Compare commits

..
Author SHA1 Message Date
sysadminandClaude Opus 4.8 fe259e6d38 fix(worktree-audit): make cleanup audit merged-PR aware for issue worktrees (Closes #858)
gitea_audit_worktree_cleanup had no PR linkage. Issue worktrees therefore
reported pr_number=null and classified as active_issue_work with
removable=false permanently, even once their PR was merged and the head was
already contained in master. Observed on live master 9301739910: 42
issue_work worktrees, 0 removable, 0 with pr_number populated, while
gitea_reconcile_merged_cleanups reported the same worktree safe to remove.

Two independent gaps caused it:

* build_worktree_metadata was never given a pr_number, and only open PRs were
  fetched, so no owning-PR evidence existed at all.
* clean_stale_removable was unreachable for issue_work: it required
  ttl_expired, derived from a last_used_at that nothing populates, and
  is_ttl_expired fail-safes to False when the timestamp is unknown.

This adds deterministic merged-PR linkage and gates removal on the complete
cleanup policy:

* build_pr_index / resolve_owning_pr link a worktree branch to exactly one
  owning PR. Competing PRs on one branch, a still-open owner, a head-branch
  mismatch, or missing PR state all fail closed while still reporting the
  resolved pr_number.
* assess_merged_pr_worktree_cleanup requires all of: conclusive merged
  ownership, branch agreement, containment of the head in authoritative
  master, no open/competing PR, no active lease, no issue lock, no live
  session, a clean tree, and a non-protected checkout. Unknown state blocks.
* Containment reuses merged_cleanup_reconcile.is_head_ancestor_of_ref so the
  audit and the PR-scoped reconciler agree on what "already landed" means.

Lease evidence is now supplied. audit_branches_directory already accepted
leased_branches but the MCP tool never passed it, so has_active_lease was
false for every worktree in a live run. That was inert only while issue
worktrees could never become removable; it is wired to authoritative
control-plane leases here, scoped so a lease on issue N protects that issue's
work worktree and not a baseline or review tree merely named after it.

Issue work no longer becomes removable on TTL age alone, since age is not
proof that a branch landed and would otherwise reclaim a worktree holding
unmerged commits. conflict_fix keeps its existing TTL behaviour, and review,
baseline, merge-simulation, detached, dirty, open-PR, and protected
classifications are unchanged.

The assessor still performs no deletion and gains no cleanup mutation. This
is assessor-side only and does not implement the PR-scoped executor or the
expired-lease reclaim policy tracked separately by #855.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
2026-07-23 21:19:32 -04:00
11 changed files with 936 additions and 1963 deletions
File diff suppressed because it is too large Load Diff
+78 -281
View File
@@ -1450,7 +1450,7 @@ def verify_preflight_purity(
dirty_files = sorted(
_parse_porcelain_entries(_get_workspace_porcelain(workspace))
)
if dirty_files and task != "commit_files":
if dirty_files:
raise RuntimeError(
nwb.format_namespace_workspace_binding_error(
role_kind=role,
@@ -2031,7 +2031,6 @@ 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
@@ -4343,280 +4342,6 @@ 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 = ""
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
)
competing_locks: list[dict] = []
try:
all_live = issue_lock_store.list_live_locks()
for l in all_live:
if l.get("issue_number") == issue_number:
wt = l.get("worktree_path")
if not wt or not issue_lock_store._same_realpath(wt, src):
competing_locks.append(l)
except Exception:
competing_locks = []
wf_active = False
wf_expired = True
try:
db, _ = _control_plane_db_or_error()
if db is not None:
active_leases_data = lease_lifecycle.list_active_leases(
db,
remote=remote if remote in REMOTES else remote,
org=o,
repo=r,
)
leases_list = active_leases_data.get("leases") or []
for l in leases_list:
if l.get("work_number") == issue_number and l.get("work_kind") == "issue":
fresh = l.get("freshness") or {}
if fresh.get("status") == "active":
wf_active = True
wf_expired = False
elif fresh.get("status") in ("expired", "stale_dead_process"):
wf_active = False
wf_expired = True
except Exception:
pass
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_locks,
competing_live_sessions=[],
workflow_lease_active=wf_active,
workflow_lease_expired=wf_expired,
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,
@@ -11909,6 +11634,7 @@ def gitea_audit_worktree_cleanup(
org: str | None = None,
repo: str | None = None,
ttl_hours: float = worktree_cleanup_audit.DEFAULT_TTL_HOURS,
merged_pr_limit: int = 200,
) -> dict:
"""Read-only: classify every session-owned worktree under ``branches/`` (#401).
@@ -11919,17 +11645,26 @@ def gitea_audit_worktree_cleanup(
the active issue-lock branch is read from the local lock file and treated
as active work. Deletes nothing and mutates no Gitea state.
Fails closed if the live open-PR list cannot be fetched: without it,
removability cannot be proven, so no candidates are returned.
Merged PRs are fetched as well, so an issue worktree can be linked to the
PR that owns its branch (#858). Such a worktree only becomes removable
when that owning PR is unambiguous and merged, the worktree head is
already contained in authoritative master, and nothing else protects it
no open or competing PR, lease, issue lock, live session, dirty file, or
protected/control checkout. Anything unproven keeps it classified as
active issue work.
Fails closed if the live open-PR list, the merged-PR list, or the
control-plane lease state cannot be read: without them removability
cannot be proven, so no candidates are returned.
Args:
remote: Known instance 'dadeschools' or 'prgs'.
host: Override the Gitea host.
org: Override the owner/organization.
repo: Override the repository name.
ttl_hours: Age (hours) after which a clean issue/conflict-fix
worktree becomes stale-removable (default from
GITEA_WORKTREE_TTL_HOURS).
ttl_hours: Age (hours) after which a clean conflict-fix worktree
becomes stale-removable (default from GITEA_WORKTREE_TTL_HOURS).
merged_pr_limit: Max closed PRs scanned for merged-PR ownership.
Returns:
dict with per-worktree classifications, counts, removable
@@ -11965,22 +11700,84 @@ def gitea_audit_worktree_cleanup(
if (pr.get("head") or {}).get("ref")
}
# #858: merged PRs are the ownership evidence that lets a landed issue
# worktree stop being reported as active work. Without them the audit can
# never agree with the PR-scoped reconciler, so treat a fetch failure the
# same way an open-PR fetch failure is treated: fail closed.
try:
closed_prs = api_get_all(
f"{repo_api_url(h, o, r)}/pulls?state=closed", auth, limit=merged_pr_limit
)
except Exception as exc:
return {
"success": False,
"performed": False,
"open_pr_state_verified": True,
"merged_pr_state_verified": False,
"reasons": [
"could not fetch merged PRs; worktree ownership unverified "
f"(fail closed): {_redact(str(exc))}"
],
}
merged_prs = [pr for pr in closed_prs if (pr.get("merged") or pr.get("merged_at"))]
pr_index = worktree_cleanup_audit.build_pr_index(list(open_prs) + merged_prs)
# #858: the auditor already accepted lease evidence but nothing ever
# supplied it, so every worktree looked unleased. Removability is now
# reachable for issue worktrees, so authoritative control-plane leases
# must be readable or the audit fails closed.
db, lease_errs = _control_plane_db_or_error()
if db is None:
return {
"success": False,
"performed": False,
"open_pr_state_verified": True,
"merged_pr_state_verified": True,
"lease_state_verified": False,
"reasons": [
"could not read control-plane leases; worktree protection "
"unverified (fail closed)",
*lease_errs,
],
}
lease_result = lease_lifecycle.list_active_leases(
db, remote=remote, org=o, repo=r, include_non_active=False, limit=500
)
leased_issue_numbers: set[int] = set()
live_session_paths: set[str] = set()
for lease in lease_result.get("leases") or []:
if lease.get("work_kind") == "issue" and lease.get("work_number") is not None:
try:
leased_issue_numbers.add(int(lease["work_number"]))
except (TypeError, ValueError):
pass
if lease.get("worktree_path"):
live_session_paths.add(str(lease["worktree_path"]))
active_issue_branches: set[str] = set()
lock = merged_cleanup_reconcile.read_issue_lock(ISSUE_LOCK_FILE)
if lock and lock.get("branch_name"):
active_issue_branches.add(str(lock["branch_name"]).strip())
master_ref = f"{remote}/master" if remote in REMOTES else "origin/master"
report = worktree_cleanup_audit.audit_branches_directory(
_canonical_local_git_root(),
open_pr_branches=open_pr_branches,
active_issue_branches=active_issue_branches,
now=datetime.now(timezone.utc),
ttl_hours=ttl_hours,
pr_index=pr_index,
leased_issue_numbers=leased_issue_numbers,
live_session_paths=live_session_paths,
master_ref=master_ref,
)
return {
"success": True,
"performed": False,
"open_pr_state_verified": True,
"merged_pr_state_verified": True,
"lease_state_verified": True,
"master_ref": master_ref,
"task_mode": "work-issue",
**report,
}
-2
View File
@@ -16,13 +16,11 @@ ISSUE_LOCK_FILE = os.environ.get("GITEA_ISSUE_LOCK_FILE", "/tmp/gitea_issue_lock
SOURCE_LOCK_ISSUE = "gitea_lock_issue"
SOURCE_LOCK_ADOPTION = "gitea_lock_issue_adoption"
SOURCE_OPERATOR_OVERRIDE = "operator_override"
SOURCE_RECOVER_DIRTY_ORPHANED = "gitea_recover_dirty_orphaned_issue_worktree"
SANCTIONED_LOCK_SOURCES = frozenset({
SOURCE_LOCK_ISSUE,
SOURCE_LOCK_ADOPTION,
SOURCE_OPERATOR_OVERRIDE,
SOURCE_RECOVER_DIRTY_ORPHANED,
})
_OPERATOR_OVERRIDE_ENV = "GITEA_ISSUE_LOCK_OPERATOR_OVERRIDE"
+4 -81
View File
@@ -169,7 +169,6 @@ def bind_session_lock(
*,
expected_generation: int | None = None,
renewal_sanctioned: bool = False,
recovery_sanctioned: bool = False,
) -> str:
"""Persist a keyed lock and bind it to the current process session.
