Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
17 commits
Select commit Hold shift + click to select a range
47700b7
proofs: record theory grades as PROOF-POLICY §8 PWG; scan the import …
claude Nov 9, 2026
a71dc76
docs(proofs): restore T-8/T-9 ledger rows; PWG census; correct proof …
claude Nov 9, 2026
77fcedb
proofs: scan the import cone Agda reports; mark the receipt pending r…
claude Nov 9, 2026
5f123b9
docs(proofs): cite the CI receipt for the re-commented proof modules
claude Nov 9, 2026
c728a8c
proofs: Agda whitespace in the postulate scan; check Agda.Primitive b…
claude Nov 9, 2026
dcaac10
docs(proofs): answer the Codex review of #171
claude Nov 9, 2026
9ff3043
proofs: comments separate tokens in the scan; skip pragma bodies as A…
claude Nov 9, 2026
ad853ee
Merge remote-tracking branch 'origin/claude/awesome-wright-va45xo' in…
claude Nov 9, 2026
9eb9f5f
docs(proofs): fold #171's receipt note into #170's pending re-run
claude Nov 9, 2026
be64d85
proofs: Rocq and Lean recheck legs for T-1 (PWG-2ii)
claude Nov 9, 2026
cf1ace7
proofs: split T-2/T-3 into an abstract single-active log and an instance
claude Nov 9, 2026
7a0bdc9
Merge remote-tracking branch 'origin/main' into claude/vibrant-cori-l…
claude Nov 9, 2026
4882688
fix(proofs): keep Rocq build output out of the tree; HTTPS-only prove…
claude Nov 9, 2026
f73046b
docs(ledger): T-5 and T-8 claim replacement by rename, not a tested f…
claude Nov 9, 2026
99770a3
docs(proofs): answer the Codex review of f73046b
claude Nov 9, 2026
3716998
docs(proofs): split T-9 from T-11; correct the Rocq equality claim; n…
claude Nov 9, 2026
231d1d8
docs(readiness): four theory theorems at PWG-3 and T-1 at PWG-2ii
claude Nov 9, 2026
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 31 additions & 0 deletions .github/workflows/agda-proofs.yml
Original file line number Diff line number Diff line change
Expand Up @@ -31,3 +31,34 @@ jobs:
run: test "$(agda --version)" = 'Agda version 2.6.4.3'
- name: Proofs, sibling pin, expected rejections
run: bash scripts/check-agda.sh
recheck:
# PROOF-POLICY §2 recheck legs: the Rocq and Lean re-proofs of the Agda
# theorems, with their expected-rejection fixtures. Local run: just test-recheck.
name: Rocq and Lean recheck legs, expected rejections
runs-on: ubuntu-24.04
timeout-minutes: 15
env:
LEAN_VERSION: 4.35.0
LEAN_SHA256: 7289597a44543246c9227b8cae501767e095ce17f6d448b95fc4a8dc97268f6d
steps:
- name: Install the pinned provers
run: |
sudo apt-get update
sudo apt-get install --no-install-recommends -y coq=8.18.0+dfsg-1build2 zstd
curl --proto '=https' --tlsv1.2 -sSfL -o lean.tar.zst \
"https://github.com/leanprover/lean4/releases/download/v${LEAN_VERSION}/lean-${LEAN_VERSION}-linux.tar.zst"
echo "${LEAN_SHA256} lean.tar.zst" | sha256sum -c -
mkdir -p "$RUNNER_TEMP/lean"
tar --zstd -xf lean.tar.zst -C "$RUNNER_TEMP/lean"
rm lean.tar.zst
echo "$RUNNER_TEMP/lean/lean-${LEAN_VERSION}-linux/bin" >> "$GITHUB_PATH"
- name: Checkout
uses: actions/checkout@v7.0.1
with:
persist-credentials: false
- name: Verify the checked prover versions
run: |
test "$(coqc --version | head -1)" = 'The Coq Proof Assistant, version 8.18.0'
lean --version | grep -q "^Lean (version ${LEAN_VERSION}, "
- name: Recheck legs, no axioms, expected rejections
run: bash scripts/check-recheck.sh
9 changes: 9 additions & 0 deletions .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -91,3 +91,12 @@ deps/
build/
dist/
*.agdai

# Rocq and Lean build outputs (scripts/check-recheck.sh builds in a temporary directory)
*.vo
*.vok
*.vos
*.glob
.*.aux
*.olean
*.ilean
21 changes: 10 additions & 11 deletions .machine_readable/6a2/STATE.a2ml
Original file line number Diff line number Diff line change
Expand Up @@ -47,17 +47,16 @@ benchmarks = "5 Criterion groups (no baseline recorded)"
total = "141 tests + 5 benchmark groups + 12 PROVEN ledger rows — as declared in READINESS.adoc and measured by dashboard-check"

[proof-grades]
# mathesis (estate-mathematical-architecture §5/§6) + standards
# 3-practice/PROOF-POLICY.adoc. A grade is a second axis over the PROVEN/TESTED
# ledger vocabulary, never a percentage. Detail: docs/theory/PROOF-GRADES.adoc.
grade-3 = "G-1, T-1, T-2, T-3 — Agda theory modules under verification/proofs/agda; AGDA-VERIFIED"
grade-3-pending = "E-1m — Epistemic.agda; no receipt yet, because the receipt-commit predates this module"
receipt-commit = "4afb710e86646658f667f10bd6274ee47416bfc7 (agda-proofs.yml run 40867211509, success)"
receipt-prover = "Agda 2.6.4.3 (agda-bin=2.6.4.3-1+b2); resource-algebra pinned at cf9235c"
receipt-flags = "--safe --without-K --cubical-compatible --no-libraries --ignore-interfaces --double-check (canonical per PROOF-POLICY §2.1 since 2026-11-01; the 4afb710 CI receipt predates the flag, so the next agda-proofs.yml run is its receipt)"
not-graded = "the 7 Idris2 PROVEN rows (ABI/interface contracts, PROOF-POLICY §1); all 29 TESTED rows (observed behaviour); ASSUMED/DESIGNED/OPEN rows"
open-obligations = "re-earn the Agda receipt in CI under the canonical flag set; one Agda version across CI (agda-proofs pins 2.6.4.3, dashboard-check installs 2.6.3); no Creusot contract on the Rust, and neither rustc nor crates.io is reachable from the agent sandbox (docs/estate/environment-toolchains.md), so no Rust behaviour is graded"
claimed-higher = "none — no Grade 2i, 2ii or 1 is claimed"
# Proof Witness Grades, standards 3-practice/PROOF-POLICY.adoc §8 (the
# Mathesis brief's §5/§6 ladder, adopted with corrections). Never a
# percentage. Receipts, lineage and per-row records: docs/theory/PROOF-GRADES.adoc.
grade-3 = "PWG-3: G-1, T-2, T-3, E-1m; PWG-2ii: T-1 (Rocq and Lean legs re-proved and reconciled) — census 4 + 1 of 5 theory theorems (G-3 and T-10 are engineering under PROOF-POLICY §1; T-2 and T-3 are stated over the abstract SingleActiveLog)"
receipt-commit = "see docs/theory/PROOF-GRADES.adoc, The PWG-3 receipt (the 4afb710 and fc188c4 receipts are superseded)"
receipt-prover = "Agda 2.6.4.3 (agda-bin=2.6.4.3-1+b2); no standard library; resource-algebra pinned at cf9235c"
receipt-flags = "--safe --without-K --cubical-compatible --no-libraries --ignore-interfaces --double-check (PROOF-POLICY §2.1 canonical, plus two stricter flags)"
not-graded = "the 7 Idris2 PROVEN rows (ABI/interface contracts, PROOF-POLICY §8.1); all 33 TESTED rows (observed behaviour); ASSUMED/DESIGNED/OPEN rows"
open-obligations = "Rocq and Lean legs for the four PWG-3 rows (PROOF-POLICY §2); one Agda version across CI (agda-proofs pins 2.6.4.3, dashboard-check installs 2.6.3); no Creusot or Verus proof on the Rust, so no Rust behaviour is proved"
claimed-higher = "PWG-2ii for T-1 only (Rocq and Lean legs re-proved and reconciled); no PWG-2i or PWG-1 is claimed"

[test-categories-complete]
unit = true
Expand Down
4 changes: 4 additions & 0 deletions Justfile
Original file line number Diff line number Diff line change
Expand Up @@ -92,6 +92,10 @@ test-contracts:
test-agda:
bash scripts/check-agda.sh

# Rocq and Lean recheck legs of the Agda theorems (PROOF-POLICY §2), no axioms, expected rejections.
test-recheck:
bash scripts/check-recheck.sh

# Idris2 ABI <-> januskey.h <-> ffi/zig agreement (sizes, status codes, enums, symbols); no compiler needed.
abi-layout-check:
bash scripts/check-abi-layout.sh
Expand Down
Loading
Loading