Establish controlled red-suite baseline

README.md

@@ -12,12 +12,13 @@ the main assembly's packet/message/asset/primitive wire-data, core
 runtime/networking, avatar-facing manager, world/social/service manager, RLV,
 LSL tools, Utilities, Vivox, and WebRTC slices now have complete callable,
 failure-only signatures. The independent downstream fixture compiles every
-cataloged type and member with zero exclusions; semantic Rust test translations
-are the next stage.
+cataloged type and member with zero exclusions, and all 1,289 NUnit invocations
+now have reviewed Rust parity cases. Production behavior implementation is the
+next stage.
 
-Pending NUnit cases are inventory only, not generated fake tests. A case counts
-as translated only when an explicit Rust test body calls the mapped API and
-retains the upstream identity and body hash.
+A case counts as translated only when an explicit Rust test body calls the
+mapped API and retains the upstream identity and body hash. The parity ledger
+now contains zero pending or unreviewed cases.
 
 The source snapshot, compatibility rules, dependency research, and ordered
 implementation plan are in [RUSTREWRITE.md](RUSTREWRITE.md).
@@ -37,6 +38,7 @@ cargo test --workspace --no-run
 python3 tools/generate_rust_mapping.py --check
 python3 tools/generate_api_shims.py --check
 python3 tools/check_test_parity.py
+python3 tools/audit_red_suite.py
 ```
 
 `tests/upstream-tests.json` is the machine-readable NUnit parity catalog.
@@ -46,3 +48,5 @@ verifies the catalog against the pinned adjacent LibreMetaverse checkout without
 overwriting those files.
 
 Running `cargo test --workspace` is intentionally red during the shim stage.
+The controlled audit aggregates every expected failure by standardized C#
+member ID and rejects unrelated fixture, assertion, compile, or symbol errors.

RUSTREWRITE.md

@@ -364,6 +364,32 @@ The test-suite gate is complete only when:
 - no production method contains real behavior beyond what is required to make
   signatures and constants compile.
 
+### 3.3 Fixed controlled-red baseline
+
+Milestone 03 closes against the pinned 1,289-invocation catalog, not the older
+1,295 source-text estimate. The six-case difference is intentional: five
+attributes were commented out and one parameterless `[Test]` marker duplicated
+a parameterized `[TestCase]` method. Reintroducing those entries would create
+tests that NUnit never runs.
+
+`tests/red-suite-baseline.json` fixes the machine-checked ledger at 1,266
+ordinary translations, 19 live-grid translations, four benchmarks, and zero
+pending, drifted, duplicate, missing, or unreviewed cases. Run the controlled
+audit with:
+
+```sh
+python3 tools/audit_red_suite.py
+```
+
+With all three live-grid credentials present, the baseline executes every case:
+22 tests pass, 1,287 fail at 131 standardized C# member IDs, and none are
+ignored. Twenty passes are gate/support tests. The only two passing parity cases
+verify the required `BAKED_TEXTURE_COUNT` constant and composable validation
+flags; they do not represent implemented production behavior. Without complete
+credentials, the same audit conditionally ignores exactly the 19 live-grid
+cases and requires the remaining 1,268 parity failures to retain standardized
+member IDs. Production crates remain the failure-only milestone-02 shims.