@@ -214,9 +213,7 @@ def bind_session_lock(
try:
with _exclusive_file_lock(sentinel):
existing = read_lock_file(path)
overwrite_block = assess_foreign_lock_overwrite(
existing, record, recovery_sanctioned=recovery_sanctioned
)
overwrite_block = assess_foreign_lock_overwrite(existing, record)
if overwrite_block:
raise RuntimeError(overwrite_block)
lease_block = assess_same_issue_lease_conflict(
@@ -225,7 +222,6 @@ def bind_session_lock(
branch_name=str(record.get("branch_name") or ""),
worktree_path=str(record.get("worktree_path") or ""),
renewal_sanctioned=renewal_sanctioned,
recovery_sanctioned=recovery_sanctioned,
)
if lease_block:
raise RuntimeError(lease_block)
@@ -384,16 +380,7 @@ def assess_lock_freshness(
pid = lock_data.get("session_pid")
if pid is None:
pid = lock_data.get("pid")
pid_missing = pid is None or str(pid).strip() == ""
try:
pid_int = int(pid) if not pid_missing else None
if pid_int is not None and pid_int <= 0:
pid_missing = True
pid_int = None
except (TypeError, ValueError):
pid_missing = True
pid_int = None
pid_alive = is_process_alive(pid_int) if pid_int is not None else False
pid_alive = is_process_alive(pid) if pid is not None else False
if expires_at and expires_at <= current:
return {
@@ -402,36 +389,15 @@ def assess_lock_freshness(
"stale": True,
"reason": f"lease expired at {expires_at.isoformat()}",
"pid_alive": pid_alive,
"pid_missing": pid_missing,
}
# #860: a PID-less lock must never be considered live merely because
# expiration / heartbeat fields are absent. Missing PID is insufficient
# evidence of a live owner; treat as malformed/stale so recovery routes
# can evaluate corroborating pins instead of blocking on a false live flag.
if pid_missing:
return {
"status": "malformed",
"live": False,
"stale": True,
"reason": (
"lock has no usable session pid; cannot prove live ownership "
"(PID-less locks are never live by missing expiry alone)"
),
"pid_alive": False,
"pid_missing": True,
"heartbeat_at": heartbeat_at.isoformat() if heartbeat_at else None,
"expires_at": expires_at.isoformat() if expires_at else None,
}
if pid_int is not None and not pid_alive:
if pid is not None and not pid_alive:
return {
"status": "stale",
"live": False,
"stale": True,
"reason": f"owner pid {pid_int} is not alive",
"reason": f"owner pid {pid} is not alive",
"pid_alive": False,
"pid_missing": False,
}
return {
@@ -440,7 +406,6 @@ def assess_lock_freshness(
"stale": False,
"reason": "lock heartbeat and lease are fresh",
"pid_alive": pid_alive,
"pid_missing": False,
"heartbeat_at": heartbeat_at.isoformat() if heartbeat_at else None,
"expires_at": expires_at.isoformat() if expires_at else None,
}
@@ -521,7 +486,6 @@ def assess_same_issue_lease_conflict(
worktree_path: str,
operation_type: str = AUTHOR_ISSUE_WORK_LEASE,
renewal_sanctioned: bool = False,
recovery_sanctioned: bool = False,
now: datetime | None = None,
) -> str | None:
"""Return a fail-closed error when a competing live lease blocks acquisition.
@@ -553,8 +517,6 @@ def assess_same_issue_lease_conflict(
existing_branch == branch_name
and _same_realpath(str(existing_worktree or ""), worktree_path)
)
if recovery_sanctioned and existing_issue == issue_number and existing_branch == branch_name:
return None
if is_lease_expired(existing_lock, now=now):
# #760 AC1/AC2: exact-owner renewal is a different disposition from
# foreign takeover and is evaluated first. Before this, both branches
@@ -585,26 +547,10 @@ def assess_same_issue_lease_conflict(
)
def _lock_claimant(lock: dict[str, Any] | None) -> dict[str, str]:
if not isinstance(lock, dict):
return {}
claimant = lock.get("claimant")
if not isinstance(claimant, dict):
lease = lock.get("work_lease")
claimant = lease.get("claimant") if isinstance(lease, dict) else None
if not isinstance(claimant, dict):
return {}
return {
"username": str(claimant.get("username") or ""),
"profile": str(claimant.get("profile") or ""),
}
def assess_foreign_lock_overwrite(
existing_lock: dict[str, Any] | None,
incoming_lock: dict[str, Any],
*,
recovery_sanctioned: bool = False,
now: datetime | None = None,
) -> str | None:
"""Block writes that would clobber an unrelated live lease on the same key."""
@@ -619,31 +565,8 @@ def assess_foreign_lock_overwrite(
)
if same_issue and same_branch and same_worktree:
return None
existing_claimant = _lock_claimant(existing_lock)
incoming_claimant = _lock_claimant(incoming_lock)
same_claimant = (
bool(existing_claimant.get("username"))
and existing_claimant.get("username") == incoming_claimant.get("username")
and existing_claimant.get("profile") == incoming_claimant.get("profile")
)
if recovery_sanctioned and same_issue and same_branch and same_claimant:
return None
if not is_lease_live(existing_lock, now=now):
# #860 F8: A non-live or PID-less lock still blocks foreign overwrite
# unless same claimant or sanctioned reclaim is proven.
if not same_claimant and same_issue:
reclaim = assess_expired_lock_reclaim(existing_lock, now=now)
if not reclaim.get("reclaim_allowed"):
return (
"Refusing foreign overwrite of non-live issue lock "
f"(issue #{existing_lock.get('issue_number')}, owner '{existing_claimant.get('username')}') "
"without sanctioned reclaim proof (fail closed)"
)
return None
return (
"Refusing to overwrite a live foreign issue lock "
f"(issue #{existing_lock.get('issue_number')}, "
+8 -10
View File
@@ -43,21 +43,19 @@ repo_root="$(cd "$script_dir/.." && pwd)"
# Enforce issue-linked, traceable branch names (issue → branch → worktree → PR).
if [[ "$allow_unlinked" -eq 0 ]]; then
if [[ "$dry_run" -eq 0 ]] && [[ ! "$branch" =~ ^review/pr-[0-9]+-.+ ]]; then
locked_branch=$(python3 -c "
locked_branch=$(python3 -c "
import sys
sys.path.insert(0, '$repo_root')
import issue_lock_store
print(issue_lock_store.resolve_locked_branch_for_session('$branch'))
")
if [[ -z "$locked_branch" ]]; then
echo "Error: No session issue lock is bound. Call gitea_lock_issue before branch creation (fail closed)." >&2
exit 2
fi
if [[ "$branch" != "$locked_branch" ]]; then
echo "Error: Requested branch '$branch' does not match locked branch '$locked_branch' (fail closed)." >&2
exit 2
fi
if [[ -z "$locked_branch" ]]; then
echo "Error: No session issue lock is bound. Call gitea_lock_issue before branch creation (fail closed)." >&2
exit 2
fi
if [[ "$branch" != "$locked_branch" ]]; then
echo "Error: Requested branch '$branch' does not match locked branch '$locked_branch' (fail closed)." >&2
exit 2
fi
if [[ "$branch" =~ ^(fix|feat|docs|chore)/issue-[0-9]+-.+ ]] \
-14
View File
@@ -32,15 +32,6 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
"permission": "gitea.issue.comment",
"role": "author",
},
# #860: dirty orphaned same-claimant worktree recovery (explicit operation).
"recover_dirty_orphaned_issue_worktree": {
"permission": "gitea.issue.comment",
"role": "author",
},
"gitea_recover_dirty_orphaned_issue_worktree": {
"permission": "gitea.issue.comment",
"role": "author",
},
"set_issue_labels": {
"permission": "gitea.issue.comment",
"role": "author",
@@ -486,11 +477,6 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
# merger lease (#763).
_PREFLIGHT_TASK_TRANSITIONS = frozenset({
("review_pr", "acquire_reviewer_pr_lease"),
("work_issue", "lock_issue"),
("work_issue", "recover_dirty_orphaned_issue_worktree"),
("work_issue", "gitea_recover_dirty_orphaned_issue_worktree"),
("work_issue", "commit_files"),
("work_issue", "gitea_commit_files"),
})
@@ -1,483 +0,0 @@
"""Synthetic regression coverage for dirty orphaned worktree recovery (#860).
Modeled on the #850 / #855 shape without mutating their real state.
