Files
Gitea-Tools/author_mutation_worktree.py
T
jcwalker3andClaude Opus 4.8 5ed2ab8a38 fix: durable author worktree resolution without control fallback (Closes #618)
Author mutation tools now resolve workspace via explicit worktree_path,
env bindings, or the active author issue lock — never silent fallback to
the control checkout/master. Missing configured bindings fail closed with
operator recovery; create_issue and create_issue_comment agree.

Recovered onto 0568f44 from preserved candidate cbf56ccd (AUTHOR_RECOVERY).
LLM_LOCK_ID=author-618-recovery-508eb3162d01-1784569919

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
2026-07-20 12:55:40 -05:00

776 lines
28 KiB
Python

"""Branches-only author mutation worktree guard (#274) with durable resolution (#618).
Author/coder mutations must run from a session-owned worktree under the
project's ``branches/`` directory, never from the stable control checkout.
#618 durable resolution:
- Prefer an explicit validated ``worktree_path`` argument.
- Else derive the workspace from the active author issue lock's worktree.
- Env bindings (``GITEA_ACTIVE_WORKTREE`` / ``GITEA_AUTHOR_WORKTREE``) may bind
when present and valid.
- Author mutations never silently fall back to the control checkout or master.
- Missing configured bindings fail closed with a clear operator recovery action.
"""
from __future__ import annotations
import os
import subprocess
BASE_BRANCHES = frozenset({"master", "main", "dev"})
ACTIVE_WORKTREE_ENV = "GITEA_ACTIVE_WORKTREE"
AUTHOR_WORKTREE_ENV = "GITEA_AUTHOR_WORKTREE"
# Author-only: reviewer/merger/reconciler namespaces use role-specific env vars
# via namespace_workspace_binding (#510).
BOUND_WORKTREE_MISSING = "bound_worktree_missing"
BOUND_WORKTREE_MISSING_MESSAGE = (
"bound worktree missing; operator must recreate or repoint the worktree "
"and reconnect"
)
OPERATOR_RECOVERY_RECREATE_REPOINT = (
"Recreate the worktree under branches/ (scripts/worktree-start or "
"git worktree add), set GITEA_AUTHOR_WORKTREE / GITEA_ACTIVE_WORKTREE "
"to that path (or pass worktree_path on mutation tools), keep the control "
"checkout clean on master, then reconnect the author MCP session and re-run."
)
def _normalize_path(path: str) -> str:
return (path or "").replace("\\", "/").rstrip("/")
def is_path_under_branches(path: str, project_root: str | None = None) -> bool:
"""True when *path* resolves inside ``<project_root>/branches/``."""
normalized = _normalize_path(path)
if not normalized:
return False
if "/branches/" in f"{normalized}/":
return True
if normalized.endswith("/branches"):
return True
if project_root:
root = _normalize_path(os.path.realpath(project_root))
real = _normalize_path(os.path.realpath(path))
if real.startswith(f"{root}/"):
rel = real[len(root) + 1 :]
return rel == "branches" or rel.startswith("branches/")
return False
def resolve_mutation_workspace(
worktree_path: str | None,
project_root: str,
*,
active_worktree_env: str | None = None,
author_worktree_env: str | None = None,
) -> str:
"""Resolve the workspace path inspected before author mutations.
Legacy helper: returns the first non-empty candidate path. Prefer
:func:`resolve_durable_author_worktree` for mutation guards (#618).
"""
for candidate in (worktree_path, active_worktree_env, author_worktree_env):
text = (candidate or "").strip()
if text:
return os.path.realpath(os.path.abspath(text))
return os.path.realpath(project_root)
def _realpath_git_common_dir(workspace_path: str, common_dir: str) -> str:
"""Resolve ``git rev-parse --git-common-dir`` relative to *workspace_path*."""
raw = (common_dir or "").strip()
if not raw:
return raw
if os.path.isabs(raw):
return os.path.realpath(raw)
return os.path.realpath(os.path.join(workspace_path, raw))
def resolve_canonical_repo_root(workspace_path: str, fallback_project_root: str) -> str:
"""Return the stable repository root for *workspace_path* via git metadata (#460)."""
