From bc860f3314d9e94dda743c6ba4b3997a25d9264d Mon Sep 17 00:00:00 2001 From: Nick Petalas Date: Wed, 18 Nov 2026 17:50:39 +0000 Subject: [PATCH 1/2] feat(research): shrink the reversible half-sum CLEAR circuit --- research/half-sum-clear-circuit/README.md | 97 ++++++++++++++++++++ research/half-sum-clear-circuit/SOURCES.json | 18 ++++ research/half-sum-clear-circuit/TASK.json | 95 +++++++++++++++++++ research/half-sum-clear-circuit/VERIFY.json | 18 ++++ research/half-sum-clear-circuit/circuit.py | 59 ++++++++++++ research/half-sum-clear-circuit/verify.py | 80 ++++++++++++++++ 6 files changed, 367 insertions(+) create mode 100644 research/half-sum-clear-circuit/README.md create mode 100644 research/half-sum-clear-circuit/SOURCES.json create mode 100644 research/half-sum-clear-circuit/TASK.json create mode 100644 research/half-sum-clear-circuit/VERIFY.json create mode 100644 research/half-sum-clear-circuit/circuit.py create mode 100644 research/half-sum-clear-circuit/verify.py diff --git a/research/half-sum-clear-circuit/README.md b/research/half-sum-clear-circuit/README.md new file mode 100644 index 0000000000..7de5b202a2 --- /dev/null +++ b/research/half-sum-clear-circuit/README.md @@ -0,0 +1,97 @@ +# A smaller reversible circuit for one signed half-sum CLEAR + +At signed width 1,076, this circuit implements the complete output map for the +eight-limb row at event 88937 with **93,811 gates and 15,103 internal zero bits**. +SYLforge reports 277,929 gates and 86,525 internal zero bits for the same row +in the general rational circuit. Specializing to four positive unit coefficients, +four negative unit coefficients and denominator two saves 184,118 gates and +71,422 work bits. Both counts include output copying and cleanup. +[Published comparator and source row](https://github.com/SYLforge/integer-mult-bounds/blob/e5ba67dfd6237a1a3acf4d67098d3242adee8229/research/clean-rational-clear-witness/README.md) + +## Interface and scope + +This is a scoped proof with an executable finite gate certificate. In SYLforge's +#7669 word, target 1502 uses donors 1072 and 500. The eight signed limbs are +the real and imaginary parts at addresses 0 and 102 of the first donor, then +the same four of the second donor. We use the real output at address zero +identified by #7687. The caller-to-row identification and the comparator counts +are taken from that work. The circuit accepts arbitrary donor bitstrings. +[Source word](https://github.com/CrocSwap/integer-mult-bounds/pull/7669) + +For any positive width w, let N be the sum of the first four signed donors +minus the sum of the last four. Put q = floor(N/2). The circuit leaves donors +untouched, XORs the low w bits of q into the target, and toggles the diagnostic +if N is odd or q is outside the signed w-bit range. Every work bit starts and +ends zero. With initial diagnostic zero, both outputs are zero exactly when +N equals twice the signed target. In particular, a fractional quotient or +signed overflow stays detectable even if the target XOR produces zero. + +## Construction and proof + +Let n = w + 3. The largest possible N is 4(2^w − 1), attained by placing +the four maxima before the four minima. Swapping the groups attains its +negative. Both fit in signed n bits. Sign extension aliases the donor sign +wire as a control. Start with the first extended donor and accumulate the +other seven modulo 2^n. The final residue therefore encodes N exactly. + +Each ripple stage uses fresh result bits and fresh internal carries. In a +column with accumulator bit a, operand bit b and incoming carry or borrow c, +first write p = a XOR b. Addition's outgoing carry is ab XOR cp. Subtraction's +outgoing borrow is (1−a)b XOR (1−p)c, or ab XOR b XOR cp XOR c. These formulas +follow by treating the equal-bit and unequal-bit cases separately. Both stages +then XOR c into p to produce the result bit. The low column takes c = 0 and +the top column discards its outgoing carry. This proves the modular stage +identity by induction over the columns. Donor wires appear only as controls. + +The low bit of N flags oddness, including for negative N. Bits 1 through w +give the low w quotient bits because arithmetic right shift gives floor +division by two. The quotient fits exactly if bits w+1 and w+2 of N both +equal bit w. Two XOR comparisons and Boolean ORs therefore implement the +specified diagnostic. Copy the result bits and flag to the output ports and +run the internal gate list backwards. Each gate is an involution, and the +internal list never accesses the output ports. This restores every work bit +regardless of validity or initial target. + +## Complete resource count + +Each of seven