"""
from __future__ import annotations
import json
import os
import shutil
import tempfile
import unittest
from unittest import mock
import dirty_orphan_worktree_recovery as dorec
import issue_lock_store
DEAD_PID = 999_999_999
LIVE_PID = os.getpid()
BRANCH = "fix/issue-901-dirty-orphan"
SOURCE_WT = "/repo/branches/issue-901-dirty-orphan"
RECOVERY_WT_NAME = "recovery-issue-901-dirty-orphan"
LOCAL_HEAD = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
REMOTE_HEAD = "bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb"
OTHER_HEAD = "cccccccccccccccccccccccccccccccccccccccc"
FP_A = dorec.sha256_bytes(b"dirty-a")
FP_B = dorec.sha256_bytes(b"dirty-b")
FP_C = dorec.sha256_bytes(b"dirty-c-conflict")
def durable_lock(**overrides):
"""#850-shaped PID-less malformed same-claimant lock."""
lock = {
"issue_number": 901,
"branch_name": BRANCH,
"worktree_path": SOURCE_WT,
"remote": "prgs",
"org": "Example-Org",
"repo": "Example-Repo",
# intentionally no pid / session_pid / work_lease expiry
"claimant": {"username": "author-user", "profile": "prgs-author"},
}
lock.update(overrides)
return lock
def base_kwargs(**overrides):
kwargs = {
"issue_number": 901,
"branch_name": BRANCH,
"source_worktree_path": SOURCE_WT,
"remote": "prgs",
"org": "Example-Org",
"repo": "Example-Repo",
"identity": "author-user",
"profile": "prgs-author",
"expected_local_head": LOCAL_HEAD,
"expected_remote_head": REMOTE_HEAD,
"expected_dirty_fingerprints": {"a.py": FP_A, "b.py": FP_B},
"current_branch": BRANCH,
"porcelain_status": " M a.py\n M b.py\n",
"observed_local_head": LOCAL_HEAD,
"observed_remote_head": REMOTE_HEAD,
"observed_dirty_fingerprints": {"a.py": FP_A, "b.py": FP_B},
"competing_live_locks": [],
"competing_live_sessions": [],
"workflow_lease_active": False,
"workflow_lease_expired": True,
"canonical_repo_root": "/repo",
"worktree_registered": True,
"current_pid": LIVE_PID,
}
kwargs.update(overrides)
return kwargs
def assess(lock=None, **overrides):
return dorec.assess_dirty_orphan_recovery(
durable_lock() if lock is None else lock, **base_kwargs(**overrides)
)
class FreshnessPidLess(unittest.TestCase):
def test_pid_less_lock_is_not_live(self):
freshness = issue_lock_store.assess_lock_freshness(durable_lock())
self.assertFalse(freshness["live"])
self.assertTrue(freshness.get("pid_missing"))
self.assertEqual(freshness["status"], "malformed")
def test_pid_less_with_far_future_expiry_still_not_live(self):
lock = durable_lock(
work_lease={
"operation_type": "author_issue_work",
"expires_at": "2999-01-01T00:00:00Z",
"last_heartbeat_at": "2999-01-01T00:00:00Z",
}
)
freshness = issue_lock_store.assess_lock_freshness(lock)
self.assertFalse(freshness["live"])
self.assertTrue(freshness.get("pid_missing"))
class EligibilityGranted(unittest.TestCase):
def test_dead_same_claimant_pid_less_dirty(self):
result = assess()
self.assertEqual(result["outcome"], dorec.ELIGIBLE)
self.assertTrue(result["eligible"])
def test_expired_workflow_lease_corroboration(self):
result = assess(workflow_lease_active=False, workflow_lease_expired=True)
self.assertTrue(result["eligible"])
def test_older_local_newer_remote_heads(self):
result = assess()
self.assertTrue(result["evidence"].get("heads_diverged"))
self.assertTrue(result["eligible"])
class EligibilityRefused(unittest.TestCase):
def test_active_owner_with_pid(self):
lock = durable_lock(pid=LIVE_PID, session_pid=LIVE_PID)
result = assess(lock=lock, owner_process_alive_override=True)
self.assertEqual(result["outcome"], dorec.REFUSED)
self.assertFalse(result["eligible"])
self.assertTrue(any("alive" in r for r in result["reasons"]))
def test_foreign_claimant(self):
result = assess(identity="other-user")
self.assertEqual(result["outcome"], dorec.REFUSED)
self.assertTrue(any("foreign claimant identity" in r for r in result["reasons"]))
def test_foreign_profile(self):
result = assess(profile="prgs-reviewer")
self.assertEqual(result["outcome"], dorec.REFUSED)
def test_fingerprint_mismatch(self):
result = assess(observed_dirty_fingerprints={"a.py": "0" * 64, "b.py": FP_B})
self.assertEqual(result["outcome"], dorec.REFUSED)
self.assertTrue(any("fingerprint mismatch" in r for r in result["reasons"]))
def test_head_mismatch(self):
result = assess(observed_local_head=OTHER_HEAD)
self.assertEqual(result["outcome"], dorec.REFUSED)
def test_remote_head_mismatch(self):
result = assess(observed_remote_head=OTHER_HEAD)
self.assertEqual(result["outcome"], dorec.REFUSED)
def test_path_not_under_branches(self):
result = assess(
source_worktree_path="/tmp/branches/evil",
# lock path also changed so worktree agreement holds
lock=durable_lock(worktree_path="/tmp/branches/evil"),
)
self.assertEqual(result["outcome"], dorec.REFUSED)
self.assertTrue(any("canonical branches" in r for r in result["reasons"]))
def test_unregistered_worktree(self):
result = assess(worktree_registered=False)
self.assertEqual(result["outcome"], dorec.REFUSED)
def test_active_workflow_lease(self):
result = assess(workflow_lease_active=True, workflow_lease_expired=False)
self.assertEqual(result["outcome"], dorec.REFUSED)
def test_unsafe_dirty_path_pin(self):
result = assess(
expected_dirty_fingerprints={"../etc/passwd": FP_A},
observed_dirty_fingerprints={"../etc/passwd": FP_A},
)
self.assertEqual(result["outcome"], dorec.REFUSED)
def test_symlink_escape_rejected_by_ancestry(self):
ok, reasons = dorec.is_path_under_canonical_branches(
"/tmp/branches/evil", canonical_repo_root="/repo"
)
self.assertFalse(ok)
self.assertTrue(reasons)
class ConflictDetection(unittest.TestCase):
def test_overlapping_upstream_change(self):
conflicts = dorec.detect_path_conflicts(
dirty_paths=["c.py"],
local_head_contents={"c.py": b"local-base"},
remote_head_contents={"c.py": b"remote-changed"},
dirty_contents={"c.py": b"dirty-c-conflict"},
)
self.assertEqual(len(conflicts), 1)
self.assertEqual(conflicts[0]["path"], "c.py")
def test_unchanged_upstream_no_conflict(self):
conflicts = dorec.detect_path_conflicts(
dirty_paths=["a.py"],
local_head_contents={"a.py": b"same"},
remote_head_contents={"a.py": b"same"},
dirty_contents={"a.py": b"dirty-a"},
)
self.assertEqual(conflicts, [])
class CrashSafeRecovery(unittest.TestCase):
def setUp(self):
self.tmp = tempfile.mkdtemp(prefix="dirty-orphan-")
self.repo = os.path.join(self.tmp, "repo")
self.branches = os.path.join(self.repo, "branches")
self.source = os.path.join(self.branches, "issue-901-dirty-orphan")
self.recovery = os.path.join(self.branches, RECOVERY_WT_NAME)
os.makedirs(self.source, exist_ok=True)
os.makedirs(self.branches, exist_ok=True)
# seed dirty files in source
with open(os.path.join(self.source, "a.py"), "wb") as fh:
fh.write(b"dirty-a")
with open(os.path.join(self.source, "b.py"), "wb") as fh:
fh.write(b"dirty-b")
self.journal_dir = os.path.join(self.tmp, "journals")
self.lock = durable_lock(worktree_path=self.source)
self.assessment = dorec.assess_dirty_orphan_recovery(
self.lock,
**base_kwargs(
source_worktree_path=self.source,
canonical_repo_root=self.repo,
),
)
class FakeGit(dorec.GitOps):
def __init__(self, recovery_path, head):
self.recovery_path = recovery_path
self.head = head
self.calls = []
def run(self, args, *, cwd):
self.calls.append((args, cwd))
if args[:3] == ["git", "worktree", "add"]:
os.makedirs(self.recovery_path, exist_ok=True)
return mock.Mock(returncode=0, stdout="", stderr="")
if args[:2] == ["git", "checkout"]:
return mock.Mock(returncode=0, stdout="", stderr="")
if args[:2] == ["git", "rev-parse"]:
return mock.Mock(returncode=0, stdout=self.head + "\n", stderr="")
return mock.Mock(returncode=0, stdout="", stderr="")
self.git = FakeGit(self.recovery, REMOTE_HEAD)
self.written_locks = []
def lock_writer(record):
self.written_locks.append(record)
self.lock_writer = lock_writer
def tearDown(self):
shutil.rmtree(self.tmp, ignore_errors=True)
def _run(self, **overrides):
kwargs = {
"assessment": self.assessment,
"existing_lock": self.lock,
"issue_number": 901,
"branch_name": BRANCH,
"source_worktree_path": self.source,
"recovery_worktree_path": self.recovery,