+
 ## 4. Validated Rust dependency map
 
 Versions below were queried from crates.io on 2026-08-08 with `cargo search`

crates/libremetaverse/src/world_internal_semantics.rs

@@ -77,7 +77,7 @@ fn estate_packet(blocked: &[UUID], trusted: &[UUID], allowed: &[UUID]) -> Estate
     }
 }
 
-fn block_on_with<F: Future>(future: F, mut after_pending: impl FnMut()) -> F::Output {
+fn block_on_with<F: Future>(future: F, mut after_first_poll: impl FnMut()) -> F::Output {
     struct ThreadWake(std::thread::Thread);
     impl Wake for ThreadWake {
         fn wake(self: Arc<Self>) {
@@ -93,7 +93,7 @@ fn block_on_with<F: Future>(future: F, mut after_pending: impl FnMut()) -> F::Ou
             Poll::Ready(value) => return value,
             Poll::Pending if !invoked => {
                 invoked = true;
-                after_pending();
+                after_first_poll();
             }
             Poll::Pending => std::thread::park_timeout(Duration::from_millis(10)),
         }

tests/compat/tests/social_constructor_semantics.rs

@@ -7,14 +7,14 @@ use libremetaverse::{AppearanceManager, AvatarManager, Error};
 // parity-case: LibreMetaverse.Tests/ConstructorNullArgumentTests.cs::ConstructorNullArgumentTests.AppearanceManager_Null_Throws::test a3c872805bc924b5a1a9441d5c9eb61ed6d6e9477e4bb411131359290b144ab4 translated
 #[test]
 fn appearance_manager_null_throws() {
-    assert!(matches!(
-        AppearanceManager::new(None),
-        Err(Error::ArgumentNull)
-    ));
+    assert_eq!(
+        AppearanceManager::new(None).err(),
+        Some(Error::ArgumentNull)
+    );
 }
 
 // parity-case: LibreMetaverse.Tests/ConstructorNullArgumentTests.cs::ConstructorNullArgumentTests.AvatarManager_Null_Throws::test 54f23cbf0ba87b0525c2914e78d75808e93fd1c460fc0bec4d15f09575b1431c translated
 #[test]
 fn avatar_manager_null_throws() {
-    assert!(matches!(AvatarManager::new(None), Err(Error::ArgumentNull)));
+    assert_eq!(AvatarManager::new(None).err(), Some(Error::ArgumentNull));
 }

tests/compat/tests/world_constructor_semantics.rs

@@ -7,17 +7,17 @@ use libremetaverse::{AgentManager, Error, GridManager, ObjectManager};
 // parity-case: LibreMetaverse.Tests/ConstructorNullArgumentTests.cs::ConstructorNullArgumentTests.GridManager_Null_Throws::test e972a95f334b0f46948cda34c27124c28c44faf4372d0e598d7dc60050b49be4 translated
 #[test]
 fn grid_manager_null_throws() {
-    assert!(matches!(GridManager::new(None), Err(Error::ArgumentNull)));
+    assert_eq!(GridManager::new(None).err(), Some(Error::ArgumentNull));
 }
 
 // parity-case: LibreMetaverse.Tests/ConstructorNullArgumentTests.cs::ConstructorNullArgumentTests.ObjectManager_Null_Throws::test 8a11feba0edfb35e5dd99f681182e8f5a5cf8a3f738211b45a683a8a2ad45ddb translated
 #[test]
 fn object_manager_null_throws() {
-    assert!(matches!(ObjectManager::new(None), Err(Error::ArgumentNull)));
+    assert_eq!(ObjectManager::new(None).err(), Some(Error::ArgumentNull));
 }
 
 // parity-case: LibreMetaverse.Tests/ConstructorNullArgumentTests.cs::ConstructorNullArgumentTests.AgentManager_Null_Throws::test d86e41b6cdd03063685aa330c31b9a274c1d400b9a461abf3065fe185fe0bbf0 translated
 #[test]
 fn agent_manager_null_throws() {
-    assert!(matches!(AgentManager::new(None), Err(Error::ArgumentNull)));
+    assert_eq!(AgentManager::new(None).err(), Some(Error::ArgumentNull));
 }

tests/red-suite-baseline.json

@@ -0,0 +1,18 @@
+{
+  "schema_version": 1,
+  "upstream_commit": "2aa70bb68513b39795da5d13c88f31b86e85a3ba",
+  "reviewed_cases": 1289,
+  "parity_report": {
+    "pending": 0,
+    "translated": 1266,
+    "ignored_live": 19,
+    "benchmark": 4,
+    "drifted": 0,
+    "unreviewed": 0
+  },
+  "allowed_parity_passes": [
+    "LibreMetaverse.Tests/AppearanceManagerTests.cs::AppearanceManagerTests.BAKED_TEXTURE_COUNT_Is11::test",
