consolidate-main-preserve-science-lfs-cpu-gpu-history

2026-10-01 16:54:47 +08:00
parent 4436241976 5b1d1b72d7
commit 9fde10d970
215 changed files with 8289 additions and 25 deletions
@@ -0,0 +1,122 @@
+"""Explicitly authorized, fail-closed archive/retire operations in the new clone."""
+import argparse
+from datetime import datetime, timezone
+import json
+import os
+from pathlib import Path
+import subprocess
+
+ROOT = Path('/home/qishizhe/digital-drosophila-main-integration-20261001')
+RECOVERY = Path('/home/qishizhe/digital-drosophila-branch-recovery-20261001.git')
+AUDIT = ROOT / 'registry/branch-consolidation-20261001'
+
+
+def require(value, message):
+    if not value:
+        raise RuntimeError(message)
+
+
+def git(*args, cwd=ROOT):
+    # Existing payloads were checked separately. This operation transfers refs
+    # and Git objects only; it neither replaces nor uploads any LFS object.
+    env = dict(os.environ, GIT_LFS_SKIP_SMUDGE='1', GIT_LFS_SKIP_PUSH='1')
+    return subprocess.check_output(['git', *args], cwd=cwd, env=env, text=True).strip()
+
+
+def snapshot():
+    refs = {}
+    default = None
+    for line in git('ls-remote', '--symref', 'origin').splitlines():
+        value, name = line.split('\t')
+        if value.startswith('ref: '):
+            if name == 'HEAD':
+                default = value[5:]
+        else:
+            refs[name] = value
+    return refs, default
+
+
+def write_receipt(name, **data):
+    with (AUDIT / name).open('x') as f:
+        json.dump(dict(schema='branch-consolidation-ref-audit-v1',
+                       created_utc=datetime.now(timezone.utc).isoformat(), **data),
+                  f, indent=2, sort_keys=True)
+        f.write('\n')
+    print(json.dumps(data, indent=2))
+
+
+def main(action):
+    require(Path.cwd().resolve() == ROOT, 'Independent integration clone required')
+    plan = json.loads((AUDIT / 'plan.json').read_text())
+    require(git('remote', 'get-url', 'origin') == plan['remote'], 'Unexpected remote')
+    branches = {'refs/heads/' + name: sha for name, sha in plan['branches'].items()}
+    tags = {plan['archive_tag_prefix'] + name.removeprefix('codex/'): sha
+            for name, sha in plan['branches'].items()}
+    before, default_before = snapshot()
+
+    if action == 'archive':
+        require(not (AUDIT / 'archive-recovery.json').exists(), 'Archive receipt already exists')
+        require(not RECOVERY.exists(), 'Recovery clone already exists; inspect, do not replace')
+        require({k: v for k, v in before.items() if k.startswith('refs/heads/')} == branches,
+                'Remote heads changed since authorized inventory')
+        for tag, sha in tags.items():
+            ref = 'refs/tags/' + tag
+            require(ref not in before, 'Archive tag already exists; inspect before proceeding')
+            require(not git('tag', '--list', tag), 'Local archive tag already exists')
+            git('tag', '-a', tag, sha, '-m',
+                'Archive before user-authorized main consolidation; preserve this exact historical tip. Do not rewrite.')
+        git('push', '--atomic', 'origin', *['refs/tags/' + tag + ':refs/tags/' + tag for tag in tags])
+        after, _ = snapshot()
+        for tag, sha in tags.items():
+            require(after.get('refs/tags/' + tag + '^{}') == sha, 'Remote archived commit differs')
+        git('init', '--bare', str(RECOVERY))
+        git('fetch', '--no-tags', plan['remote'],
+            *['refs/tags/' + tag + ':refs/tags/' + tag for tag in tags], cwd=RECOVERY)
+        recovered = {tag: git('rev-parse', 'refs/tags/' + tag + '^{commit}', cwd=RECOVERY)
+                     for tag in tags}
+        require(recovered == tags, 'Fresh remote recovery failed')
+        git('fsck', '--full', '--no-reflogs', cwd=RECOVERY)
+        write_receipt('archive-recovery.json', pass_all=True, remote=plan['remote'],
+                      remote_heads_before=branches, remote_default_before=default_before,
+                      tags=tags, fresh_remote_recovery_path=str(RECOVERY),
+                      recovered_commits=recovered, git_fsck_pass=True,
+                      lfs_payload_downloaded=False, old_remote_branches_deleted=False)
+
+    elif action == 'retire':
+        require(not (AUDIT / 'remote-cleanup.json').exists(), 'Cleanup receipt already exists')
+        require(json.loads((AUDIT / 'archive-recovery.json').read_text())['pass_all'], 'Recovery not verified')
+        require(json.loads((AUDIT / 'merge-audit-final.json').read_text())['pass_all'], 'Merge not verified')
+        require(default_before == 'refs/heads/main', 'Remote default must already be main')
+        require(git('branch', '--show-current') == 'main', 'Wrong local branch')
+        require(git('status', '--porcelain') == '', 'Integration clone is not clean')
+        main_sha = git('rev-parse', 'HEAD')
+        expected = dict(branches, **{'refs/heads/main': main_sha})
+        require({k: v for k, v in before.items() if k.startswith('refs/heads/')} == expected,
+                'Remote heads changed; stop cleanup')
+        for tag, sha in tags.items():
+            require(before.get('refs/tags/' + tag + '^{}') == sha, 'Remote archive missing/different')
+            require(git('rev-parse', 'refs/tags/' + tag + '^{commit}', cwd=RECOVERY) == sha,
+                    'Recovery archive differs')
+            git('merge-base', '--is-ancestor', sha, main_sha)
+        leases = ['--force-with-lease=' + ref + ':' + sha for ref, sha in branches.items()]
+        # Delete only these seven exact branch refs, atomically and with their
+        # recorded old OIDs. No local refs, tags, commits, worktrees or LFS deletion.
+        git('push', '--atomic', *leases, 'origin', *[':' + ref for ref in branches])
+        after, default_after = snapshot()
+        require({k: v for k, v in after.items() if k.startswith('refs/heads/')} ==
+                {'refs/heads/main': main_sha}, 'Unexpected final heads')
+        require(default_after == 'refs/heads/main', 'Default branch changed unexpectedly')
+        for tag, sha in tags.items():
+            require(after.get('refs/tags/' + tag + '^{}') == sha, 'Archive lost after deletion')
+        write_receipt('remote-cleanup.json', pass_all=True, remote=plan['remote'],
+                      main_commit=main_sha, remote_default=default_after,
+                      deleted_remote_branch_refs=branches, preserved_archive_tags=tags,
+                      remaining_remote_heads={'main': main_sha},
+                      all_old_tips_ancestors_of_main=True, local_branches_deleted=False,
+                      source_worktrees_write_operations=False, lfs_objects_deleted=False)
+
+
+if __name__ == '__main__':
+    p = argparse.ArgumentParser()
+    p.add_argument('action', choices=['archive', 'retire'])
+    main(p.parse_args().action)