"remote": "prgs",
"org": "Example-Org",
"repo": "Example-Repo",
"identity": "author-user",
"profile": "prgs-author",
"expected_local_head": LOCAL_HEAD,
"expected_remote_head": REMOTE_HEAD,
"expected_dirty_fingerprints": {"a.py": FP_A, "b.py": FP_B},
"dirty_contents": {"a.py": b"dirty-a", "b.py": b"dirty-b"},
"local_head_contents": {"a.py": b"base-a", "b.py": b"base-b"},
"remote_head_contents": {"a.py": b"base-a", "b.py": b"base-b"},
"canonical_repo_root": self.repo,
"bind_lock": True,
"lock_writer": self.lock_writer,
"git_ops": self.git,
"journal_dir": self.journal_dir,
"session_pid": LIVE_PID,
}
kwargs.update(overrides)
return dorec.run_dirty_orphan_recovery(**kwargs)
def test_success_preserves_dirty_bytes_and_source(self):
result = self._run()
self.assertTrue(result["success"])
self.assertEqual(result["outcome"], dorec.RECOVERY_COMPLETED)
self.assertTrue(os.path.isdir(self.source))
with open(os.path.join(self.source, "a.py"), "rb") as fh:
self.assertEqual(fh.read(), b"dirty-a")
with open(os.path.join(self.recovery, "a.py"), "rb") as fh:
self.assertEqual(fh.read(), b"dirty-a")
with open(os.path.join(self.recovery, "b.py"), "rb") as fh:
self.assertEqual(fh.read(), b"dirty-b")
self.assertEqual(len(self.written_locks), 1)
rec = self.written_locks[0]
self.assertEqual(rec["session_pid"], LIVE_PID)
self.assertTrue(rec["dirty_orphan_recovery"]["recovered"])
self.assertTrue(rec["dirty_orphan_recovery"]["source_frozen"])
def test_conflict_leaves_governed_state(self):
result = self._run(
expected_dirty_fingerprints={"c.py": FP_C},
dirty_contents={"c.py": b"dirty-c-conflict"},
local_head_contents={"c.py": b"local-base"},
remote_head_contents={"c.py": b"remote-changed"},
)
# #860 F4: session binding is NOT finalized while conflicts remain
self.assertFalse(result["success"])
self.assertEqual(result["outcome"], dorec.CONFLICTS_PRESENT)
sidecar = os.path.join(self.recovery, "c.py.recovered-dirty")
self.assertTrue(os.path.isfile(sidecar))
state = os.path.join(
self.recovery, dorec.CONFLICT_STATE_DIR, dorec.CONFLICT_STATE_FILE
)
self.assertTrue(os.path.isfile(state))
with open(state, "r", encoding="utf-8") as fh:
payload = json.load(fh)
self.assertEqual(payload["resolution"], "author_edit_required")
def test_interrupt_before_journal_no_artifacts(self):
result = self._run(interrupt_after_phase=dorec.PHASE_ELIGIBILITY)
self.assertFalse(result["success"])
self.assertEqual(result["outcome"], "INTERRUPTED")
self.assertFalse(os.path.isdir(self.recovery))
def test_interrupt_after_journal_then_retry_idempotent(self):
first = self._run(interrupt_after_phase=dorec.PHASE_JOURNAL_PERSISTED)
self.assertEqual(first["outcome"], "INTERRUPTED")
self.assertTrue(first["journal"]["artifacts_created"]["journal"])
second = self._run()
self.assertTrue(second["success"])
# source still recoverable
with open(os.path.join(self.source, "a.py"), "rb") as fh:
self.assertEqual(fh.read(), b"dirty-a")
def test_interrupt_after_worktree_then_retry(self):
first = self._run(interrupt_after_phase=dorec.PHASE_RECOVERY_WORKTREE)
self.assertEqual(first["outcome"], "INTERRUPTED")
self.assertTrue(os.path.isdir(self.recovery))
second = self._run()
self.assertTrue(second["success"])
def test_interrupt_after_binding_then_retry_complete(self):
first = self._run(interrupt_after_phase=dorec.PHASE_BINDING)
self.assertEqual(first["outcome"], "INTERRUPTED")
second = self._run()
self.assertTrue(second["success"])
# completed journal makes further retries no-ops
third = self._run()
self.assertEqual(third["outcome"], dorec.RECOVERY_RESUMED)
def test_source_worktree_never_deleted(self):
self._run()
self.assertTrue(os.path.isdir(self.source))
self.assertTrue(os.path.isfile(os.path.join(self.source, "a.py")))
def test_fingerprint_drift_refuses_without_mutation(self):
result = self._run(dirty_contents={"a.py": b"CHANGED", "b.py": b"dirty-b"})
self.assertFalse(result["success"])
self.assertFalse(os.path.isdir(self.recovery))
class SessionBindingPreflight(unittest.TestCase):
def test_canonical_session_binding_recognized(self):
lock = {
"worktree_path": "/repo/branches/recovery",
"session_pid": LIVE_PID,
"dirty_orphan_recovery": {
"recovered": True,
"conflicts": [],
"recovery_worktree_path": "/repo/branches/recovery",
"source_worktree_path": SOURCE_WT,
"accepted_head": REMOTE_HEAD,
},
}
result = dorec.preflight_recognizes_recovered_provenance(lock)
self.assertTrue(result["recognized"])
def test_conflicts_block_commit_preflight(self):
lock = {
"worktree_path": "/repo/branches/recovery",
"session_pid": LIVE_PID,
"dirty_orphan_recovery": {
"recovered": True,
"conflicts": [{"path": "c.py"}],
},
}
result = dorec.preflight_recognizes_recovered_provenance(lock)
self.assertFalse(result["recognized"])
def test_active_foreign_does_not_mutate(self):
# assess-only path: foreign refused before run
result = assess(identity="intruder")
self.assertFalse(result["eligible"])
class JournalSymlinkRefusal(unittest.TestCase):
def test_symlink_journal_path_refused_on_load(self):
tmp = tempfile.mkdtemp()
try:
real = os.path.join(tmp, "real.json")
with open(real, "w", encoding="utf-8") as fh:
fh.write("{}")
link = os.path.join(tmp, "link.json")
os.symlink(real, link)
key = "symlink-test"
jdir = tmp
path = dorec._journal_path(key, journal_dir=jdir)
with open(path, "w", encoding="utf-8") as fh:
json.dump({"idempotency_key": key}, fh)
os.remove(path)
os.symlink(real, path)
with self.assertRaises(ValueError):
dorec.load_journal(key, journal_dir=jdir)
finally:
shutil.rmtree(tmp, ignore_errors=True)
class RealGitMultiWorktreeIntegration(unittest.TestCase):
def setUp(self):
import subprocess
self.tmp = tempfile.mkdtemp(prefix="git-integration-")
self.repo = os.path.join(self.tmp, "repo")
os.makedirs(self.repo, exist_ok=True)
subprocess.run(["git", "init"], cwd=self.repo, check=True, capture_output=True)
subprocess.run(["git", "config", "user.name", "Test User"], cwd=self.repo, check=True)
subprocess.run(["git", "config", "user.email", "[email protected]"], cwd=self.repo, check=True)
with open(os.path.join(self.repo, "init.txt"), "w") as fh:
fh.write("init")
subprocess.run(["git", "add", "."], cwd=self.repo, check=True)
subprocess.run(["git", "commit", "-m", "init"], cwd=self.repo, check=True)
branch = "fix/issue-999-test"
subprocess.run(["git", "branch", branch], cwd=self.repo, check=True)
self.branches = os.path.join(self.repo, "branches")
self.source = os.path.join(self.branches, "issue-999-test")
subprocess.run(["git", "worktree", "add", self.source, branch], cwd=self.repo, check=True)
self.dirty_path = os.path.join(self.source, "dirty.txt")
with open(self.dirty_path, "w") as fh:
fh.write("dirty-data")
def tearDown(self):
shutil.rmtree(self.tmp, ignore_errors=True)
def test_prepare_recovery_worktree_detached_no_exit_128(self):
import subprocess
head_sha = subprocess.check_output(["git", "rev-parse", "HEAD"], cwd=self.repo, text=True).strip()
rec_wt = os.path.join(self.branches, "recovery-issue-999-test")
res = dorec.prepare_recovery_worktree(
canonical_repo_root=self.repo,
recovery_worktree_path=rec_wt,
branch_name="fix/issue-999-test",
remote_head=head_sha,
)
self.assertTrue(res["success"], res.get("reasons"))
self.assertTrue(os.path.isdir(rec_wt))
def test_real_lock_rebind_recovery_sanctioned(self):
lock_dir = os.path.join(self.tmp, "locks")
rec_wt = os.path.join(self.branches, "recovery-issue-999-test")
os.makedirs(rec_wt, exist_ok=True)
record = {
"remote": "prgs",
"org": "Example-Org",
"repo": "Example-Repo",
"issue_number": 999,
"branch_name": "fix/issue-999-test",
"worktree_path": rec_wt,
"claimant": {"username": "author-user", "profile": "prgs-author"},
}
record_src = dict(record)
record_src["worktree_path"] = self.source
issue_lock_store.bind_session_lock(record_src, lock_dir=lock_dir)
path = issue_lock_store.bind_session_lock(
record,
lock_dir=lock_dir,
recovery_sanctioned=True,
)
self.assertTrue(os.path.isfile(path))
if __name__ == "__main__":
unittest.main()
@@ -0,0 +1,551 @@
"""Merged-PR awareness for the worktree cleanup audit (#858).