+    "LibreMetaverse.Tests/MarketplaceFolderClassifierTests.cs::MarketplaceFolderClassifierTests.ValidateListing_ValidFlags_AreBitmaskComposable::test"
+  ],
+  "support_passes": 20
+}

tests/upstream-tests.json

@@ -3054,7 +3054,7 @@
       "body_sha256": "e972a95f334b0f46948cda34c27124c28c44faf4372d0e598d7dc60050b49be4",
       "categories": [],
       "fixture_dependencies": [],
-      "rust_body_sha256": "7ced2dbdadce6cc8654767c7f17f491b428f21c3d397f3236fd46e686ca3f219",
+      "rust_body_sha256": "440233e304c7561b384d23798d815d10806cb624558cc847475b2f517b5275c4",
       "status": "translated",
       "rust_file": "tests/compat/tests/world_constructor_semantics.rs",
       "rust_line": 7,
@@ -3092,7 +3092,7 @@
       "body_sha256": "a3c872805bc924b5a1a9441d5c9eb61ed6d6e9477e4bb411131359290b144ab4",
       "categories": [],
       "fixture_dependencies": [],
-      "rust_body_sha256": "5d9e748f126a3ff03db848d71258287441dd520c3f2a5bfadb5921f3e7fba7d0",
+      "rust_body_sha256": "65ab61a0cc83ccef52575370de46c61fa91a93246938d2e7a5df41b2547c6e41",
       "status": "translated",
       "rust_file": "tests/compat/tests/social_constructor_semantics.rs",
       "rust_line": 7,
@@ -3111,7 +3111,7 @@
       "body_sha256": "8a11feba0edfb35e5dd99f681182e8f5a5cf8a3f738211b45a683a8a2ad45ddb",
       "categories": [],
       "fixture_dependencies": [],
-      "rust_body_sha256": "c6849d0a524859f5436a8e0a78a9baf75a761a8edaa801a3eed09c4057c7eb96",
+      "rust_body_sha256": "551175a56c31bfee564b3f408c6a9868d56e0b6763e36cf71c0cf372760ee575",
       "status": "translated",
       "rust_file": "tests/compat/tests/world_constructor_semantics.rs",
       "rust_line": 13,
@@ -3130,7 +3130,7 @@
       "body_sha256": "d86e41b6cdd03063685aa330c31b9a274c1d400b9a461abf3065fe185fe0bbf0",
       "categories": [],
       "fixture_dependencies": [],
-      "rust_body_sha256": "4c6198a60bbdee2fe94096d579ebff31b8b38048982d3aea25e0c0bb041ba70c",
+      "rust_body_sha256": "0ccd306db6d19296ce8793dc7b6712601f79c5c7cd6f013171102f581589b065",
       "status": "translated",
       "rust_file": "tests/compat/tests/world_constructor_semantics.rs",
       "rust_line": 19,
@@ -3149,7 +3149,7 @@
       "body_sha256": "54f23cbf0ba87b0525c2914e78d75808e93fd1c460fc0bec4d15f09575b1431c",
       "categories": [],
       "fixture_dependencies": [],
-      "rust_body_sha256": "fed746879e584f0c75b19f08009234588905204e5954d7a5f61d14c40664bef1",
+      "rust_body_sha256": "1307f3ee0990260c80fa9ec1b693231d5c3e1f94c293fab7bcca4d5c5140ce55",
       "status": "translated",
       "rust_file": "tests/compat/tests/social_constructor_semantics.rs",
       "rust_line": 16,

tools/audit_red_suite.py

@@ -0,0 +1,207 @@
+#!/usr/bin/env python3
+"""Run and verify MetaCrate's controlled red test-suite baseline."""
+
+from __future__ import annotations
+
+import argparse
+from collections import Counter, defaultdict, deque
+from dataclasses import dataclass
+import json
+import os
+from pathlib import Path
+import re
+import subprocess
+
+
+ROOT = Path(__file__).resolve().parents[1]
+CATALOG = ROOT / "tests" / "upstream-tests.json"
+BASELINE = ROOT / "tests" / "red-suite-baseline.json"
+LIVE_KEYS = ("GRID_USER", "GRID_PASSWORD", "GRID_LOGIN_URL")
+SUMMARY_RE = re.compile(
+    r"test result: (?:ok|FAILED)\. (\d+) passed; (\d+) failed; "
+    r"(\d+) ignored; (\d+) measured; (\d+) filtered out"
+)
+RESULT_RE = re.compile(
+    r"^test (.+) \.\.\. (ok|FAILED|ignored)(?:, .*)?$", re.MULTILINE
+)
+PANIC_RE = re.compile(r"(?:^|\n)thread '([^']+)'(?: \(\d+\))? panicked at ")
+MEMBER_RE = re.compile(
+    r'unimplemented C# API member: ([^\n]+)|NotImplemented \{ csharp_member: "([^"]+)" \}'
+)
+
+
+@dataclass(frozen=True)
+class LogAudit:
+    passed: int
+    failed: int
+    ignored: int
+    measured: int
+    filtered: int
+    passed_names: tuple[str, ...]