stages allocates n result bits and n−1 carry bits. Two comparison +bits and two OR bits give 7(2n−1)+4 = **14w+39 work bits**. The external wires +are the 8w immutable inputs, w target bits and one diagnostic bit. + +An addition uses 2n gates to form p, n−1 to copy incoming carries into the +result, n−1 for ab and n−2 for cp. Each of the four subtractions adds +(n−1)+(n−2) borrow toggles. The flag needs four CNOTs for comparisons and +three gates for each of two ORs. Thus the forward computation uses +7(5n−4)+4(2n−3)+10 = 43n−30 gates. Output copying costs w+1 and the reverse +costs another 43n−30, giving **87w+199 gates**. At width 1,076 the emitted +list contains 63,637 CNOTs and 30,174 Toffolis. + +## Reproduce + +From the repository root with CPython 3.12 and its standard library, run + +~~~sh +python3.12 -B research/half-sum-clear-circuit/verify.py +python3.12 -B scripts/research_package.py --package research/half-sum-clear-circuit +~~~ + +The verifier simulates every gate, checks wire indices and donor immutability, +and compares every output and workspace wire with an integer oracle. It +exhausts donor tuples at widths one and two, then executes 32 cases at width +1,076, including negative odd numerators, both signed endpoints, wrapped +overflow and reproducible mixed inputs. It prints PASS_HALF_SUM_CLEAR. +The gate certificate establishes an upper bound for this row. Optimality, +rounded producer reachability, full erasure, tape costs and a change to κ +remain outside its scope. + +## Open next questions + +What does this circuit cost on the physical tapes? Fix a tape layout and +account for its clean banks, carry access, output copy and reverse scans. + +## Credit + +The specialized circuit, proof and verifier were produced by Nick Petalas. +SYLforge supplied the source word, the coordinate identification, the complete +validity interface, the published comparator and the smaller-circuit question. +Ripple arithmetic and reversible compute/copy/uncompute are standard. diff --git a/research/half-sum-clear-circuit/SOURCES.json b/research/half-sum-clear-circuit/SOURCES.json new file mode 100644 index 0000000000..5335fa97d9 --- /dev/null +++ b/research/half-sum-clear-circuit/SOURCES.json @@ -0,0 +1,18 @@ +{ + "schema_version": 1, + "base_commit": "e54523517d0f03e58352e647c403a5af3e525a57", + "files": [ + { + "path": "certificates/selected-result.json", + "usage": "provenance", + "git_blob": "75d77b328ea02ded535e7f23aee5b1e55d0bb1a8", + "sha256": "154c3d30455d778fd3343b6b4851f0fa4665f0f7625b0adb3675e2bafbbf6bf1" + }, + { + "path": "docs/research/agent-task-catalog.json", + "usage": "provenance", + "git_blob": "3404fbdd5e7529a0674eef26114b5071e4586cec", + "sha256": "ead6cdc9d0af6d58e8a49744d8ec8c7c15e13d2ba93c276c434bcf9b51b93a81" + } + ] +} diff --git a/research/half-sum-clear-circuit/TASK.json b/research/half-sum-clear-circuit/TASK.json new file mode 100644 index 0000000000..b3592eee4c --- /dev/null +++ b/research/half-sum-clear-circuit/TASK.json @@ -0,0 +1,95 @@ +{ + "schema_version": 1, + "task_id": "formal-interface-lemma", + "priority_revision": 8, + "base_commit": "e54523517d0f03e58352e647c403a5af3e525a57", + "original_card": { + "id": "formal-interface-lemma", + "question": "Can one uncovered interface implication be formalized with exact caller and certificate bindings?", + "starting_points": [ + "docs/research/research-family-status.md", + "certificates/selected-result.json", + "research/gate-operand-parity-lean/README.md", + "research/staged544-certified-endpoint/README.md", + "research/unconditional-batched-crt/README.md" + ], + "methods": [ + "Formalize a missing boundary lemma identified by the selected review.", + "Audit a formal theorem-to-certificate binding independently." + ], + "acceptance_gate": "State the exact formalized proposition and remaining assumptions; avoid duplicate arithmetic formalizations already present.", + "first_step": { + "command": [ + "python3", + "-B", + "scripts/research_selected_baseline.py" + ], + "expected": "PASS_RESEARCH_BASELINE_BINDINGS_ONLY", + "inspect": "Resolve the current selected review, separate complex/ordinary BIT/admitted BIT/outer budgets, and compare the card against live handoffs before starting. Historical ceilings require exact source/model equivalence.", + "scope": "Source-binding orientation only; not a scientific replay or all-size proof. Materialize selected inputs if this checkout is sparse." + }, + "first_experiment": "Write one missing statement with quantified hypotheses, actual caller and existing coverage. A compact-switch lemma is a candidate only after its mathematical contract is reviewed. Establish a bounded proof plan before