benbrownandClaude Opus 4.8
899d55f4b6
An adversarial audit found the enforcement story ahead of the code: gates that were documented as hard gates were advisory, manual, or absent, and several human-facing claims outran the machine record. This makes the claims true. High findings - Differential fuzz was documentation, not enforcement: verdict hardcoded fuzz_iters=0 and diff-test hardcoded the gate to Skipped, while the case studies claimed 10k-iteration fuzz on the same wins. Fuzz is now a real pipeline gate (strict FUZZ-RESULT contract, executed count recorded), and it is inherently baseline-vs-candidate, so it runs on the accept path and reports Skipped in the standalone `just gates` flow. New hard rule: a machine `accepted` verdict is impossible unless the fuzz gate actually passed — otherwise it caps at needs-human-review. - The agent's system prompt claimed FP/concurrency/unsafe patches were "routed to human review automatically". No such mechanism existed. Added a conservative lexical risk classifier (crates/verdict/src/risk.rs) that forces needs-human-review on any would-be accept carrying those signals; fp-tolerance equivalence always signals. - The local verdict path ran agent-influenced code unsandboxed. It now runs under scripts/no-net.sh (network namespace) and fails closed. Upstream test suites are hash-verified against corpora/<t>/TESTSUITE.sha256 when present (scripts/pin-testsuite.sh generates them). Also fixed, found while fixing the above - The pipeline script's `set -e` was inert (brace group as the left operand of `&&`), so a failing candidate build did not abort the run and verdict could bench a stale binary. Now a scoped subshell whose status is branched on at top level. - A wrapper that exits before exec'ing (no-net.sh refusing, bad wrapper path) stranded RUNNING.lock and left read_verdict polling forever. Failure accounting now lives outside the wrapper. - harnessd's patch allowlist ignored git rename/copy headers and --no-prefix diffs; the rename-escape case is now a committed regression test. - The workspace did not compile on Windows (ungated Unix APIs). cfg-gated; 71 portable tests now run on both platforms. - pin-check regenerated the corpus manifest instead of verifying it; it is now verify-only, with a deliberate `just pin-corpus` to re-pin. - Max RSS is captured per run on Unix; PMU counters are opt-in diagnostics (compare --perf-stat), never part of the accept decision. Docs now match the code, including what is NOT yet enforced: no target ships a TESTSUITE.sha256 pin, no target declares [build].tsan, and matmul is not wired to the fp-tolerance gate — each is stated as mechanized-but-inert rather than done. Corrected the stale "33 ledger rows" (34), the playbook's class-3 cJSON win (rejected), adversarial-review.md's sanitizer-separation claim (five accepted rows carry sanitizers_clean=false), the unsupported "40,000 requests" figure, and the blanket "historical rows record fuzz_iters=0" (8 of 10; phase0-tokei-002/-003 record 4,332). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
3.9 KiB
Phase 3 — playbook + proof
Exit criteria (SPEC §5): 3–5 public case studies · zero regressions shipped · playbook ≥6 classes · C/C++ targets · coz.
Phase 3 turns the trust layer and the agent loop from Phases 1–2 into evidence: verified optimization wins across the playbook and across languages, each one reproducible from a pinned corpus through the same gated pipeline, with every attempt — win or loss — in the append-only ledger.
What changed for Phase 3
- The trust layer went language-agnostic. Build isolation moved from
a cargo-specific
CARGO_TARGET_DIRinjection to an explicit{out}placeholder plus optionalsanitizer/sanitizer_binarybuild templates (crates/diff-test/src/target.rs). A C/C++ target is now just atarget.tomlwithclangcommands. Proven zero-regression: tokei ran a full verdict through the refactored pipeline to a correct null result before any C target was added. - A C target joined the roster — cJSON (v1.7.19, MIT), with a trust-layer harness driver, a hermetic Unity/CTest gate, ASan+UBSan sanitizers, a deterministic pinned corpus, and its own A/A calibration (0/20 false positives, 20/20 injected-slowdown detections). CI gates it on every push.
- coz is wired (
-DHOTPATH_COZprogress point,just coz,scripts/coz-*); its apt runtime aborts in its own init on this container's glibc (documented inresults/cjson/coz/README.md), so callgrind cache-sim is the working profiler.
Playbook classes exercised (≥6 required)
| Class | Mechanism | Exercised on | Result |
|---|---|---|---|
| 1 | build config (LTO, codegen-units) | tokei | ✅ win (+10.4%) |
| 2 | allocator swap (mimalloc) | comrak | needs-human-review (+4.6%) |
| 3 | allocation churn | tokei, comrak, cjson | ✅ wins + one overturned |
| 4 | data layout | comrak | attempted (rejected) |
| 5 | algorithmic / redundant work | tokei ×3, cjson | ✅ wins |
| 6 | SIMD / autovectorization | comrak, tokei | attempted (rejected) |
Six classes exercised (1–6); class 5 and class 3 carry verified wins on both a Rust and a C target.
The case studies
01-tokei-algorithmic-rust.md— three independent CI-verified class-5 wins on a Rust code counter (~1.26× multiplied, stated as an approximation, not a measured figure), each unattended and audited.02-build-flags-and-allocators.md— the cheap wins first: LTO (class 1) accepted, mimalloc (class 2) correctly held at needs-human-review.03-comrak-caught-false-accept.md— the pipeline auto-accepted a leaking teardown patch; the audit overturned it and hardened the pipeline. The most important study.04-cjson-c-target.md— the cross-language proof: a real sub-threshold win correctly rejected, then a byte- identical number-handling win accepted on the C target.
The through-line
Every number here carries its 95% bootstrap CI and its workload. Every win survived byte-identical golden replay, a 10k-input differential fuzz, and sanitizers. Every rejection is a real mechanism that simply didn't clear the 2% CI-lower-bound bar — and it is in the ledger too, because a rejection is a complete, valid outcome. Nothing shipped that the pipeline couldn't prove.
Note (2026-07-13). "Every win survived … a 10k-input differential fuzz, and sanitizers" is true of the evidence, not of the machine record at the time: through Phase 5 the fuzz ran out-of-band (
scripts/diff-fuzz-<target>.py, per-attempt) and the Phase 3 rows therefore carryfuzz_iters=0. The fuzz gate is now integrated into the accept path, where a passed fuzz gate is a precondition for a machineacceptedverdict; rows written after this date record the iteration count actually executed. See the per-case-study notes in01-tokei-algorithmic-rust.mdand04-cjson-c-target.md.