+    failed_names: tuple[str, ...]
+    ignored_names: tuple[str, ...]
+    members: Counter[str]
+    nonstandard_failures: tuple[str, ...]
+
+
+def parse_log(text: str) -> LogAudit:
+    """Parse libtest output and associate each failed test with its member ID."""
+    summaries = [tuple(map(int, match)) for match in SUMMARY_RE.findall(text)]
+    if not summaries:
+        raise ValueError("controlled suite log contains no libtest summaries")
+    totals = tuple(sum(row[index] for row in summaries) for index in range(5))
+    results = RESULT_RE.findall(text)
+    names = {
+        state: tuple(name for name, result in results if result == state)
+        for state in ("ok", "FAILED", "ignored")
+    }
+
+    panic_members: dict[str, deque[tuple[str, ...]]] = defaultdict(deque)
+    starts = list(PANIC_RE.finditer(text))
+    for index, start in enumerate(starts):
+        end = starts[index + 1].start() if index + 1 < len(starts) else len(text)
+        chunk = text[start.end() : end]
+        members = tuple(first or second for first, second in MEMBER_RE.findall(chunk))
+        panic_members[start.group(1)].append(members)
+
+    member_counts: Counter[str] = Counter()
+    nonstandard: list[str] = []
+    for name in names["FAILED"]:
+        members = panic_members[name].popleft() if panic_members[name] else ()
+        if members:
+            member_counts[members[0]] += 1
+        else:
+            nonstandard.append(name)
+
+    if totals[0] != len(names["ok"]) or totals[1] != len(names["FAILED"]):
+        raise ValueError("libtest summaries do not match parsed pass/fail result lines")
+    return LogAudit(
+        *totals,
+        names["ok"],
+        names["FAILED"],
+        names["ignored"],
+        member_counts,
+        tuple(nonstandard),
+    )
+
+
+def dotenv_values() -> dict[str, str]:
+    values: dict[str, str] = {}
+    path = ROOT / ".env"
+    if not path.exists():
+        return values
+    for raw_line in path.read_text().splitlines():
+        line = raw_line.strip()
+        if not line or line.startswith("#"):
+            continue
+        line = line.removeprefix("export ")
+        if "=" not in line:
+            continue
+        key, value = line.split("=", 1)
+        values[key.strip()] = value.strip().strip("'\"")
+    return values
+
+
+def has_live_credentials() -> bool:
+    dotenv = dotenv_values()
+    return all((os.environ.get(key) or dotenv.get(key, "")).strip() for key in LIVE_KEYS)
+
+
+def pending_calls() -> list[str]:
+    pending: list[str] = []
+    roots = (ROOT / "tests" / "compat" / "tests", ROOT / "crates")
+    for path in sorted(file for root in roots for file in root.rglob("*.rs")):
+        if re.search(r"\bpending\s*\(", path.read_text()):
+            pending.append(path.relative_to(ROOT).as_posix())
+    return pending
+
+
+def verify(log: LogAudit, live: bool) -> None:
+    catalog = json.loads(CATALOG.read_text())
+    baseline = json.loads(BASELINE.read_text())
+    report = catalog["report"]
+    expected_cases = baseline["reviewed_cases"]
+    if catalog["upstream_commit"] != baseline["upstream_commit"]:
+        raise ValueError("red-suite baseline targets a different upstream commit")
+    if catalog["expected_cases"] != expected_cases or sum(report.values()) != expected_cases:
+        raise ValueError("parity catalog does not contain the fixed reviewed case count")
+    expected_report = baseline["parity_report"]
+    if report != expected_report:
+        raise ValueError(f"parity report changed: expected {expected_report}, found {report}")
+    pending = pending_calls()
+    if pending:
+        raise ValueError("pending( remains in Rust test sources: " + ", ".join(pending))
+
+    by_test = defaultdict(list)
+    for case in catalog["tests"]:
+        by_test[case["rust_test"]].append(case["id"])
+    passed_cases = sorted(