Before #858 an ``issue_work`` worktree could never leave ``active_issue_work``:
the audit had no PR linkage at all (``pr_number`` was structurally ``None``)
and its only route to ``clean_stale_removable`` was a TTL derived from a
``last_used_at`` that nothing ever populated. A merged, clean, unprotected
worktree was therefore reported as active work forever, disagreeing with the
PR-scoped reconciler.
These tests use fabricated temporary repositories and synthetic PR records
only. Nothing here removes a worktree or deletes a branch.
"""
import os
import subprocess
import sys
import tempfile
import unittest
from unittest.mock import patch
sys.path.insert(0, str(__import__("pathlib").Path(__file__).resolve().parent.parent))
import merged_cleanup_reconcile as mcr # noqa: E402
import worktree_cleanup_audit as wca # noqa: E402
MERGED_BRANCH = "feat/issue-777-timeline"
MERGED_PATH = "/repo/branches/issue-777-timeline"
HEAD_SHA = "a" * 40
def _pr(number, branch, *, merged=True, sha=HEAD_SHA, state=None):
"""Synthetic Gitea PR payload."""
return {
"number": number,
"head": {"ref": branch, "sha": sha},
"merged_at": "2026-07-24T01:00:00Z" if merged else None,
"state": state or ("closed" if merged else "open"),
}
def _porcelain(*entries):
out = []
for path, branch, sha in entries:
out.append(f"worktree {path}")
out.append(f"HEAD {sha}")
if branch is None:
out.append("detached")
else:
out.append(f"branch refs/heads/{branch}")
out.append("")
return "\n".join(out)
class _AuditHarness(unittest.TestCase):
"""Runs audit_branches_directory over a fabricated worktree listing."""
PORCELAIN = _porcelain(
("/repo", "master", "f" * 40),
(MERGED_PATH, MERGED_BRANCH, HEAD_SHA),
)
def run_audit(self, *, dirty_paths=(), contained=True, **kwargs):
def fake_dirty(path):
if path in dirty_paths:
return {"exists": True, "dirty": True, "dirty_files": [" M x.py"]}
return {"exists": True, "dirty": False, "dirty_files": []}
with patch.object(
wca, "list_worktrees",
return_value=wca.parse_worktree_porcelain(self.PORCELAIN),
), patch.object(
wca, "read_worktree_dirty", side_effect=fake_dirty
), patch.object(
wca, "git_worktree_list", return_value="(mocked)"
), patch.object(
wca, "is_head_ancestor_of_ref", return_value=contained
):
report = wca.audit_branches_directory("/repo", **kwargs)
return {wt["path"]: wt for wt in report["worktrees"]}, report
def merged_audit(self, **kwargs):
kwargs.setdefault("pr_index", wca.build_pr_index([_pr(849, MERGED_BRANCH)]))
kwargs.setdefault("master_ref", "prgs/master")
return self.run_audit(**kwargs)
class TestMergedWorktreeBecomesRemovable(_AuditHarness):
def test_clean_merged_issue_worktree_is_linked_and_removable(self):
by_path, report = self.merged_audit()
entry = by_path[MERGED_PATH]
self.assertEqual(entry["classification"], wca.CLASS_CLEAN_STALE_REMOVABLE)
self.assertTrue(entry["removable"])
self.assertEqual(entry["merged_pr_linkage"]["status"], wca.LINKAGE_MERGED)
self.assertEqual(entry["merged_pr_cleanup"]["block_reasons"], [])
self.assertIn(MERGED_PATH, [c["path"] for c in report["removable_candidates"]])
def test_pr_number_populated_from_authoritative_linkage(self):
by_path, _ = self.merged_audit()
self.assertEqual(by_path[MERGED_PATH]["pr_number"], 849)
def test_regression_without_pr_evidence_stays_active_issue_work(self):
"""The pre-#858 behaviour, still correct when no PR state is supplied."""
by_path, _ = self.run_audit()
entry = by_path[MERGED_PATH]
self.assertEqual(entry["classification"], wca.CLASS_ACTIVE_ISSUE_WORK)
self.assertFalse(entry["removable"])
self.assertIsNone(entry["pr_number"])
class TestProtectiveSignalsSurvive(_AuditHarness):
def test_open_pr_worktree_is_not_removable(self):
index = wca.build_pr_index([_pr(900, MERGED_BRANCH, merged=False)])
by_path, _ = self.run_audit(
pr_index=index,
master_ref="prgs/master",
open_pr_branches={MERGED_BRANCH},
)
entry = by_path[MERGED_PATH]
self.assertEqual(entry["classification"], wca.CLASS_ACTIVE_OPEN_PR)
self.assertFalse(entry["removable"])
# linkage still reports the owning PR, it just is not merge proof
self.assertEqual(entry["merged_pr_linkage"]["status"], wca.LINKAGE_OPEN)
self.assertEqual(entry["pr_number"], 900)
def test_dirty_tracked_worktree_is_not_removable(self):
by_path, _ = self.merged_audit(dirty_paths=(MERGED_PATH,))
entry = by_path[MERGED_PATH]
self.assertEqual(entry["classification"], wca.CLASS_DIRTY_LOCAL)
self.assertFalse(entry["removable"])
self.assertIn(
"worktree has uncommitted changes",
entry["merged_pr_cleanup"]["block_reasons"],
)
def test_untracked_only_worktree_is_not_removable(self):
"""``git status --porcelain`` reports untracked files as dirty too."""
def untracked(path):
if path == MERGED_PATH:
return {"exists": True, "dirty": True, "dirty_files": ["?? scratch.txt"]}
return {"exists": True, "dirty": False, "dirty_files": []}
with patch.object(
wca, "list_worktrees",
return_value=wca.parse_worktree_porcelain(self.PORCELAIN),
), patch.object(
wca, "read_worktree_dirty", side_effect=untracked
), patch.object(
wca, "git_worktree_list", return_value="(mocked)"
), patch.object(
wca, "is_head_ancestor_of_ref", return_value=True
):
report = wca.audit_branches_directory(
"/repo",
pr_index=wca.build_pr_index([_pr(849, MERGED_BRANCH)]),
master_ref="prgs/master",
)
entry = {wt["path"]: wt for wt in report["worktrees"]}[MERGED_PATH]
self.assertEqual(entry["classification"], wca.CLASS_DIRTY_LOCAL)
self.assertFalse(entry["removable"])
def test_active_lease_by_issue_number_is_protective(self):
by_path, _ = self.merged_audit(leased_issue_numbers={777})
entry = by_path[MERGED_PATH]
self.assertTrue(entry["has_active_lease"])
self.assertEqual(entry["classification"], wca.CLASS_ACTIVE_ISSUE_WORK)
self.assertFalse(entry["removable"])
def test_active_lease_by_branch_is_protective(self):
by_path, _ = self.merged_audit(leased_branches={MERGED_BRANCH})
entry = by_path[MERGED_PATH]
self.assertTrue(entry["has_active_lease"])
self.assertFalse(entry["removable"])
def test_active_issue_lock_is_protective(self):
by_path, _ = self.merged_audit(active_issue_branches={MERGED_BRANCH})
entry = by_path[MERGED_PATH]
self.assertTrue(entry["has_active_issue_lock"])
self.assertEqual(entry["classification"], wca.CLASS_ACTIVE_ISSUE_WORK)
self.assertFalse(entry["removable"])
def test_live_session_worktree_is_protective(self):
by_path, _ = self.merged_audit(live_session_paths={MERGED_PATH})
entry = by_path[MERGED_PATH]
self.assertTrue(entry["has_live_session"])
self.assertEqual(entry["classification"], wca.CLASS_ACTIVE_ISSUE_WORK)
self.assertFalse(entry["removable"])
def test_head_not_contained_in_master_is_not_removable(self):
by_path, _ = self.merged_audit(contained=False)
entry = by_path[MERGED_PATH]
self.assertEqual(entry["classification"], wca.CLASS_ACTIVE_ISSUE_WORK)
self.assertFalse(entry["removable"])
self.assertIn(
"worktree head is not contained in authoritative master "
"(unmerged commits remain)",
entry["merged_pr_cleanup"]["block_reasons"],
)
def test_unknown_containment_fails_closed(self):
by_path, _ = self.merged_audit(contained=None)
entry = by_path[MERGED_PATH]
self.assertFalse(entry["removable"])
self.assertIn(
"containment of the worktree head in master is unknown",
entry["merged_pr_cleanup"]["block_reasons"],
)
def test_missing_master_ref_fails_closed(self):
by_path, _ = self.run_audit(
pr_index=wca.build_pr_index([_pr(849, MERGED_BRANCH)])
)
self.assertFalse(by_path[MERGED_PATH]["removable"])
def test_unmerged_owning_pr_is_not_removable(self):
index = wca.build_pr_index([_pr(901, MERGED_BRANCH, merged=False)])
by_path, _ = self.run_audit(pr_index=index, master_ref="prgs/master")
entry = by_path[MERGED_PATH]
self.assertFalse(entry["removable"])
self.assertIn(
"owning PR #901 is not merged",
entry["merged_pr_cleanup"]["block_reasons"],
)
def test_control_checkout_is_never_removable(self):
by_path, _ = self.merged_audit()
control = by_path["/repo"]
self.assertTrue(control["is_protected"])
self.assertEqual(control["classification"], wca.CLASS_UNSAFE_UNKNOWN)
self.assertFalse(control["removable"])
def test_control_checkout_not_removable_even_if_linked_and_merged(self):
"""A merged PR on the control checkout must not unlock removal."""
