From e5a5c17e52b12e8a47c4b3af1e6afda76c51c0dd Mon Sep 17 00:00:00 2001 From: N0zoM1z0 <161784452+N0zoM1z0@users.noreply.github.com> Date: Tue, 13 Oct 2026 18:13:47 +0000 Subject: [PATCH] fix(perf): verify retained parent digest identity Require declared summary/page parent digests to match their linked Evidence IDs at SDK acceptance and factual grading. Keep the fixture faithful to the producer and reject mismatched, malformed or missing parent digests. Original delivery observations and measured model data remain unchanged. Validation: 30 context/grading tests, six actual SDK before/after fault and normal-control probes, plus four stored original-model factual regrades. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com> Co-authored-by: Kaoru0822 <208281322+kaoru0822-kitauji@users.noreply.github.com> --- experiments/analysis-efficiency/measure.mjs | 5 +++++ .../analysis-efficiency/pcap-small-captures.md | 10 ++++++++-- experiments/analysis-efficiency/review-model.py | 1 + .../analysis-efficiency/test_codex_context.py | 14 ++++++++++++++ 4 files changed, 28 insertions(+), 2 deletions(-) diff --git a/experiments/analysis-efficiency/measure.mjs b/experiments/analysis-efficiency/measure.mjs index 11faa451b..613fa6ca1 100644 --- a/experiments/analysis-efficiency/measure.mjs +++ b/experiments/analysis-efficiency/measure.mjs @@ -575,6 +575,11 @@ const pcapObservation = (evidence, requestedView) => { !evidence.evidence_links.includes(value.parent_evidence_id)) ) throw new Error("PCAP retained parent lacks a distinct Evidence link"); + if ( + requestedView && + value.parent_digest !== value.parent_evidence_id.slice(3) + ) + throw new Error("PCAP retained parent digest differs from its identity"); const parameters = requestedView ? { parent_evidence_id: value.parent_evidence_id, view: requestedView } : { path: values.path }; diff --git a/experiments/analysis-efficiency/pcap-small-captures.md b/experiments/analysis-efficiency/pcap-small-captures.md index ea944caef..e36ff6456 100644 --- a/experiments/analysis-efficiency/pcap-small-captures.md +++ b/experiments/analysis-efficiency/pcap-small-captures.md @@ -126,7 +126,7 @@ validated. Both real CLI complete results match full MCP normalized results, subjects, parameters, IDs and limitations. Portable CLI summary/URI views match MCP retained normalized facts and subjects; source forms/caller parameters remain distinct. -Source bytes stay unchanged. Twenty-nine context/grading regressions pass, including +Source bytes stay unchanged. Thirty context/grading regressions pass, including cited complete metadata/counts/UTF-16 diagnostics and exact ordered response ID lists that reject parent lookups, duplicates and nested representations. URI prefix coverage must come from its cited page, even if an uncited page has the @@ -159,7 +159,7 @@ the preceding driver accepts inconsistent coverage, while the corrected driver rejects wrong status, next offset or exhaustion. Unmodified exhausted and continuable URI pages still pass. The grader also requires each cited receipt's subject digest and local path to identify the reference capture, and uses the -reference page's verified coverage. Twenty-nine grading/context regressions pass, +reference page's verified coverage. Thirty grading/context regressions pass, including missing or malformed subjects and faithful but inconsistent coverage; all four original model answers still pass factual regrading. Strict resource grades remain false where terminal whole-scope counters are unknown. @@ -244,3 +244,9 @@ faithful receipts with missing or incorrect outer artifact identities. Private mutations over actual SDK replies reproduce the previous false success and verify rejection after the shared observation guard; normal deliveries and all four original model answers retain their recorded facts. + +Declared retained parent digests must match the digest encoded in the linked +parent Evidence ID for both summary and page views. SDK acceptance and factual +grading reject mismatches and missing digests while preserving complete +deliveries. Before/after private actual-reply mutations verify both view roles; +unmodified deliveries and four stored original-model factual regrades pass. diff --git a/experiments/analysis-efficiency/review-model.py b/experiments/analysis-efficiency/review-model.py index 6c8dee8e6..580eba19e 100644 --- a/experiments/analysis-efficiency/review-model.py +++ b/experiments/analysis-efficiency/review-model.py @@ -300,6 +300,7 @@ def main(): len(cited) == 1 or (len(cited) == 2 and all( isinstance(record['normalized_result'].get('parent_evidence_id'), str) and re.fullmatch(r'ev_[a-f0-9]{64}', record['normalized_result']['parent_evidence_id']) + and record['normalized_result'].get('parent_digest') == record['normalized_result']['parent_evidence_id'][3:] and record['normalized_result']['parent_evidence_id'] != record['evidence_id'] and isinstance(record.get('evidence_links'), list) and record['normalized_result']['parent_evidence_id'] in record['evidence_links'] diff --git a/experiments/analysis-efficiency/test_codex_context.py b/experiments/analysis-efficiency/test_codex_context.py index 326f27f02..37152cb6c 100644 --- a/experiments/analysis-efficiency/test_codex_context.py +++ b/experiments/analysis-efficiency/test_codex_context.py @@ -100,6 +100,7 @@ class PcapGraderWorkflowTests(unittest.TestCase): 'source_coverage': 'complete', 'artifact': capture['target'], 'limitations': ['source', 'view'], 'unknowns': ['unrecorded traffic']}} for record in [summary, page]: + record['normalized_result']['parent_digest'] = parent[3:] record['parameters'] = {'parent_evidence_id': parent, 'view': copy.deepcopy(record['normalized_result']['view'])} observations = [self.observation(value) for value in [summary, page]] reference = {'artifact_sha256': 'd' * 64, 'capture': capture, @@ -355,6 +356,19 @@ class PcapGraderWorkflowTests(unittest.TestCase): answer, records, reference = self.fixture();records[index]['normalized_result'][field] = wrong self.assertFalse(self.grade(answer, records, reference, tools)['all_factual_checks_pass']) + def test_retained_parent_digest_must_match_its_declared_identity(self): + for index in [0, 1]: + for digest in [None, {}, [], True, 'digest', 'e' * 64]: + with self.subTest(index=index, digest=digest): + answer, records, reference = self.fixture() + records[index]['normalized_result']['parent_digest'] = digest + report = self.grade(answer, records, reference) + self.assertTrue(report['factual_checks']['pcap_original_delivery_observations']) + self.assertFalse(report['all_factual_checks_pass']) + answer, records, reference = self.fixture() + records[index]['normalized_result'].pop('parent_digest') + self.assertFalse(self.grade(answer, records, reference)['all_factual_checks_pass']) + def test_summary_outer_artifact_must_identify_the_selected_capture(self): for wrong in [None, {}, [], 'artifact', {'path': '/fixture/other.pcapng', 'sha256': 'd' * 64},