+        case_id for name in log.passed_names for case_id in by_test.get(name, [])
+    )
+    allowed_passes = sorted(baseline["allowed_parity_passes"])
+    if passed_cases != allowed_passes:
+        raise ValueError(
+            f"parity pass baseline changed: expected {allowed_passes}, found {passed_cases}"
+        )
+    support_passes = log.passed - len(passed_cases)
+    if support_passes != baseline["support_passes"]:
+        raise ValueError(
+            f"support pass baseline changed: expected {baseline['support_passes']}, "
+            f"found {support_passes}"
+        )
+
+    expected_ignored = 0 if live else report["ignored_live"]
+    expected_failed = expected_cases - len(allowed_passes) - expected_ignored
+    if (log.failed, log.ignored) != (expected_failed, expected_ignored):
+        raise ValueError(
+            "controlled totals changed: "
+            f"expected failed={expected_failed}, ignored={expected_ignored}; "
+            f"found failed={log.failed}, ignored={log.ignored}"
+        )
+    if log.nonstandard_failures:
+        raise ValueError(
+            "failures without standardized member IDs: "
+            + ", ".join(log.nonstandard_failures)
+        )
+    if sum(log.members.values()) != log.failed:
+        raise ValueError("standardized member aggregation does not cover every failure")
+
+
+def run_suite() -> tuple[int, str]:
+    command = [
+        "cargo",
+        "test",
+        "--workspace",
+        "--no-fail-fast",
+        "--",
+        "--nocapture",
+        "--test-threads=1",
+    ]
+    completed = subprocess.run(command, cwd=ROOT, capture_output=True, text=True, check=False)
+    return completed.returncode, completed.stdout + completed.stderr
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--log", type=Path, help="audit an existing captured cargo-test log")
+    args = parser.parse_args()
+    if args.log:
+        return_code, text = 101, args.log.read_text()
+    else:
+        return_code, text = run_suite()
+    if return_code != 101:
+        raise SystemExit(f"controlled suite returned {return_code}, expected Cargo test failure 101")
+    live = has_live_credentials()
+    audit = parse_log(text)
+    verify(audit, live)
+    print(
+        f"controlled red suite is current: passed={audit.passed}, failed={audit.failed}, "
+        f"ignored={audit.ignored}, live_credentials={str(live).lower()}, "
+        f"standardized_members={len(audit.members)}"
+    )
+    for member, count in audit.members.most_common():
+        print(f"{count:4} {member}")
+
+
+if __name__ == "__main__":
+    main()

tools/test_audit_red_suite.py

@@ -0,0 +1,39 @@
+import unittest
+
+from audit_red_suite import parse_log
+
+
+class AuditRedSuiteTests(unittest.TestCase):
+    def test_associates_standardized_boundaries_with_failed_tests(self) -> None:
+        audit = parse_log(
+            """
+thread 'direct' panicked at generated.rs:1:1:
+unimplemented C# API member: M:Example.Direct
+test direct ... FAILED
+thread 'typed' panicked at test.rs:1:1:
+assertion failed: left == right
+  left: Some(NotImplemented { csharp_member: "M:Example.Typed" })
+ right: Some(ArgumentNull)
+test typed ... FAILED
+test support ... ok
+test result: FAILED. 1 passed; 2 failed; 0 ignored; 0 measured; 0 filtered out
+"""
+        )
+        self.assertEqual(audit.members["M:Example.Direct"], 1)
+        self.assertEqual(audit.members["M:Example.Typed"], 1)
+        self.assertEqual(audit.nonstandard_failures, ())
+
+    def test_reports_nonstandard_failure(self) -> None:
+        audit = parse_log(
+            """
+thread 'broken' panicked at test.rs:1:1:
+assertion failed
+test broken ... FAILED
+test result: FAILED. 0 passed; 1 failed; 0 ignored; 0 measured; 0 filtered out
+"""
+        )
+        self.assertEqual(audit.nonstandard_failures, ("broken",))
+
+
+if __name__ == "__main__":
+    unittest.main()