path = (workspace_path or "").strip()
fallback = os.path.realpath(fallback_project_root)
if not path:
return fallback
try:
res = subprocess.run(
["git", "-C", path, "rev-parse", "--git-common-dir"],
capture_output=True,
text=True,
check=True,
)
common = _realpath_git_common_dir(path, res.stdout)
except Exception:
return fallback
if common.endswith(f"{os.sep}.git"):
return os.path.dirname(common)
if os.path.basename(common) == ".git":
return os.path.dirname(common)
return fallback
def resolve_author_mutation_context(
worktree_path: str | None,
process_project_root: str,
*,
active_worktree_env: str | None = None,
author_worktree_env: str | None = None,
) -> dict:
"""Shared workspace resolution for runtime_context and mutation guards (#460)."""
workspace = resolve_mutation_workspace(
worktree_path,
process_project_root,
active_worktree_env=active_worktree_env,
author_worktree_env=author_worktree_env,
)
process_root = os.path.realpath(process_project_root)
# Canonical repository identity comes from the MCP process checkout (#460),
# not from the declared task workspace being validated.
canonical_root = resolve_canonical_repo_root(process_root, process_root)
return {
"workspace_path": workspace,
"process_project_root": process_root,
"canonical_repo_root": canonical_root,
"roots_aligned": canonical_root == process_root,
}
def assess_workspace_repo_membership(
*,
workspace_path: str,
canonical_repo_root: str,
) -> dict:
"""Fail closed when *workspace_path* is not a git worktree of *canonical_repo_root*."""
workspace = os.path.realpath(workspace_path)
root = os.path.realpath(canonical_repo_root)
reasons: list[str] = []
if not os.path.exists(workspace):
reasons.append(f"worktree path '{workspace}' does not exist")
return _membership_assessment(False, reasons, workspace, root, None)
if not os.path.isdir(workspace):
reasons.append(f"worktree path '{workspace}' is not a directory")
return _membership_assessment(False, reasons, workspace, root, None)
try:
res = subprocess.run(
["git", "-C", workspace, "rev-parse", "--git-common-dir"],
capture_output=True,
text=True,
check=True,
)
common_dir = _realpath_git_common_dir(workspace, res.stdout)
except Exception:
reasons.append(f"worktree '{workspace}' is not a valid git repository")
return _membership_assessment(False, reasons, workspace, root, None)
expected_dir = os.path.realpath(os.path.join(root, ".git"))
if common_dir != expected_dir:
reasons.append(
f"worktree '{workspace}' does not belong to the target repository '{root}'"
)
return _membership_assessment(not reasons, reasons, workspace, root, common_dir)
def _membership_assessment(
proven: bool,
reasons: list[str],
workspace: str,
root: str,
common_dir: str | None,
) -> dict:
return {
"proven": proven,
"block": not proven,
"reasons": reasons,
"workspace_path": workspace,
"canonical_repo_root": root,
"git_common_dir": common_dir,
}
def format_workspace_repo_membership_error(assessment: dict) -> str:
workspace = assessment.get("workspace_path") or "(unknown)"
root = assessment.get("canonical_repo_root") or "(unknown)"
reasons = "; ".join(assessment.get("reasons") or ["unknown repository membership violation"])
return (
f"Branches-only mutation guard (#274): {reasons} (fail closed). "
f"canonical repository root: {root}; workspace: {workspace}."
)
def assess_author_mutation_worktree(
*,
workspace_path: str,
project_root: str,
current_branch: str | None = None,
base_branches: frozenset[str] | None = None,
) -> dict:
"""Fail closed when author mutations are not rooted under ``branches/``."""
