Register all seven public Speedrun cohorts with verifiable boundaries

scripts/audit-ai-research.py

@@ -4,7 +4,7 @@ from collections import Counter
 import json
 from pathlib import Path
 import sys
-from urllib.parse import urlsplit
+from urllib.parse import parse_qs, urlsplit
 
 ROOT = Path(__file__).resolve().parents[1]
 DATA = json.loads((ROOT / 'content/research/ai-companies.seed.json').read_text())
@@ -49,6 +49,27 @@ def source_register():
             assert roster['defaultCohort'] == 'SR007' and roster['next'] is None
             assert len(batch['records']) == roster['recordCount'] == roster['reportedCount']
             assert len({row['url'] for row in batch['records']}) == roster['recordCount']
+        if source['id'] == 'S14' and source.get('publicRosterAudits'):
+            audits = source['publicRosterAudits']
+            assert {a['cohort'] for a in audits} == {f'SR{i:03d}' for i in range(1, 8)}
+            assert len(audits) == 7
+            profile_urls = []
+            for audit in audits:
+                batch = next(b for b in DATA['candidateBatches'] if b['id'] == audit['candidateBatchId'])
+                query = parse_qs(urlsplit(audit['url']).query)
+                assert urlsplit(audit['url']).netloc == 'speedrun.a16z.com'
+                assert query == {'limit': ['100'], 'offset': ['0'], 'cohort': [audit['cohort']]}
+                assert urlsplit(audit['url']).path == '/api/companies/companyparams'
+                assert audit['httpStatus'] == 200 and audit['accessedAt'] <= DATA['asOf']
+                assert audit['next'] is None and audit['previous'] is None
+                assert len(batch['records']) == audit['recordCount'] == audit['reportedCount']
+                assert audit['uniquePublicIds'] == audit['uniqueSlugs'] == audit['recordCount']
+                assert len(audit['responseSha256']) == 64 and all(c in '0123456789abcdef' for c in audit['responseSha256'])
+                assert batch['sourceId'] == 'S14' and not batch['complete']
+                proof = next(e for e in DATA['evidence'] if e['id'] == audit['evidenceId'])
+                assert proof['url'] == audit['url'] and proof['companyId'] is None
+                profile_urls.extend(row['url'] for row in batch['records'])
+            assert len(profile_urls) == len(set(profile_urls)), 'duplicate profiles across public cohorts'
         if source['url']:
             assert urlsplit(source['url']).scheme in {'http', 'https'} and urlsplit(source['url']).netloc
         for host in source['hosts']: