpheed - Arc of Deception (USA, Europe) (En,Ja).iso";
fn iso_path() -> String {
std::env::var("SYLPHEED_ISO").unwrap_or_else(|_| ISO_DEFAULT.to_string())
}
fn run_oracle(label: &str, max_instr: u64, golden_rel: &str) {
let bin = env!("CARGO_BIN_EXE_xenia-rs");
let iso = iso_path();
if !std::path::Path::new(&iso).exists() {
eprintln!("{label}: iso not found at {iso}; set SYLPHEED_ISO to override. SKIPPING.");
return;
}
// Resolve the golden path relative to the test's CARGO_MANIFEST_DIR so the
// test runs correctly from any cwd.
let manifest_dir = env!("CARGO_MANIFEST_DIR");
let golden = std::path::Path::new(manifest_dir).join(golden_rel);
assert!(
golden.exists(),
"{label}: golden file missing at {}",
golden.display()
);
let max_instr_str = max_instr.to_string();
let golden_str = golden.to_string_lossy().to_string();
let out = Command::new(bin)
.args([
"check",
&iso,
"-n",
&max_instr_str,
"--stable-digest",
"--expect",
&golden_str,
])
.output()
.expect("failed to spawn xenia-rs");
if !out.status.success() {
eprintln!(
"{label}: STDOUT:\n{}\nSTDERR:\n{}",
String::from_utf8_lossy(&out.stdout),
String::from_utf8_lossy(&out.stderr),
);
panic!("{label}: digest mismatch (exit {:?})", out.status.code());
}
}
/// Sylpheed boot to first VdSwap pair, captured at -n 50M lockstep.
/// Catches regressions in: addi/addic semantics, kernel HLE for VdSwap path,
/// thread spawning, file I/O for sound/config. With Phase A's swap fix landed,
/// `swaps` should be 2 and `draws` 0 (Phase E gates draws>0).
#[test]
#[ignore = "long-running; run via `cargo test ... -- --ignored sylpheed_n50m`"]
fn sylpheed_n50m() {
run_oracle("sylpheed_n50m", 50_000_000, "tests/golden/sylpheed_n50m.json");
}