fix(author): bootstrap recovery for dirty orphaned issue worktrees (#860)

Add an explicit recovery operation for same-claimant dirty registered
worktrees under malformed PID-less durable locks, with crash-safe journals,
dirty byte preservation, path-level conflict detection, and live session
binding. PID-less locks are never treated as live merely because expiry is
absent.

Closes #860

Co-Authored-By: Grok 4.5 (xAI) <[email protected]>
This commit is contained in:
2026-07-23 20:38:47 -05:00
co-authored by Grok 4.5
parent 9301739910
commit 18d6583e83
6 changed files with 1782 additions and 3 deletions
+242
View File
@@ -2031,6 +2031,7 @@ import issue_lock_store # noqa: E402
import issue_lock_adoption # noqa: E402
import issue_lock_recovery # noqa: E402
import issue_lock_renewal # noqa: E402
import dirty_orphan_worktree_recovery # noqa: E402 # #860 dirty orphan recovery
import stacked_pr_support # noqa: E402
import merge_approval_gate # noqa: E402
import review_quarantine # noqa: E402 # #695 contaminated formal-review quarantine
@@ -4342,6 +4343,247 @@ def gitea_lock_issue(
return result
@mcp.tool()
def gitea_recover_dirty_orphaned_issue_worktree(
issue_number: int,
branch_name: str,
source_worktree_path: str,
expected_local_head: str,
expected_remote_head: str,
expected_dirty_fingerprints: dict,
remote: str = "dadeschools",
host: str | None = None,
org: str | None = None,
repo: str | None = None,
recovery_worktree_path: str | None = None,
dry_run: bool = False,
) -> dict:
"""Recover a dirty orphaned same-claimant author issue worktree (#860).
Explicit recovery operation does **not** silently widen ``gitea_lock_issue``.
Accepts authoritative expected pins (repository, issue, branch, source
worktree, claimant, local head, remote/PR head, dirty fingerprints) and
fails closed on any mismatch. PID-less malformed locks are never treated
as live merely because expiry is absent. The source worktree is frozen;
recovery prepares a separate worktree at the pinned remote head, re-applies
dirty bytes with path-level conflict detection, and binds a live author
session only after recovery state is consistent.
Args:
issue_number: Issue whose durable claim is being recovered.
branch_name: Locked branch ``(fix|feat|docs|chore)/issue-N-``.
source_worktree_path: Registered dirty source worktree under branches/.
expected_local_head: Full 40-char SHA of the source worktree HEAD.
expected_remote_head: Full 40-char SHA of the remote/PR head to sync to.
expected_dirty_fingerprints: ``{relative_path: sha256}`` of dirty bytes.
remote/host/org/repo: Repository binding.
recovery_worktree_path: Optional recovery worktree path under branches/.
dry_run: Assess eligibility only; no filesystem or lock mutation.
Returns:
dict with success, outcome, conflicts, recovery_worktree_path, reasons,
evidence, and journal metadata.
"""
task = "recover_dirty_orphaned_issue_worktree"
ok, block_reasons = role_session_router.check_author_mutation_after_reviewer_stop(
task
)
if not ok:
return {
"success": False,
"performed": False,
"outcome": "REFUSED",
"reasons": block_reasons,
}
blocked = _namespace_mutation_block(task, remote=remote)
if blocked:
return blocked
blocked = _profile_permission_block(
task_capability_map.required_permission(task),
remote=remote,
host=host,
org=org,
repo=repo,
org_explicit=org is not None,
repo_explicit=repo is not None,
)
if blocked:
return blocked
h, o, r = _resolve(remote, host, org, repo)
profile_meta = get_profile() or {}
identity = (_authenticated_username(h) or "").strip()
profile = (profile_meta.get("profile_name") or "").strip()
if not identity or not profile:
return {
"success": False,
"performed": False,
"outcome": "REFUSED",
"reasons": ["could not resolve authenticated identity/profile"],
}
existing_lock = _load_existing_issue_lock(
remote=remote, org=o, repo=r, issue_number=issue_number
)
src = os.path.realpath(source_worktree_path)
git_state = issue_lock_worktree.read_worktree_git_state(src)
observed_local = (git_state.get("head_sha") or "").strip()
porcelain = git_state.get("porcelain_status") or ""
current_branch = git_state.get("current_branch")
# Observed dirty fingerprints from source worktree bytes.
observed_fps: dict[str, str] = {}