bases = base_branches or BASE_BRANCHES
reasons: list[str] = []
root = os.path.realpath(project_root)
workspace = os.path.realpath(workspace_path)
branch = (current_branch or "").strip()
under_branches = is_path_under_branches(workspace, root)
if not under_branches:
if workspace == root:
reasons.append(
"author mutation blocked: workspace is the stable control checkout; "
"create or switch to a session-owned worktree under branches/"
)
else:
reasons.append(
f"author mutation blocked: workspace '{workspace}' is not under "
f"'{root}/branches/'; create a branches/<task> worktree first"
)
if not under_branches and workspace == root and branch and branch not in bases:
reasons.append(
f"control checkout drift: branch '{branch}' is not a stable base "
f"branch ({'/'.join(sorted(bases))})"
)
proven = not reasons
return {
"proven": proven,
"block": not proven,
"reasons": reasons,
"project_root": root,
"workspace_path": workspace,
"under_branches": is_path_under_branches(workspace, root),
"current_branch": branch or None,
}
def format_author_mutation_worktree_error(assessment: dict) -> str:
"""Single RuntimeError message for MCP preflight gates."""
workspace = assessment.get("workspace_path") or "(unknown)"
root = assessment.get("project_root") or "(unknown)"
reasons = "; ".join(assessment.get("reasons") or ["unknown branches-only violation"])
return (
f"Branches-only mutation guard (#274): {reasons}. "
f"project root: {root}; workspace: {workspace}. "
"Create a session-owned worktree under branches/ before mutating."
)
# ---------------------------------------------------------------------------
# #618 durable author worktree resolution
# ---------------------------------------------------------------------------
def _abs_real(path: str) -> str:
return os.path.realpath(os.path.abspath((path or "").strip()))
def assess_path_traversal_safety(
*,
path: str,
canonical_repo_root: str,
) -> dict:
"""Fail closed on traversal/symlink escapes outside the target repository.
Uses ``realpath`` so intermediate symlinks cannot walk outside
``canonical_repo_root``. Author mutation workspaces must also land under
``branches/`` of that root (enforced separately by the branches-only guard).
"""
reasons: list[str] = []
raw = (path or "").strip()
if not raw:
return {
"proven": False,
"block": True,
"reasons": ["worktree path is empty (fail closed)"],
"workspace_path": None,
"canonical_repo_root": os.path.realpath(canonical_repo_root),
}
if "\x00" in raw:
return {
"proven": False,
"block": True,
"reasons": ["worktree path contains a null byte (fail closed)"],
"workspace_path": raw,
"canonical_repo_root": os.path.realpath(canonical_repo_root),
}
root = os.path.realpath(canonical_repo_root)
# Resolve without requiring existence first: abspath then realpath of parents.
abs_path = os.path.abspath(raw)
try:
real = os.path.realpath(abs_path)
except OSError as exc:
return {
"proven": False,
"block": True,
"reasons": [f"worktree path could not be resolved safely: {exc}"],
"workspace_path": abs_path,
"canonical_repo_root": root,
}
root_norm = _normalize_path(root)
real_norm = _normalize_path(real)
if real_norm != root_norm and not real_norm.startswith(f"{root_norm}/"):
reasons.append(
f"worktree path '{real}' escapes canonical repository root '{root}' "
"(traversal/symlink safety, fail closed)"
)
return {
"proven": not reasons,
"block": bool(reasons),
"reasons": reasons,
"workspace_path": real,
"canonical_repo_root": root,
}
def list_git_worktree_paths(canonical_repo_root: str) -> list[str]:
"""Return realpaths registered in ``git worktree list --porcelain``."""
root = os.path.realpath(canonical_repo_root)
try:
res = subprocess.run(
["git", "-C", root, "worktree", "list", "--porcelain"],
capture_output=True,
text=True,
check=False,
)
except Exception:
return []
if res.returncode != 0:
return []
paths: list[str] = []
for line in (res.stdout or "").splitlines():
if line.startswith("worktree "):
raw = line[len("worktree ") :].strip()
if raw:
paths.append(os.path.realpath(raw))
return paths
def path_in_git_worktree_list(path: str, canonical_repo_root: str) -> bool | None:
"""True/False when inventory is available; None when git inventory fails.
An empty inventory with a working git root is treated as inconclusive
(``None``) so unit tests and partial sandboxes are not false-negative
blocked when ``git worktree list`` is mocked/unavailable.