porcelain = _porcelain(("/repo", MERGED_BRANCH, HEAD_SHA))
with patch.object(
wca, "list_worktrees", return_value=wca.parse_worktree_porcelain(porcelain)
), patch.object(
wca, "read_worktree_dirty",
return_value={"exists": True, "dirty": False, "dirty_files": []},
), patch.object(
wca, "git_worktree_list", return_value="(mocked)"
), patch.object(
wca, "is_head_ancestor_of_ref", return_value=True
):
report = wca.audit_branches_directory(
"/repo",
pr_index=wca.build_pr_index([_pr(849, MERGED_BRANCH)]),
master_ref="prgs/master",
)
entry = report["worktrees"][0]
self.assertEqual(entry["classification"], wca.CLASS_UNSAFE_UNKNOWN)
self.assertFalse(entry["removable"])
class TestAmbiguousLinkageFailsClosed(_AuditHarness):
def test_competing_prs_on_one_branch_fail_closed(self):
index = wca.build_pr_index(
[_pr(849, MERGED_BRANCH), _pr(860, MERGED_BRANCH)]
)
by_path, _ = self.run_audit(pr_index=index, master_ref="prgs/master")
entry = by_path[MERGED_PATH]
self.assertEqual(entry["merged_pr_linkage"]["status"], wca.LINKAGE_AMBIGUOUS)
self.assertIsNone(entry["pr_number"])
self.assertEqual(entry["classification"], wca.CLASS_ACTIVE_ISSUE_WORK)
self.assertFalse(entry["removable"])
def test_merged_plus_open_pr_on_one_branch_fails_closed(self):
index = wca.build_pr_index(
[_pr(849, MERGED_BRANCH), _pr(861, MERGED_BRANCH, merged=False)]
)
by_path, _ = self.run_audit(pr_index=index, master_ref="prgs/master")
entry = by_path[MERGED_PATH]
self.assertEqual(entry["merged_pr_linkage"]["status"], wca.LINKAGE_AMBIGUOUS)
self.assertFalse(entry["removable"])
def test_no_owning_pr_fails_closed(self):
by_path, _ = self.run_audit(
pr_index=wca.build_pr_index([_pr(849, "feat/other-branch")]),
master_ref="prgs/master",
)
entry = by_path[MERGED_PATH]
self.assertEqual(entry["merged_pr_linkage"]["status"], wca.LINKAGE_NONE)
self.assertFalse(entry["removable"])
def test_malformed_pr_records_are_dropped_not_guessed(self):
index = wca.build_pr_index(
[
{"number": None, "head": {"ref": MERGED_BRANCH}},
{"number": 5, "head": {}},
{"number": "not-an-int", "head": {"ref": MERGED_BRANCH}},
]
)
self.assertEqual(index, {})
self.assertEqual(
wca.resolve_owning_pr(branch=MERGED_BRANCH, pr_index=index)["status"],
wca.LINKAGE_NONE,
)
def test_detached_worktree_has_no_branch_linkage(self):
self.assertEqual(
wca.resolve_owning_pr(branch=None, pr_index={})["status"],
wca.LINKAGE_UNKNOWN,
)
class TestUnrelatedClassificationsUnchanged(unittest.TestCase):
"""Non-issue_work worktrees keep their pre-#858 classifications."""
PORCELAIN = _porcelain(
("/repo", "master", "f" * 40),
("/repo/branches/review-pr42", "review-pr42", "2" * 40),
("/repo/branches/baseline-master-x", "baseline-master-x", "3" * 40),
("/repo/branches/conflict-fix-pr50", "conflict-fix-pr50", "4" * 40),
("/repo/branches/review-pr99", None, "5" * 40),
)
def _audit(self, **kwargs):
with patch.object(
wca, "list_worktrees",
return_value=wca.parse_worktree_porcelain(self.PORCELAIN),
), patch.object(
wca, "read_worktree_dirty",
return_value={"exists": True, "dirty": False, "dirty_files": []},
), patch.object(
wca, "git_worktree_list", return_value="(mocked)"
), patch.object(
wca, "is_head_ancestor_of_ref", return_value=True
):
report = wca.audit_branches_directory("/repo", **kwargs)
return {wt["path"]: wt for wt in report["worktrees"]}
def test_classifications_identical_with_and_without_pr_evidence(self):
without = self._audit()
with_evidence = self._audit(
pr_index=wca.build_pr_index([_pr(849, MERGED_BRANCH)]),
master_ref="prgs/master",
)
self.assertEqual(
{p: e["classification"] for p, e in without.items()},
{p: e["classification"] for p, e in with_evidence.items()},
)
def test_lease_on_issue_does_not_capture_similarly_named_scratch_trees(self):
"""A lease on issue 777 protects issue work, not baseline/review trees."""
porcelain = _porcelain(
("/repo/branches/baseline-master-issue-777", "baseline-issue-777", "7" * 40),
("/repo/branches/issue-777-timeline", MERGED_BRANCH, HEAD_SHA),
)
with patch.object(
wca, "list_worktrees", return_value=wca.parse_worktree_porcelain(porcelain)
), patch.object(
wca, "read_worktree_dirty",
return_value={"exists": True, "dirty": False, "dirty_files": []},
), patch.object(
wca, "git_worktree_list", return_value="(mocked)"
), patch.object(
wca, "is_head_ancestor_of_ref", return_value=True
):
report = wca.audit_branches_directory(
"/repo",
pr_index=wca.build_pr_index([_pr(849, MERGED_BRANCH)]),
master_ref="prgs/master",
leased_issue_numbers={777},
)
by_path = {wt["path"]: wt for wt in report["worktrees"]}
baseline = by_path["/repo/branches/baseline-master-issue-777"]
self.assertFalse(baseline["has_active_lease"])
self.assertEqual(baseline["classification"], wca.CLASS_CLEAN_STALE_REMOVABLE)
issue_work = by_path["/repo/branches/issue-777-timeline"]
self.assertTrue(issue_work["has_active_lease"])
self.assertFalse(issue_work["removable"])
def test_review_and_baseline_still_removable(self):
by_path = self._audit(
pr_index=wca.build_pr_index([]), master_ref="prgs/master"
)
self.assertEqual(
by_path["/repo/branches/review-pr42"]["classification"],
wca.CLASS_CLEAN_STALE_REMOVABLE,
)
self.assertEqual(
by_path["/repo/branches/baseline-master-x"]["classification"],
wca.CLASS_CLEAN_STALE_REMOVABLE,
)
self.assertEqual(
by_path["/repo/branches/review-pr99"]["classification"],
wca.CLASS_DETACHED_REVIEW_LEFTOVER,
)
def test_conflict_fix_ttl_behaviour_unchanged(self):
"""conflict_fix still needs only TTL expiry; #858 did not touch it."""
self.assertEqual(
wca.classify_worktree(
workflow_type=wca.WORKFLOW_CONFLICT_FIX,
is_dirty=False,
ttl_expired=True,
),
wca.CLASS_CLEAN_STALE_REMOVABLE,
)
self.assertEqual(
wca.classify_worktree(
workflow_type=wca.WORKFLOW_CONFLICT_FIX,
is_dirty=False,
ttl_expired=False,
),
wca.CLASS_ACTIVE_ISSUE_WORK,
)
def test_issue_work_ttl_alone_no_longer_grants_removal(self):
"""Age is not landing proof: TTL alone must not reclaim issue work."""
self.assertEqual(
wca.classify_worktree(
workflow_type=wca.WORKFLOW_ISSUE_WORK,
is_dirty=False,
ttl_expired=True,
),
wca.CLASS_ACTIVE_ISSUE_WORK,
)
class TestAssessorPerformsNoDeletion(_AuditHarness):
def test_audit_never_removes_a_worktree(self):
with patch.object(wca, "remove_worktree") as removal:
self.merged_audit()
removal.assert_not_called()
def test_audit_shells_out_to_no_destructive_git_command(self):
seen = []
real_run = subprocess.run
def recording_run(cmd, *args, **kwargs):
seen.append(cmd)
return real_run(["true"], *args, **kwargs)
with patch.object(subprocess, "run", side_effect=recording_run):
wca.audit_branches_directory("/nonexistent-repo-for-audit")
joined = [" ".join(c) if isinstance(c, list) else str(c) for c in seen]
for cmd in joined:
self.assertNotIn("worktree remove", cmd)
self.assertNotIn("branch -D", cmd)
self.assertNotIn("push", cmd)
class TestAgreementWithPrScopedReconciler(unittest.TestCase):
"""The audit and merged_cleanup_reconcile must agree on identical input.
Uses a real throwaway git repository so containment is computed by git
rather than asserted. Nothing outside the temporary directory is touched.