a separately budgeted proof-assistant build; do not rerun large Lean jobs as orientation.", + "bottleneck_link": "A missing interface proof can reduce the conditional gap even if it does not change kappa.", + "allowed_variations": [ + "Narrow to one formal lemma or one theorem-to-certificate binding." + ], + "scope_change_triggers": [ + "Formalizing already-covered arithmetic and claiming the full multiplication theorem." + ], + "overlap_terms": [ + "hyperplane end", + "formal interface", + "Lean binding", + "3807", + "3857", + "4100", + "gate-operand-parity-lean", + "staged544-certified-endpoint", + "unconditional-batched-crt" + ], + "existing_checks": [ + { + "scope": "PR #3807: scoped gate-operand parity formalization.", + "evidence": "research/gate-operand-parity-lean/README.md", + "remaining": "Exact theorem-to-caller binding and genuinely uncovered interface lemmas.", + "status": "author-checked", + "source_commit": "4c3530f42a6abcc48e7a6bcffd6c901911dc8269", + "selected_record_sha256": "bb2eaa58647b353f88d0aec2eafb9d30df1be53589231b23e12ceef3e4bad129" + }, + { + "scope": "PR #3857: certified real-power moment/endpoint arithmetic.", + "evidence": "research/staged544-certified-endpoint/README.md", + "remaining": "Uniform algorithmic implications, not another endpoint digit.", + "status": "author-checked", + "source_commit": "ef4315b8caa605e47a2515004845eb2d2ed71a86", + "selected_record_sha256": "bb2eaa58647b353f88d0aec2eafb9d30df1be53589231b23e12ceef3e4bad129" + }, + { + "scope": "PR #4100: compact-switch formalization proposed as future validation.", + "evidence": "research/unconditional-batched-crt/README.md", + "remaining": "Audit the statement and assumptions before a formal proof campaign.", + "status": "author-checked", + "source_commit": "337d04939571a637aeab54a0f58f54fde811663a", + "selected_record_sha256": "bb2eaa58647b353f88d0aec2eafb9d30df1be53589231b23e12ceef3e4bad129" + } + ] + }, + "scope_status": "changed", + "actual_scope": "Construct a smaller exact reversible gate circuit for the single signed half-sum CLEAR row at event 88937.", + "scope_change_reason": "Question 3 of PR #7687 asks for a constructive gate and workspace improvement under its existing output contract. This contributes a mathematical interface proof and executable circuit rather than a proof-assistant formalization.", + "bottleneck_link": "The owned_erasure interface needs an exact validity test and restoration of temporary storage at the chosen row. Gate-level cost is only one part of that service.", + "budget_minutes": 60, + "stop_rule": "Stop at the first construction improving the cited complete gate and clean-workspace counts at width 1076 with all four output obligations proved.", + "outcome": "completed", + "evidence": "README.md gives the all-input proof and resource count. verify.py executes the emitted gates and compares every wire to integer arithmetic.", + "author": "Nick Petalas", + "ai_assistance": "Independent human and formal proof-kernel review are unclaimed.", + "open_questions": [ + { + "question": "What tape movement and initialization cost does this row require?", + "why_it_matters": "The gate count omits physical access and clean-bank provisioning.", + "first_step": "Assign each bit block to a tape and count the full forward, output and reverse scans.", + "blocked_by": "A fixed tape layout and initialization service for this word remain unspecified." + } + ] +} diff --git a/research/half-sum-clear-circuit/VERIFY.json b/research/half-sum-clear-circuit/VERIFY.json new file mode 100644 index 0000000000..c4ff5d4106 --- /dev/null +++ b/research/half-sum-clear-circuit/VERIFY.json @@ -0,0 +1,18 @@ +{ + "schema_version": 1, + "status": "ready", + "python": "3.12", + "requirements": [], + "inputs": [], + "commands": [ + { + "argv": [ + "{python}", + "-B", + "{package}/verify.py" + ], + "timeout_seconds": 120, + "checks": "Check every gate and complete emitted resource counts. Compare all wires to exact arithmetic for all donor tuples at widths 1 and 2 and full-width fixtures at 1076." + } + ] +} diff --git a/research/half-sum-clear-circuit/circuit.py b/research/half-sum-clear-circuit/circuit.py new file mode 100644 index 0000000000..a21ae75253 --- /dev/null +++ b/research/half-sum-clear-circuit/circuit.py @@ -0,0 +1,59 @@ +"""Reversible CLEAR for (x0+x1+x2+x3-x4-x5-x6-x7)/2. + +Wires store little-endian bits. A gate tuple contains its controls followed +by its XOR target. The first 8*w wires are immutable inputs, followed by the +w target wires and the diagnostic. All remaining wires start and end zero. +""" + + +def compile_row(width): + if width < 1: + raise ValueError("positive signed width