"""
root = os.path.realpath(canonical_repo_root)
try:
res = subprocess.run(
["git", "-C", root, "worktree", "list", "--porcelain"],
capture_output=True,
text=True,
check=False,
)
except Exception:
return None
if res.returncode != 0:
return None
inventory: list[str] = []
for line in (res.stdout or "").splitlines():
if line.startswith("worktree "):
raw = line[len("worktree ") :].strip()
if raw:
inventory.append(os.path.realpath(raw))
if not inventory:
return None
return os.path.realpath(path) in inventory
def assess_bound_worktree_existence(
*,
configured_path: str,
binding_source: str,
canonical_repo_root: str | None = None,
role_kind: str = "author",
profile_name: str | None = None,
) -> dict:
"""Fail closed when a configured role-bound worktree path is missing (#618)."""
raw = (configured_path or "").strip()
if not raw:
return {
"proven": True,
"block": False,
"bound_worktree_missing": False,
"path_exists": None,
"in_git_worktree_list": None,
"inspected_git_root": None,
"reasons": [],
"configured_path": None,
"binding_source": binding_source,
"role_kind": role_kind,
"profile_name": profile_name,
"blocker_kind": None,
"operator_recovery": None,
}
try:
real = _abs_real(raw)
except OSError:
real = os.path.abspath(raw)
path_exists = os.path.isdir(real)
in_list: bool | None = None
inspected_git_root: str | None = None
root = (canonical_repo_root or "").strip()
if root:
in_list = path_in_git_worktree_list(real, root) if path_exists else False
if path_exists:
try:
res = subprocess.run(
["git", "-C", real, "rev-parse", "--show-toplevel"],
capture_output=True,
text=True,
check=False,
)
if res.returncode == 0:
inspected_git_root = (res.stdout or "").strip() or None
except Exception:
inspected_git_root = None
if path_exists:
return {
"proven": True,
"block": False,
"bound_worktree_missing": False,
"path_exists": True,
"in_git_worktree_list": in_list,
"inspected_git_root": inspected_git_root,
"reasons": [],
"configured_path": real,
"binding_source": binding_source,
"role_kind": role_kind,
"profile_name": profile_name,
"blocker_kind": None,
"operator_recovery": None,
}
reasons = [
BOUND_WORKTREE_MISSING_MESSAGE,
(
f"role/profile '{profile_name or role_kind}' binding via {binding_source} "
f"points to '{real}' which does not exist on disk"
),
f"path_exists=false; in_git_worktree_list={in_list}; inspected_git_root=null",
]
return {
"proven": False,
"block": True,
"bound_worktree_missing": True,
"path_exists": False,
"in_git_worktree_list": False if in_list is not None else False,
"inspected_git_root": None,
"reasons": reasons,
"configured_path": real,
"binding_source": binding_source,
"role_kind": role_kind,
"profile_name": profile_name,
"blocker_kind": BOUND_WORKTREE_MISSING,
"operator_recovery": OPERATOR_RECOVERY_RECREATE_REPOINT,
}
def format_bound_worktree_missing_error(assessment: dict) -> str:
"""Canonical operator-facing message for a missing author worktree binding."""
reasons = list(assessment.get("reasons") or [BOUND_WORKTREE_MISSING_MESSAGE])
recovery = assessment.get("operator_recovery") or OPERATOR_RECOVERY_RECREATE_REPOINT
profile = assessment.get("profile_name") or assessment.get("role_kind") or "author"
source = (
assessment.get("binding_source")
or assessment.get("workspace_binding_source")
or "unknown binding"
)
path = (
assessment.get("configured_path")
or assessment.get("workspace_path")
or "(unknown)"
)
return (
f"Author worktree binding unhealthy (#618): {'; '.join(reasons)}. "
f"role/profile: {profile}; binding_source: {source}; configured_path: {path}. "
f"Operator recovery: {recovery}"
)
def assess_lock_worktree_ownership(
*,
workspace_path: str,
session_lock_worktree: str | None,
) -> dict:
"""When a live lock records a worktree, mutation workspace must match it."""