"""
def _git(self, *args):
subprocess.run(
["git", "-C", self.root, *args],
check=True,
capture_output=True,
text=True,
)
def setUp(self):
self._tmp = tempfile.TemporaryDirectory()
self.root = os.path.realpath(self._tmp.name)
self._git("init", "-b", "master", ".")
self._git("config", "user.email", "[email protected]")
self._git("config", "user.name", "Test")
with open(os.path.join(self.root, "seed.txt"), "w") as fh:
fh.write("seed\n")
self._git("add", "seed.txt")
self._git("commit", "-m", "seed")
self.branch = "feat/issue-777-timeline"
self._git("checkout", "-b", self.branch)
with open(os.path.join(self.root, "feature.txt"), "w") as fh:
fh.write("feature\n")
self._git("add", "feature.txt")
self._git("commit", "-m", "feature")
self.head_sha = subprocess.run(
["git", "-C", self.root, "rev-parse", "HEAD"],
capture_output=True, text=True, check=True,
).stdout.strip()
self._git("checkout", "master")
self._git("merge", "--no-ff", "-m", "merge feature", self.branch)
self.worktree = os.path.join(self.root, "branches", "issue-777-timeline")
self._git("worktree", "add", self.worktree, self.branch)
def tearDown(self):
self._tmp.cleanup()
def _pr_index(self):
return wca.build_pr_index(
[
{
"number": 849,
"head": {"ref": self.branch, "sha": self.head_sha},
"merged_at": "2026-07-24T01:00:00Z",
}
]
)
def _audit_entry(self):
report = wca.audit_branches_directory(
self.root, pr_index=self._pr_index(), master_ref="master"
)
return next(wt for wt in report["worktrees"] if wt["path"] == self.worktree)
def _reconciler_entry(self):
return mcr.assess_local_worktree_cleanup(
pr_number=849,
head_branch=self.branch,
merged=True,
worktree_state=mcr.resolve_cleanup_worktree_state(
project_root=self.root,
head_branch=self.branch,
issue_number=777,
pr_head_sha=self.head_sha,
target_ref="master",
),
active_lock=False,
)
def test_both_assessors_agree_the_worktree_is_safe(self):
audit_entry = self._audit_entry()
reconciler = self._reconciler_entry()
self.assertTrue(reconciler["safe_to_remove_worktree"], reconciler)
self.assertTrue(audit_entry["removable"], audit_entry)
self.assertEqual(audit_entry["pr_number"], reconciler["pr_number"])
self.assertEqual(audit_entry["merged_pr_cleanup"]["block_reasons"], [])
self.assertEqual(reconciler["block_reasons"], [])
def test_both_assessors_agree_a_dirty_worktree_is_unsafe(self):
with open(os.path.join(self.worktree, "feature.txt"), "a") as fh:
fh.write("local edit\n")
audit_entry = self._audit_entry()
reconciler = self._reconciler_entry()
self.assertFalse(audit_entry["removable"])
self.assertFalse(reconciler["safe_to_remove_worktree"])
def test_worktree_still_present_after_audit(self):
self._audit_entry()
self.assertTrue(os.path.isdir(self.worktree))
if __name__ == "__main__":
unittest.main()
-6
View File
@@ -24,8 +24,6 @@ def _lease(expires_at: str) -> dict:
def _lock_record(**overrides) -> dict:
# #860: live locks require a usable session pid; PID-less records are never
# classified live merely because expiry/heartbeat fields are present.
record = {
"issue_number": 420,
"branch_name": "feat/issue-420-server-code-parity",
@@ -33,8 +31,6 @@ def _lock_record(**overrides) -> dict:
"org": "Scaled-Tech-Consulting",
"repo": "Gitea-Tools",
"worktree_path": "/tmp/wt-420",
"session_pid": os.getpid(),
"pid": os.getpid(),
"work_lease": _lease("2999-01-01T00:00:00Z"),
}
record.update(overrides)
@@ -92,8 +88,6 @@ class TestIssueLockStore(unittest.TestCase):
existing = _lock_record(
branch_name="feat/issue-420-other",
worktree_path="/tmp/other",
session_pid=os.getpid(),
pid=os.getpid(),
work_lease=_lease("2999-01-01T00:00:00Z"),
)
path = ils.lock_file_path(
+24 -2
View File
@@ -134,13 +134,35 @@ class TestClassification(unittest.TestCase):
self.assertEqual(cls, wca.CLASS_ACTIVE_OPEN_PR)
self.assertFalse(wca.is_removable(cls))
def test_stale_clean_issue_worktree_removable(self):
# Scenario 5: clean issue worktree, TTL expired, no lock -> removable.
def test_stale_clean_issue_worktree_needs_merged_pr_proof(self):
# Scenario 5 (#858): age is not proof that the branch landed, so a
# TTL-expired issue worktree stays active work. Only authoritative
# merged-PR evidence makes it removable, which is what keeps a
# worktree holding unmerged commits from being reclaimed by age.
cls = wca.classify_worktree(
workflow_type=wca.WORKFLOW_ISSUE_WORK,
is_dirty=False,
ttl_expired=True,
)
self.assertEqual(cls, wca.CLASS_ACTIVE_ISSUE_WORK)
self.assertFalse(wca.is_removable(cls))
cls = wca.classify_worktree(
workflow_type=wca.WORKFLOW_ISSUE_WORK,
is_dirty=False,
ttl_expired=True,
merged_pr_cleanup={"proven": True},
)
self.assertEqual(cls, wca.CLASS_CLEAN_STALE_REMOVABLE)
self.assertTrue(wca.is_removable(cls))
def test_stale_clean_conflict_fix_worktree_removable(self):
# conflict_fix keeps the original TTL rule; #858 changed issue work only.
cls = wca.classify_worktree(
workflow_type=wca.WORKFLOW_CONFLICT_FIX,
is_dirty=False,
ttl_expired=True,
)
self.assertEqual(cls, wca.CLASS_CLEAN_STALE_REMOVABLE)
self.assertTrue(wca.is_removable(cls))
+271 -4
View File
@@ -34,7 +34,11 @@ import subprocess
from datetime import datetime, timezone
from typing import Any
from merged_cleanup_reconcile import branch_worktree_folder, read_local_worktree_state
from merged_cleanup_reconcile import (
branch_worktree_folder,
is_head_ancestor_of_ref,
read_local_worktree_state,
)
from reviewer_worktree import parse_dirty_tracked_files, REVIEW_WORKTREE_RE
PROTECTED_BRANCHES = frozenset({"master", "main", "dev"})
@@ -67,6 +71,14 @@ REMOVABLE_CLASSES = frozenset(
{CLASS_CLEAN_STALE_REMOVABLE, CLASS_DETACHED_REVIEW_LEFTOVER}
)
# Merged-PR linkage outcomes for issue worktrees (#858). Only ``LINKAGE_MERGED``
# is ownership proof; every other outcome leaves the worktree protected.
LINKAGE_MERGED = "merged_pr"
LINKAGE_OPEN = "open_pr"
LINKAGE_NONE = "no_owning_pr"
LINKAGE_AMBIGUOUS = "ambiguous"
LINKAGE_UNKNOWN = "unknown"
_ISSUE_REF_RE = re.compile(r"issue-(\d+)", re.IGNORECASE)
_ISSUE_BRANCH_PREFIXES = ("feat/", "fix/", "docs/", "chore/")
@@ -169,6 +181,186 @@ def is_ttl_expired(
return (now_dt - last).total_seconds() > ttl_hours * 3600.0
def build_pr_index(prs: list[dict[str, Any]] | None) -> dict[str, list[dict[str, Any]]]:
"""Index PR records by head branch for deterministic worktree linkage (#858).
Accepts Gitea PR payloads (``head`` as a dict) and pre-flattened records
(``head_branch``/``head_sha``). Records without a usable head branch or
number are dropped rather than guessed at, so a branch is only ever linked
to a PR the caller actually proved.
"""
index: dict[str, list[dict[str, Any]]] = {}
for pr in prs or []:
head = pr.get("head")
if isinstance(head, dict):
head_branch = head.get("ref")
head_sha = head.get("sha")
else:
head_branch = pr.get("head_branch") or (head if isinstance(head, str) else None)
head_sha = pr.get("head_sha")
number = pr.get("number")
if not head_branch or number is None:
continue
try:
pr_number = int(number)
except (TypeError, ValueError):
continue
index.setdefault(str(head_branch).strip(), []).append(
{
"pr_number": pr_number,
"head_branch": str(head_branch).strip(),
"head_sha": head_sha,
"merged": bool(pr.get("merged") or pr.get("merged_at")),
"state": pr.get("state"),
}
)
return index
def resolve_owning_pr(
*,
branch: str | None,
pr_index: dict[str, list[dict[str, Any]]] | None,
) -> dict[str, Any]:
"""Resolve the single PR that owns ``branch``, failing closed when unclear.
Ownership is only ``LINKAGE_MERGED`` when exactly one PR claims the branch
and that PR is merged. Several distinct PRs on one branch is a competing
claim (``LINKAGE_AMBIGUOUS``), and a still-open owner is reported as
``LINKAGE_OPEN`` both keep the worktree protected while still exposing
the PR number the audit resolved.