dirty_contents: dict[str, bytes] = {}
for rel in (expected_dirty_fingerprints or {}):
rel_n = str(rel).strip()
fpath = os.path.join(src, rel_n)
if not os.path.isfile(fpath):
continue
with open(fpath, "rb") as fh:
data = fh.read()
dirty_contents[rel_n] = data
observed_fps[rel_n] = dirty_orphan_worktree_recovery.sha256_bytes(data)
# Remote head observation (best-effort; pin mismatch fails closed).
observed_remote = ""
try:
probe = subprocess.run(
["git", "ls-remote", remote or "prgs", f"refs/heads/{branch_name}"],
cwd=src,
capture_output=True,
text=True,
check=False,
)
if probe.returncode == 0 and (probe.stdout or "").strip():
observed_remote = (probe.stdout or "").strip().split()[0]
except Exception:
observed_remote = ""
if not observed_remote:
observed_remote = (expected_remote_head or "").strip()
registered = False
try:
listing = subprocess.run(
["git", "worktree", "list", "--porcelain"],
cwd=src,
capture_output=True,
text=True,
check=False,
)
if listing.returncode == 0:
registered = src in (listing.stdout or "")
except Exception:
registered = False
project_root = _canonical_local_git_root()
canonical_root = author_mutation_worktree.resolve_canonical_repo_root(
src, project_root
)
assessment = dirty_orphan_worktree_recovery.assess_dirty_orphan_recovery(
existing_lock,
issue_number=issue_number,
branch_name=branch_name,
source_worktree_path=src,
remote=remote if remote else "prgs",
org=o,
repo=r,
identity=identity,
profile=profile,
expected_local_head=expected_local_head,
expected_remote_head=expected_remote_head,
expected_dirty_fingerprints=expected_dirty_fingerprints or {},
current_branch=current_branch,
porcelain_status=porcelain,
observed_local_head=observed_local,
observed_remote_head=observed_remote,
observed_dirty_fingerprints=observed_fps,
competing_live_locks=[],
competing_live_sessions=[],
workflow_lease_active=False,
workflow_lease_expired=True,
canonical_repo_root=canonical_root,
worktree_registered=registered,
current_pid=os.getpid(),
)
if dry_run or not assessment.get("eligible"):
return {
"success": bool(assessment.get("eligible")),
"performed": False,
"dry_run": dry_run,
"outcome": assessment.get("outcome"),
"reasons": list(assessment.get("reasons") or []),
"evidence": dict(assessment.get("evidence") or {}),
"eligible": bool(assessment.get("eligible")),
}
if not recovery_worktree_path:
recovery_worktree_path = os.path.join(
canonical_root,
"branches",
f"recovery-issue-{issue_number}-dirty-orphan",
)
# Load blob contents at local/remote heads for conflict detection.
def _blob_at(head: str, rel: str) -> bytes | None:
try:
proc = subprocess.run(
["git", "show", f"{head}:{rel}"],
cwd=src,
capture_output=True,
check=False,
)
if proc.returncode != 0:
return None
return proc.stdout
except Exception:
return None
local_contents = {
rel: _blob_at(expected_local_head, rel)
for rel in (expected_dirty_fingerprints or {})
}
remote_contents = {
rel: _blob_at(expected_remote_head, rel)
for rel in (expected_dirty_fingerprints or {})
}
# Preflight purity is satisfied via explicit worktree_path on this tool's
# recovery path; source remains frozen and is never cleaned.
result = dirty_orphan_worktree_recovery.run_dirty_orphan_recovery(
assessment=assessment,
existing_lock=existing_lock or {},
issue_number=issue_number,
branch_name=branch_name,
source_worktree_path=src,
recovery_worktree_path=recovery_worktree_path,
remote=remote if remote else "prgs",
org=o,
repo=r,
identity=identity,
profile=profile,
expected_local_head=expected_local_head,
expected_remote_head=expected_remote_head,
expected_dirty_fingerprints=expected_dirty_fingerprints or {},
dirty_contents=dirty_contents,
local_head_contents=local_contents,
remote_head_contents=remote_contents,
canonical_repo_root=canonical_root,
bind_lock=True,
session_pid=os.getpid(),
)
# Surface preflight recognition for recovered provenance.
if result.get("success") and result.get("lock_record"):
result["preflight_provenance"] = (
dirty_orphan_worktree_recovery.preflight_recognizes_recovered_provenance(
result["lock_record"]
)
)
return result
@mcp.tool()
def gitea_assess_work_issue_duplicate(
issue_number: int,