required") + size = width + 3 + next_wire = 9 * width + 1 + gates = [] + + def allocate(length): + nonlocal next_wire + block = range(next_wire, next_wire + length) + next_wire += length + return block + + def signed_operand(index): + start = index * width + return [start + min(bit, width - 1) for bit in range(size)] + + total = signed_operand(0) + for index in range(1, 8): + operand = signed_operand(index) + result = allocate(size) + carries = allocate(size - 1) + for bit, (a, b, out) in enumerate(zip(total, operand, result, strict=True)): + gates.extend(((a, out), (b, out))) # propagate bit p = a XOR b + if bit + 1 < size: + carry = carries[bit] + gates.append((a, b, carry)) + if index >= 4: + gates.append((b, carry)) + if bit: + gates.append((carries[bit - 1], out, carry)) + if index >= 4: + gates.append((carries[bit - 1], carry)) + if bit: + gates.append((carries[bit - 1], out)) + total = result + + mismatch = allocate(2) + for offset, flag in enumerate(mismatch): + gates.extend(((total[width], flag), (total[width + offset + 1], flag))) + + def boolean_or(left, right): + out, = allocate(1) + gates.extend(((left, out), (right, out), (left, right, out))) + return out + + overflow = boolean_or(*mismatch) + invalid = boolean_or(total[0], overflow) + copy_outputs = [(total[bit + 1], 8 * width + bit) for bit in range(width)] + copy_outputs.append((invalid, 9 * width)) + return next_wire, gates + copy_outputs + gates[::-1] diff --git a/research/half-sum-clear-circuit/verify.py b/research/half-sum-clear-circuit/verify.py new file mode 100644 index 0000000000..f880633ca6 --- /dev/null +++ b/research/half-sum-clear-circuit/verify.py @@ -0,0 +1,80 @@ +"""Execute the generated gates and compare all wires to signed integer arithmetic.""" + +from collections import Counter +from itertools import batched, product +from random import Random + +from circuit import compile_row + + +def check_batch(width, size, gates, cases): + """Each bit of a Python integer simulates one independent circuit input.""" + states = [0] * size + expected_outputs = [0] * (width + 1) + limit = 1 << (width - 1) + for lane, (donors, target, diagnostic) in enumerate(cases): + for port, value in enumerate((*donors, target)): + for bit in range(width): + states[port * width + bit] |= ((value >> bit) & 1) << lane + states[9 * width] |= diagnostic << lane + numerator = sum(donors[:4]) - sum(donors[4:]) + quotient, remainder = divmod(numerator, 2) + invalid = bool(remainder or not -limit <= quotient < limit) + for bit in range(width): + expected_outputs[bit] |= (((target ^ quotient) >> bit) & 1) << lane + expected_outputs[-1] |= (diagnostic ^ invalid) << lane + expected = states.copy() + expected[8 * width:9 * width + 1] = expected_outputs + for gate in gates: + flip = states[gate[0]] + if len(gate) == 3: + flip &= states[gate[1]] + states[gate[-1]] ^= flip + if states != expected: + raise ValueError("gate output differs from the full expected wire state") + + +def cases_for(width): + limit = 1 << (width - 1) + if width <= 2: + for values in product(range(-limit, limit), repeat=8): + # Targets are XOR outputs. Cover every donor configuration. + yield values, sum(values) % (2 * limit) - limit, values[0] & 1 + return + low, high = -limit, limit - 1 + for numerator in (-1, 0, 1, 2): + yield (numerator,) + (0,) * 7, numerator // 2, 0 + for value in (low, high): + yield (value, value, 0, 0, 0, 0, 0, 0), value, 0 + opposite = -1 - value + quotient = 2 * (value - opposite) + wrapped = (quotient + limit) % (2 * limit) - limit + yield (value,) * 4 + (opposite,) * 4, wrapped, 0 + rng = Random(88937) + for _ in range(24): + words = [rng.randrange(low, high + 1) for _ in range(9)] + yield tuple(words[:8]), words[8], rng.randrange(2) + + +def main(): + for width in (1, 2, 1076): + size, gates = compile_row(width) + counts = Counter(map(len, gates)) + for gate in gates: + if (len(gate) not in (2, 3) or len(set(gate)) != len(gate) + or min(gate) < 0 or max(gate) >= size or gate[-1] < 8 * width): + raise ValueError(f"illegal gate {gate}") + work = size - 9 * width - 1 + if (len(gates), work) != (87 * width + 199, 14 * width + 39): + raise ValueError("emitted gate or workspace count differs from the proof") + checked = 0 + for batch in batched(cases_for(width), 256): + check_batch(width, size, gates, batch) + checked += len(batch) + print(f"w={width} cases={checked} CNOT={counts[2]} Toffoli={counts[3]} " + f"total={len(gates)} work={size - 9 * width - 1}") + print("PASS_HALF_SUM_CLEAR") + + +if __name__ == "__main__": + main() From 8f6279527c4362e2638737c90fa18c3cfec724fa Mon Sep 17 00:00:00 2001 From: Nick Petalas Date: Wed, 18 Nov 2026 17:52:13 +0000 Subject: [PATCH 