"""
if pr_index is None:
return {
"status": LINKAGE_UNKNOWN,
"pr_number": None,
"candidate_pr_numbers": [],
"reasons": ["live PR state was not supplied; ownership unproven"],
}
branch_name = (branch or "").strip()
if not branch_name:
return {
"status": LINKAGE_UNKNOWN,
"pr_number": None,
"candidate_pr_numbers": [],
"reasons": ["worktree has no attached branch; ownership unproven"],
}
candidates = list(pr_index.get(branch_name) or [])
numbers = sorted({c["pr_number"] for c in candidates})
if not candidates:
return {
"status": LINKAGE_NONE,
"pr_number": None,
"candidate_pr_numbers": [],
"reasons": [f"no PR claims branch '{branch_name}'"],
}
if len(numbers) > 1:
return {
"status": LINKAGE_AMBIGUOUS,
"pr_number": None,
"candidate_pr_numbers": numbers,
"reasons": [
f"branch '{branch_name}' is claimed by competing PRs {numbers}; "
"ownership is ambiguous"
],
}
owner = candidates[0]
pr_number = owner["pr_number"]
if owner.get("head_branch") != branch_name:
return {
"status": LINKAGE_UNKNOWN,
"pr_number": pr_number,
"candidate_pr_numbers": numbers,
"reasons": [
f"PR #{pr_number} head branch '{owner.get('head_branch')}' does not "
f"match worktree branch '{branch_name}'"
],
}
if not owner.get("merged"):
return {
"status": LINKAGE_OPEN,
"pr_number": pr_number,
"candidate_pr_numbers": numbers,
"pr_head_sha": owner.get("head_sha"),
"reasons": [f"owning PR #{pr_number} is not merged"],
}
return {
"status": LINKAGE_MERGED,
"pr_number": pr_number,
"candidate_pr_numbers": numbers,
"pr_head_sha": owner.get("head_sha"),
"reasons": [],
}
def assess_merged_pr_worktree_cleanup(
*,
linkage: dict[str, Any] | None,
head_sha: str | None,
head_in_master: bool | None,
is_dirty: bool,
has_open_pr: bool,
has_active_lease: bool,
has_active_issue_lock: bool,
is_protected: bool,
has_live_session: bool = False,
) -> dict[str, Any]:
"""Decide whether a merged issue worktree satisfies the full cleanup policy.
Every condition must be independently proven: conclusive merged-PR
ownership, agreement between the worktree branch and the PR head branch,
containment of the worktree head in authoritative master (which is what
proves no unmerged commits remain), absence of any open/competing PR,
lease, issue lock, or live session, a clean tree, and a worktree that is
not the protected control checkout. Anything unknown blocks.
"""
link = linkage or {
"status": LINKAGE_UNKNOWN,
"pr_number": None,
"reasons": ["no linkage assessment supplied"],
}
status = link.get("status")
reasons: list[str] = []
if status != LINKAGE_MERGED:
reasons.extend(
link.get("reasons") or ["owning PR could not be conclusively identified"]
)
if is_protected:
reasons.append("worktree is protected or the stable control checkout")
if is_dirty:
reasons.append("worktree has uncommitted changes")
if has_open_pr:
reasons.append("worktree branch has an open PR")
if has_active_lease:
reasons.append("worktree has an active lease")
if has_active_issue_lock:
reasons.append("an active issue lock references this branch")
if has_live_session:
reasons.append("a live process or session is using this worktree")
if not head_sha:
reasons.append("worktree head sha is unknown")
if head_in_master is None:
reasons.append("containment of the worktree head in master is unknown")
elif not head_in_master:
reasons.append(
"worktree head is not contained in authoritative master "
"(unmerged commits remain)"
)
proven = not reasons
return {
"linkage_status": status,
"pr_number": link.get("pr_number"),
"pr_head_sha": link.get("pr_head_sha"),
"head_in_master": head_in_master,
"proven": proven,
"block_reasons": reasons,
}
def classify_worktree(
*,
workflow_type: str,
@@ -181,6 +373,8 @@ def classify_worktree(
ttl_expired: bool = False,
is_protected: bool = False,
metadata_known: bool = True,
merged_pr_cleanup: dict[str, Any] | None = None,
has_live_session: bool = False,
) -> str:
"""Classify a worktree, safety-first: any preservation signal wins.
@@ -199,6 +393,8 @@ def classify_worktree(
return CLASS_ACTIVE_ISSUE_WORK # never auto-deleted (criterion 8)
if has_active_issue_lock:
return CLASS_ACTIVE_ISSUE_WORK
if has_live_session:
return CLASS_ACTIVE_ISSUE_WORK # a live session still owns this tree
if not metadata_known or workflow_type == WORKFLOW_UNKNOWN:
return CLASS_UNSAFE_UNKNOWN # never auto-deleted without proof
@@ -207,7 +403,15 @@ def classify_worktree(
if is_detached or branch_gone:
return CLASS_DETACHED_REVIEW_LEFTOVER
return CLASS_CLEAN_STALE_REMOVABLE
# issue_work / conflict_fix: only removable once the TTL has expired.
if workflow_type == WORKFLOW_ISSUE_WORK:
# #858: an issue worktree becomes removable only on authoritative
# merged-PR evidence satisfying the whole cleanup policy. Age alone
# never proves the branch landed, so TTL cannot qualify one by itself
# — otherwise a worktree holding unmerged commits would be reclaimed.
if (merged_pr_cleanup or {}).get("proven"):
return CLASS_CLEAN_STALE_REMOVABLE
return CLASS_ACTIVE_ISSUE_WORK
# conflict_fix: only removable once the TTL has expired.
if ttl_expired:
return CLASS_CLEAN_STALE_REMOVABLE
return CLASS_ACTIVE_ISSUE_WORK
@@ -400,6 +604,20 @@ def remove_worktree(project_root: str, path: str) -> dict[str, Any]:
}
def head_contained_in_ref(
project_root: str, head_sha: str | None, ref: str | None
) -> bool | None:
"""Return True when ``head_sha`` is already contained in ``ref``.
Shares :mod:`merged_cleanup_reconcile`'s ancestry check so the audit and
the PR-scoped reconciler agree on what "already landed" means (#858).
Returns None when containment cannot be determined, which fails closed.
"""
if not head_sha or not ref:
return None
return is_head_ancestor_of_ref(project_root, head_sha, ref)
def _is_under_branches(project_root: str, path: str) -> bool:
branches_root = os.path.join(os.path.abspath(project_root), "branches")
return os.path.abspath(path or "").startswith(branches_root + os.sep)
@@ -413,16 +631,30 @@ def audit_branches_directory(
active_issue_branches: set[str] | None = None,
now: datetime | str | None = None,
ttl_hours: float = DEFAULT_TTL_HOURS,
pr_index: dict[str, list[dict[str, Any]]] | None = None,
leased_issue_numbers: set[int] | None = None,
live_session_paths: set[str] | None = None,
master_ref: str | None = None,
) -> dict[str, Any]:
"""Classify every session-owned worktree under ``branches/``.
Read-only: shells out to git for discovery and dirty state, then applies
the pure classifier. Returns per-worktree classifications, counts, the
list of removable candidates, and the ``git worktree list`` proof.
``pr_index`` (see :func:`build_pr_index`) supplies the authoritative PR
ownership used to link issue worktrees to their merged PR (#858).
``master_ref`` is the ref a worktree head must be contained in before it
can be considered landed. Both are optional and their absence only ever
fails closed: without them no issue worktree becomes removable.
"""
open_pr_branches = open_pr_branches or set()
leased_branches = leased_branches or set()
active_issue_branches = active_issue_branches or set()
leased_issue_numbers = leased_issue_numbers or set()
live_session_paths = {
os.path.abspath(p) for p in (live_session_paths or set()) if p
}
worktrees: list[dict[str, Any]] = []
for entry in list_worktrees(project_root):
@@ -433,12 +665,42 @@ def audit_branches_directory(
)
dirty_state = read_worktree_dirty(path)
is_dirty = bool(dirty_state.get("dirty"))
head_sha = entry.get("head")
linkage = resolve_owning_pr(branch=branch, pr_index=pr_index)
metadata = build_worktree_metadata(
path=path, branch=branch, head_sha=entry.get("head")
path=path,
branch=branch,
head_sha=head_sha,
pr_number=linkage.get("pr_number"),
)
has_open_pr = bool(branch) and branch in open_pr_branches
has_active_lease = bool(branch) and branch in leased_branches
# A lease on issue N protects that issue's own work worktree. It must
# not incidentally protect a baseline/review scratch tree that merely
# carries the same issue marker in its name, which would change the
# classification of worktrees this policy does not own.
has_active_lease = (bool(branch) and branch in leased_branches) or (
metadata["workflow_type"] == WORKFLOW_ISSUE_WORK
and metadata.get("issue_number") is not None
and metadata["issue_number"] in leased_issue_numbers
)
has_active_lock = bool(branch) and branch in active_issue_branches
has_live_session = bool(path) and os.path.abspath(path) in live_session_paths
head_in_master = (
head_contained_in_ref(project_root, head_sha, master_ref)
if master_ref
else None
)
merged_pr_cleanup = assess_merged_pr_worktree_cleanup(
linkage=linkage,
head_sha=head_sha,
head_in_master=head_in_master,
is_dirty=is_dirty,
has_open_pr=has_open_pr,
has_active_lease=has_active_lease,
has_active_issue_lock=has_active_lock,
is_protected=is_protected,
has_live_session=has_live_session,
)
ttl_expired = is_ttl_expired(
last_used_at=metadata.get("last_used_at"), now=now, ttl_hours=ttl_hours
)
@@ -452,6 +714,8 @@ def audit_branches_directory(
branch_gone=branch is None and not entry.get("detached"),
ttl_expired=ttl_expired,
is_protected=is_protected,
merged_pr_cleanup=merged_pr_cleanup,
has_live_session=has_live_session,
)
metadata["cleanup_eligibility"] = classification
worktrees.append(
@@ -463,7 +727,10 @@ def audit_branches_directory(
"has_open_pr": has_open_pr,
"has_active_lease": has_active_lease,
"has_active_issue_lock": has_active_lock,
"has_live_session": has_live_session,
"is_protected": is_protected,
"merged_pr_linkage": linkage,
"merged_pr_cleanup": merged_pr_cleanup,
"classification": classification,
"removable": is_removable(classification),
}