locked = (session_lock_worktree or "").strip()
if not locked:
return {
"proven": True,
"block": False,
"reasons": [],
"workspace_path": os.path.realpath(workspace_path) if workspace_path else None,
"lock_worktree_path": None,
}
workspace = os.path.realpath(workspace_path)
locked_real = os.path.realpath(locked)
if workspace != locked_real:
return {
"proven": False,
"block": True,
"reasons": [
f"active author issue lock worktree '{locked_real}' does not match "
f"mutation workspace '{workspace}' (lock ownership, fail closed)"
],
"workspace_path": workspace,
"lock_worktree_path": locked_real,
}
return {
"proven": True,
"block": False,
"reasons": [],
"workspace_path": workspace,
"lock_worktree_path": locked_real,
}
def resolve_durable_author_worktree(
*,
worktree_path: str | None = None,
worktree: str | None = None,
process_project_root: str,
active_worktree_env: str | None = None,
author_worktree_env: str | None = None,
session_lock_worktree: str | None = None,
canonical_repo_root: str | None = None,
profile_name: str | None = None,
validate: bool = True,
) -> dict:
"""Resolve author mutation workspace without silent control-checkout fallback (#618).
Candidate priority:
1. explicit ``worktree_path`` argument
2. ``worktree`` argument
3. ``GITEA_ACTIVE_WORKTREE``
4. ``GITEA_AUTHOR_WORKTREE``
5. active author issue lock ``worktree_path``
6. process project root **only** when it is already under ``branches/``
Configured bindings that point at a missing path fail closed immediately
(no demotion to the control checkout). Validation (when *validate*) covers
existence, traversal/symlink safety, repository identity, branches/
containment, and lock ownership.
"""
process_root = os.path.realpath(process_project_root)
canonical = os.path.realpath(canonical_repo_root or process_root)
reasons: list[str] = []
role = "author"
candidates: list[tuple[str | None, str, bool]] = [
(worktree_path, "worktree_path argument", False),
(worktree, "worktree argument", False),
(active_worktree_env, f"{ACTIVE_WORKTREE_ENV} environment variable", True),
(author_worktree_env, f"{AUTHOR_WORKTREE_ENV} environment variable", True),
(session_lock_worktree, "active author issue lock worktree", False),
]
selected_path: str | None = None
selected_source: str | None = None
existence: dict | None = None
for candidate, source, _configured in candidates:
text = (candidate or "").strip()
if not text:
continue
try:
real = _abs_real(text)
except OSError:
real = os.path.abspath(text)
existence = assess_bound_worktree_existence(
configured_path=real,
binding_source=source,
canonical_repo_root=canonical,
role_kind=role,
profile_name=profile_name,
)
if existence["block"]:
# Missing configured binding: fail closed, never fall back (#618).
return {
"proven": False,
"block": True,
"workspace_path": real,
"workspace_binding_source": source,
"process_project_root": process_root,
"canonical_repo_root": canonical,
"bound_worktree_missing": True,
"path_exists": False,
"in_git_worktree_list": existence.get("in_git_worktree_list"),
"inspected_git_root": None,
"reasons": list(existence.get("reasons") or []),
"blocker_kind": BOUND_WORKTREE_MISSING,
"operator_recovery": OPERATOR_RECOVERY_RECREATE_REPOINT,
"silent_control_fallback": False,
}
selected_path = real
selected_source = source
break
if selected_path is None:
# No explicit/env/lock binding. Allow process root only when it is a
# branches/ worktree (MCP launched from the task worktree). Never
# silently bind the stable control checkout.
if is_path_under_branches(process_root, canonical):
selected_path = process_root
selected_source = "MCP process root under branches/ (session-owned)"
else:
return {
"proven": False,
"block": True,
"workspace_path": process_root,
"workspace_binding_source": "no author worktree binding",
"process_project_root": process_root,
"canonical_repo_root": canonical,
"bound_worktree_missing": False,
"path_exists": os.path.isdir(process_root),
"in_git_worktree_list": None,
"inspected_git_root": None,
"reasons": [
"author mutation blocked: workspace is the stable control checkout; "
"author mutation requires an explicit validated worktree_path "
"or a worktree derived from the active author issue lock; "
"silent fallback to the control checkout/master is forbidden (#618)"
],
"blocker_kind": "author_worktree_unbound_control_checkout",
"operator_recovery": OPERATOR_RECOVERY_RECREATE_REPOINT,
"silent_control_fallback": False,
}
workspace = selected_path
source = selected_source or "unknown"
path_exists = os.path.isdir(workspace)
inspected_git_root: str | None = None
in_list: bool | None = None
if not validate:
return {
"proven": True,
"block": False,
"workspace_path": workspace,
"workspace_binding_source": source,
"process_project_root": process_root,
"canonical_repo_root": canonical,
"bound_worktree_missing": False,
"path_exists": path_exists,
"in_git_worktree_list": None,
"inspected_git_root": None,
"reasons": [],
"blocker_kind": None,
"operator_recovery": None,
"silent_control_fallback": False,
}
# Traversal / symlink safety
safety = assess_path_traversal_safety(
path=workspace, canonical_repo_root=canonical
)
if safety["block"]:
reasons.extend(safety["reasons"])
else:
workspace = safety["workspace_path"] or workspace
# Existence + git inventory
if not path_exists:
reasons.append(BOUND_WORKTREE_MISSING_MESSAGE)
reasons.append(f"resolved worktree '{workspace}' does not exist")
else:
in_list = path_in_git_worktree_list(workspace, canonical)
try:
res = subprocess.run(
["git", "-C", workspace, "rev-parse", "--show-toplevel"],
capture_output=True,
text=True,
check=False,
)
if res.returncode == 0:
inspected_git_root = (res.stdout or "").strip() or None
except Exception:
inspected_git_root = None
if in_list is False:
# Only hard-fail when inventory was obtained and the path is absent.
reasons.append(
f"worktree '{workspace}' is not listed in git worktree list for "
f"'{canonical}' (fail closed)"
)
# Repository identity
if path_exists:
membership = assess_workspace_repo_membership(
workspace_path=workspace,
canonical_repo_root=canonical,
)
if membership["block"]:
reasons.extend(membership["reasons"])
# branches/ containment
branches = assess_author_mutation_worktree(
workspace_path=workspace,
project_root=canonical,
)
if branches["block"]:
reasons.extend(branches["reasons"])
# Lock ownership (when a lock worktree is recorded)
lock_own = assess_lock_worktree_ownership(
workspace_path=workspace,
session_lock_worktree=session_lock_worktree,
)
if lock_own["block"]:
reasons.extend(lock_own["reasons"])
# Forbid resolved control checkout even if somehow selected
if workspace == canonical or workspace == process_root:
if not is_path_under_branches(workspace, canonical):
if not any("control checkout" in r for r in reasons):
reasons.append(
"author mutation blocked: resolved workspace is the stable "
"control checkout; silent fallback forbidden (#618)"
)
block = bool(reasons)
bound_missing = any("does not exist" in r or BOUND_WORKTREE_MISSING_MESSAGE in r for r in reasons)
return {
"proven": not block,
"block": block,
"workspace_path": workspace,
"workspace_binding_source": source,
"process_project_root": process_root,
"canonical_repo_root": canonical,
"bound_worktree_missing": bound_missing,
"path_exists": path_exists,
"in_git_worktree_list": in_list,
"inspected_git_root": inspected_git_root,
"reasons": reasons,
"blocker_kind": BOUND_WORKTREE_MISSING if bound_missing else (
"author_worktree_validation_failed" if block else None
),
"operator_recovery": OPERATOR_RECOVERY_RECREATE_REPOINT if block else None,
"silent_control_fallback": False,
}
def format_durable_author_worktree_error(assessment: dict) -> str:
"""Format fail-closed error for durable author worktree resolution."""
if assessment.get("bound_worktree_missing") or assessment.get("blocker_kind") == BOUND_WORKTREE_MISSING:
return format_bound_worktree_missing_error(assessment)
workspace = assessment.get("workspace_path") or "(unknown)"
source = assessment.get("workspace_binding_source") or "unknown"
reasons = "; ".join(
assessment.get("reasons") or ["author worktree resolution failed"]
)
recovery = assessment.get("operator_recovery") or OPERATOR_RECOVERY_RECREATE_REPOINT
return (
f"Durable author worktree resolution blocked (#618): {reasons}. "
f"workspace: {workspace}; binding_source: {source}. "
f"Operator recovery: {recovery}"
)