2/2] fix(ci): sync CI verification doc and historical replay-gap verifier --- docs/ci-verification.md | 19 +++++- .../historical-selected-replay-gap/README.md | 6 +- .../SOURCES.json | 60 +++++++++--------- .../VERIFY.json | 31 +-------- .../historical-selected-replay-gap/verify.py | 63 ++++++++++++++----- 5 files changed, 100 insertions(+), 79 deletions(-) diff --git a/docs/ci-verification.md b/docs/ci-verification.md index 63ba3e9aa8..52b62d0481 100644 --- a/docs/ci-verification.md +++ b/docs/ci-verification.md @@ -1,8 +1,25 @@ # CI verification -## Current selected-family replay: #6030 +## Current selected-family replay: #7000 with #7001 The [selected record](../certificates/selected-result.json) binds conditional +κ = 0.00363005817 to the [application review](research/pr-intake-evidence/pr7000-application/PROOF-REVIEW.md), +[validation receipts](research/pr-intake-evidence/pr7000-application/VALIDATION.json), +and [explicit source closure](../certificates/frontier7000-source.json). +`make frontier7000-verify` follows that exact-source selected replay. The review +reuses eleven authenticated preceding executions and records seven fresh serial +application, scalar and complete native-catalogue executions. The earlier +monolithic timeout is retained separately and is not completed coverage. +Consult the receipts for exact commands, source heads and limits. + +The five inherited framework assumptions remain. No complete uniform word, +literal multiplier execution, independent human proof or formal-kernel proof +is asserted. Routine research submissions do not need to rerun this +selected-family replay. The sections below preserve historical checkpoints. + +## Historical selected-family replay: #6030 + +The [historical checkpoint](../certificates/checkpoints/frontier6030.json) binds conditional κ = 0.003125804 to the [proof review](research/pr-intake-evidence/pr6030-audit/PROOF-REVIEW.md), [validation receipts](research/pr-intake-evidence/pr6030-audit/VALIDATION.json), and [explicit source closure](../certificates/frontier6030-source.json). diff --git a/research/historical-selected-replay-gap/README.md b/research/historical-selected-replay-gap/README.md index 55d8cc3b49..36d9a873ca 100644 --- a/research/historical-selected-replay-gap/README.md +++ b/research/historical-selected-replay-gap/README.md @@ -69,7 +69,11 @@ python3 -B scripts/research_package.py --package research/historical-selected-re The direct command prints `PASS_HISTORICAL_SELECTED_REPLAY_GAP`. A registered replay prints `PASS_REGISTERED_RESEARCH_PACKAGE`. Both require Git history -containing the two inspected commits. +containing the two inspected commits and the source and manifest objects at +`2485805a6d47f36ea83ddde6327d453ac82d44dc`. The verifier uses a temporary +sparse checkout of that commit, checks the declared source digests there, and +uses its planner and manifest inventory. The recorded rejections and selection +therefore remain reproducible after later changes to the live Makefile or CI guide. ## Open next questions diff --git a/research/historical-selected-replay-gap/SOURCES.json b/research/historical-selected-replay-gap/SOURCES.json index c1010eec95..62bb8b3950 100644 --- a/research/historical-selected-replay-gap/SOURCES.json +++ b/research/historical-selected-replay-gap/SOURCES.json @@ -4,13 +4,13 @@ "files": [ { "path": "Makefile", - "usage": "input", + "usage": "provenance", "git_blob": "0d683a06b9e7ee162496108ce9a7c5d2ee94fccf", "sha256": "4f2d4f2dcd15139ec82658a975f85ed300897385f85799218539f4c8d60567da" }, { "path": "certificates/partial-swap-network.json", - "usage": "input", + "usage": "provenance", "git_blob": "eccafa830c16170c36faf93045ddf1f638f7bcd4", "sha256": "4c0b9d37e1034b2076e30a70f8e514416298c462d9ee98bc87fe6556b14df786" }, @@ -22,7 +22,7 @@ }, { "path": "docs/ci-verification.md", - "usage": "input", + "usage": "provenance", "git_blob": "63ba3e9aa8bdc5e942b56e34244b92b16f854085", "sha256": "c7d3027e9ad8bcbff68f07aa9576b30fb2f3c76c44d876d40c7fdbf4a3e2228a" }, @@ -34,163 +34,163 @@ }, { "path": "research/clifford-state-performance/SOURCE.json", - "usage": "input", + "usage": "provenance", "git_blob": "6f98a0061a5104dfab82c9e806f819b41811f684", "sha256": "396d0f08df24952248140d5c65c51b8c902ef1c580892ff7ea182890530f67ee" }, { "path": "research/community-batch1047-audit/CONTENT-COVERAGE.json", - "usage": "input", + "usage": "provenance", "git_blob": "5e0f92af463ec12c5e1dcc3effd44081a88af647", "sha256": "07a9daeaf2bda308a92e9a4684f13d5fc766c7772d74801fceb7f4599fdab226" }, { "path": "research/community-batch1099-audit/CONTENT-COVERAGE.json", - "usage": "input", + "usage": "provenance", "git_blob": "9e13266bf85e627f1b7dc225e9530ea69fd2c7f0", "sha256": "421e1211fb1897c45621dc6801c276e53f2e6f335583c9c9049e535f87c0a3b1" }, { "path": "research/community-batch932-audit/CONTENT-COVERAGE.json", - "usage": "input", + "usage": "provenance", "git_blob": "cc4d03eb59b9ab3f952735f7e88ff18c2d15d7af", "sha256": "184629cac91a5cfaca50330a88596008b824221433867dcf8117539c913c284a" }, { "path": "research/community-batch970-audit/CONTENT-COVERAGE.json", - "usage": "input", + "usage": "provenance", "git_blob": "8b9f4111badf7de5d97684799560b55110e9da79", "sha256": "23188ed920e38a54006cb883e181585620821c63bf7e8b5e05d32719417cc37e" }, { "path": "research/community-frontier741-audit/CONTENT-COVERAGE.json", - "usage": "input", + "usage": "provenance", "git_blob": "a5300d4e7a5381a3f443fc54c768ca6f0f236d68", "sha256": "3c820fb30e1b4d9bcfc6a7ab524375e5b2abd66b940af2c509146104f0bcd79c" }, { "path": "research/community-frontier890-audit/CONTENT-COVERAGE.json", - "usage": "input", + "usage": "provenance", "git_blob": "d7ff6d777b01d69b6ce84caf25d3b7e4a4d2f211", "sha256": "6b185a9902652f893f3ebd8ada92d2f11b6de6533a9a4d11718a8a4496101128" }, { "path": "research/community-hyperplane599-audit/SOURCE.json", - "usage": "input", + "usage": "provenance", "git_blob": "546f37d326d10a99910ae8f908e71ef768524d98", "sha256": "65099d764bfcc39bda5e4d9966783611b094c3522dbdd1435cd498d657a8ef8e" }, { "path": "research/community-k492-audit/SOURCE.json", - "usage": "input", + "usage": "provenance", "git_blob": "e538481e4cb16ed936d3195f2dfb5b5a9ca0a76b", "sha256": "2c0f4fa5bc150d05658af2e7c54c4d2c337dd52b7efd3d69530ae73bcbdf452a" }, { "path": "research/community-reconciliation92-audit/MANIFEST.json", - "usage": "input", + "usage": "provenance", "git_blob": "2a2e93685173d5f13cbb5abe740f5d90352e0228", "sha256": "5f501f3c118131e7d069f30ad77186eb2ad6961f9680a0ef105f4514ed41808a" }, { "path": "research/partial-swap-digest/baseline.py", - "usage": "input", + "usage": "provenance", "git_blob": "a2f0190704db83bd8ef48e46e723c49b925804fe", "sha256": "81e9af92cdf38243a540cdcff2062778e449467848d444da37a9553c12ca4c34" }, { "path": "research/r420-two-sided-basis/SOURCES.json", - "usage": "input", + "usage": "provenance", "git_blob": "5d718e11e62f4bcadecf1e02d6b61f87dbe190b0", "sha256": "d9810b0d139c5a1211fd2c1f0d142187cc1fca30026e1e7bc4f9ecfacf1596d1" }, { "path": "research/skip-clones/SOURCE.json", - "usage": "input", + "usage": "provenance", "git_blob": "8d1bb3b9c8189e35e5d8bfdfa632d7473e8be0d5", "sha256": "0b68e63e35a97ce6b0cdb6e291b88ebaa8f2dd4afb70b2498f10ee89428258dc" }, { "path": "research/split-skip/SOURCE.json", - "usage": "input", + "usage": "provenance", "git_blob": "2ab610b6ea2edd2865fda793ef2168b0c76afb4f", "sha256": "7c2b4646a3ecfef6f881da5c43e4bd0fa9a4d1b00548b8ab458d897e16735134" }, { "path": "scripts/historical-ci-inputs/Makefile", - "usage": "input", + "usage": "provenance", "git_blob": "aff68409021c9d401a6f8013b9dfd7dbcc30f2a8", "sha256": "ea8830dd79da493e2d75baf753d733ff7efbcf2b4794afe41fae0ac8f3055646" }, { "path": "scripts/historical-ci-inputs/ledger-batch932-run_isolated_tests.py", - "usage": "input", + "usage": "provenance", "git_blob": "65db599ab0b1dea0312c4ca048e0bd0f44c3736f", "sha256": "96ea543e6c707424afe247e77bd86c82152f90fc76a0773c4232145da5cdf8d1" }, { "path": "scripts/historical-ci-inputs/ledger-batch932-test_isolated_test_runner.py", - "usage": "input", + "usage": "provenance", "git_blob": "34820a8f24678f918f4d0e7a35380d8013fc3495", "sha256": "628391b6abfbc8674ceec1751867a4392f2cc0b5b66886243e139af86cf355ac" }, { "path": "scripts/historical-ci-inputs/ledger-batch970-verify_selected_result.py", - "usage": "input", + "usage": "provenance", "git_blob": "c755b76e0d44ba4917aa94440ebe54daefce5b2a", "sha256": "d7fd929726b326aeeaf0a3996475adec88eee9aac09ae0bebeeaa0bc1fc8f199" }, { "path": "scripts/historical-ci-inputs/ledger-frontier741-ci-verification.md", - "usage": "input", + "usage": "provenance", "git_blob": "7f3c012504187917a728b9fe87043f0fc8cd006a", "sha256": "a854022e0e1d5d4db4d60e586be3ea56005013ef14a1fc06d02bc06e8529c4b0" }, { "path": "scripts/historical-ci-inputs/partial-swap-context.json", - "usage": "input", + "usage": "provenance", "git_blob": "ad65114886bf34a4fd27e79f3be502389e689faa", "sha256": "833a9642f33aeab2ffea17ec9c6b82e0a953f90192b2c82e10bef21538dccba9" }, { "path": "scripts/historical-ci-inputs/partial-swap-network.json", - "usage": "input", + "usage": "provenance", "git_blob": "52075f2463f60af5e16571347f24274fce73a1ea", "sha256": "f3c4be597b2f2136da4ae2cc80c7454f63c90aa01f84e5b8131cee4dd55de815" }, { "path": "scripts/partial_swap/shared.py", - "usage": "input", + "usage": "provenance", "git_blob": "44a0e454c70f9c4b98e258b8443612e6a119904b", "sha256": "5a0646a50b9f3e8ea55168620a78e8853b0ab810517cefc8cfb8696aedee278a" }, { "path": "scripts/replay_historical_check.py", - "usage": "input", + "usage": "provenance", "git_blob": "1e92fff2782970ef71378f594f2350d245a4db26", "sha256": "5467619c78183d3adc82b0cb55af28e5c1a01fca2b0588677816244b53e2bafd" }, { "path": "scripts/research_package.py", - "usage": "input", + "usage": "provenance", "git_blob": "091b4c8f58bac9a9580d76025b887dc5c873d05f", "sha256": "e1256016e7f51827d04fa2179255989f639ae1d97afaa9c16265f85a0c6abd70" }, { "path": "scripts/run_isolated_tests.py", - "usage": "input", + "usage": "provenance", "git_blob": "a96ab35b315ce492e7fbbfd6c5ae211aa066b541", "sha256": "49eb56dd0fc0d8d8ffdb209970a7adf2176223580646f575d5c22e59543b381c" }, { "path": "scripts/verify_selected_result.py", - "usage": "input", + "usage": "provenance", "git_blob": "6882a4700e410dec569b51ae2eaf1a19cc019195", "sha256": "d6b305eac5b9bdb8172c469ad30a1655a60fa0aceac8b1bf610e1b73f51babd8" }, { "path": "tests/test_isolated_test_runner.py", - "usage": "input", + "usage": "provenance", "git_blob": "343b24abf6719b81805eba5a84c74e57634c8288", "sha256": "3a5470d0b139828b90e19bf9583ddeafcd69f8e34f2824664eb3a2958a52e34d" } diff --git a/research/historical-selected-replay-gap/VERIFY.json b/research/historical-selected-replay-gap/VERIFY.json index 98553e72ed..ab7efa3471 100644 --- a/research/historical-selected-replay-gap/VERIFY.json +++ b/research/historical-selected-replay-gap/VERIFY.json @@ -4,36 +4,7 @@ "python": "3.12", "requirements": [], "inputs": [ - "Makefile", - "certificates/partial-swap-network.json", - "docs/ci-verification.md", - "research/clifford-state-performance/SOURCE.json", - "research/community-batch1047-audit/CONTENT-COVERAGE.json", - "research/community-batch1099-audit/CONTENT-COVERAGE.json", - "research/community-batch932-audit/CONTENT-COVERAGE.json", - "research/community-batch970-audit/CONTENT-COVERAGE.json", - "research/community-frontier741-audit/CONTENT-COVERAGE.json", - "research/community-frontier890-audit/CONTENT-COVERAGE.json", - "research/community-hyperplane599-audit/SOURCE.json", - "research/community-k492-audit/SOURCE.json", - "research/community-reconciliation92-audit/MANIFEST.json", - "research/partial-swap-digest/baseline.py", - "research/r420-two-sided-basis/SOURCES.json", - "research/skip-clones/SOURCE.json", - "research/split-skip/SOURCE.json", - "scripts/historical-ci-inputs/Makefile", - "scripts/historical-ci-inputs/ledger-batch932-run_isolated_tests.py", - "scripts/historical-ci-inputs/ledger-batch932-test_isolated_test_runner.py", - "scripts/historical-ci-inputs/ledger-batch970-verify_selected_result.py", - "scripts/historical-ci-inputs/ledger-frontier741-ci-verification.md", - "scripts/historical-ci-inputs/partial-swap-context.json", - "scripts/historical-ci-inputs/partial-swap-network.json", - "scripts/partial_swap/shared.py", - "scripts/replay_historical_check.py", - "scripts/research_package.py", - "scripts/run_isolated_tests.py", - "scripts/verify_selected_result.py", - "tests/test_isolated_test_runner.py" + "scripts/research_package.py" ], "commands": [ { diff --git a/research/historical-selected-replay-gap/verify.py b/research/historical-selected-replay-gap/verify.py index 83b995941a..9d266c5a4e 100644 --- a/research/historical-selected-replay-gap/verify.py +++ b/research/historical-selected-replay-gap/verify.py @@ -6,8 +6,10 @@ """ import hashlib import importlib.util +import json import subprocess import sys +import tempfile from pathlib import Path ROOT = Path(__file__).resolve().parents[2] @@ -61,31 +63,47 @@ def require(ok, message): raise SystemExit(message) -def load_checker(): - path = ROOT / "scripts/replay_historical_check.py" - spec = importlib.util.spec_from_file_location("historical_selected_replay_gap_checker", path) +def load_module(path): + spec = importlib.util.spec_from_file_location(path.stem, path) module = importlib.util.module_from_spec(spec) spec.loader.exec_module(module) return module +def checkout_snapshot(snapshot, sources, runner, env): + paths = [runner.canonical_relative_path(row["path"]) for row in sources["files"]] + git = ["git", "-c", "maintenance.auto=false", "-c", "gc.auto=0", + "-c", "core.autocrlf=false"] + subprocess.run([*git, "clone", "--quiet", "--shared", "--no-tags", "--no-checkout", + "--", str(ROOT), str(snapshot)], cwd=ROOT, env=env, check=True) + subprocess.run([*git, "update-ref", "--no-deref", "HEAD", INSPECTED], + cwd=snapshot, env=env, check=True) + # The pinned planner reads omitted manifests from the sparse HEAD/index. + patterns = "".join(f"/{path.as_posix()}\n" for path in paths) + subprocess.run([*git, "sparse-checkout", "set", "--no-cone", "--stdin"], + cwd=snapshot, env=env, input=patterns.encode("utf-8"), check=True) + subprocess.run([*git, "read-tree", "-mu", "HEAD"], cwd=snapshot, env=env, check=True) + for path, row in zip(paths, sources["files"], strict=True): + require(hashlib.sha256((snapshot / path).read_bytes()).hexdigest() == row["sha256"], + "historical checkout source digest changed: " + path.as_posix()) + + def entries(checker): for name, config in checker.CONFIG.items(): for entry in [config, *config.get("additional_inputs", [])]: yield name, entry -def reject(checker, entry): +def reject(root, checker, entry): try: - checker.authenticated_input(ROOT, entry) + checker.authenticated_input(root, entry) except ValueError as exc: return str(exc) raise SystemExit("historical input was admitted: " + entry["path"]) -def main(): - require(not sys.flags.optimize, "assertions must stay enabled") - checker = load_checker() +def check_snapshot(root, env): + checker = load_module(root / "scripts/replay_historical_check.py") selected = [entry for name, entry in entries(checker) if name == "tooling-ledger" and entry["path"] == SELECTED_PATH] require(len(selected) == 1, "selected-result checker overlay is not unique") @@ -94,7 +112,7 @@ def main(): require(entry["accepted_live_sha256"] == [SELECTED_ACCEPTED], "accepted selected-checker successors changed") frozen = (checker.INPUTS / entry["input"]).read_bytes() - live = (ROOT / SELECTED_PATH).read_bytes() + live = (root / SELECTED_PATH).read_bytes() require(hashlib.sha256(frozen).hexdigest() == SELECTED_PIN, "frozen selected checker bytes changed") require(hashlib.sha256(live).hexdigest() == SELECTED_LIVE, "live selected checker digest changed") require(SELECTED_LIVE not in (SELECTED_PIN, SELECTED_ACCEPTED), "live checker was already admitted") @@ -102,7 +120,7 @@ def main(): # live successor, not a broken comparison. require(SELECTED_PIN in (SELECTED_PIN, *entry["accepted_live_sha256"]), "pin membership control failed") - require(reject(checker, entry) == REJECTIONS[SELECTED_PATH][1], + require(reject(root, checker, entry) == REJECTIONS[SELECTED_PATH][1], "selected checker rejection text changed") counts = {path: 0 for path in REJECTIONS} @@ -110,7 +128,7 @@ def main(): for _name, item in entries(checker): if item["path"] not in REJECTIONS: continue - message = reject(checker, item) + message = reject(root, checker, item) counts[item["path"]] += 1 messages.setdefault(item["path"], message) for path, (count, message) in REJECTIONS.items(): @@ -118,20 +136,31 @@ def main(): require(messages[path] == message, "rejection text changed for " + path) require(sum(counts.values()) == 19, "rejection total changed") ci = [item for _name, item in entries(checker) if item["path"] == CI_PATH] - require(len(ci) == 1 and hashlib.sha256((ROOT / CI_PATH).read_bytes()).hexdigest() == CI_LIVE, + require(len(ci) == 1 and hashlib.sha256((root / CI_PATH).read_bytes()).hexdigest() == CI_LIVE, "selected CI note digest changed") diff = subprocess.check_output( - ["git", "diff", "--name-only", PARENT, INSPECTED], cwd=ROOT, text=True) + ["git", "diff", "--name-only", PARENT, INSPECTED], cwd=root, env=env, text=True) changed = sorted(name for name in diff.splitlines() if name) require(changed == CHANGED, "inspected commit diff changed") - sys.path.insert(0, str(ROOT / "scripts")) - from research_package import plan_details - details = plan_details(ROOT, set(changed)) + planner = load_module(root / "scripts/research_package.py") + details = planner.plan_details(root, set(changed)) require([row["package"] for row in details] == PLAN_PACKAGES, "helper plan selection changed") matched = {name for row in details for names in row["causes"].values() for name in names} require(sorted(set(changed) - matched) == UNMATCHED, "unmatched plan paths changed") - require(plan_details(ROOT, set()) == [], "empty change set selected a package") + require(planner.plan_details(root, set()) == [], "empty change set selected a package") + + +def main(): + require(not sys.flags.optimize, "assertions must stay enabled") + sources = json.loads(Path(__file__).with_name("SOURCES.json").read_bytes()) + require(sources["base_commit"] == INSPECTED, "historical checkout base changed") + runner = load_module(ROOT / "scripts/research_package.py") + env = runner.git_source_env() + with tempfile.TemporaryDirectory(prefix="historical-selected-replay-") as temporary: + snapshot = Path(temporary) / "snapshot" + checkout_snapshot(snapshot, sources, runner, env) + check_snapshot(snapshot, env) print("PASS_HISTORICAL_SELECTED_REPLAY_GAP") print("selected_checker_live=" + SELECTED_LIVE) print("rejections=19 distinct_paths=7 plan_packages=9")