Compare commits

..
Author SHA1 Message Date
sysadmin 6b675f5c83 fix: harden structured auth MCP errors against reviewer findings (#699)
Address PR #701 request-changes-class defects:

1. Fixed messages only — never embed HTTP bodies, Keychain, or exception
   text in tool results or daemon logs; sanitization fails closed.
2. Narrow Tool.run boundary wraps original success path; re-raises
   UrlElicitationRequiredError; install is idempotent.
3. No RuntimeError substring heuristics; only typed client failures
   are classified as auth/authz/network/config.
4. Central classify_http_status — every HTTP 403 is GiteaAuthzError.

Regressions cover adversarial secrets, stdio survival, elicitation,
parser RuntimeError, generic 403, repeated install, profiles, provenance.

Closes #699
2026-07-13 13:40:38 -04:00
sysadmin b4d0cb22e4 fix: map Gitea auth failures to structured MCP tool errors (Closes #699)
HTTP 401/scope-403/network failures become typed client errors with stable
reason codes. The FastMCP Tool.run boundary returns CallToolResult isError
payloads so stdio transport survives; daemon logs use sanitized reason codes
only. Regression tests cover author/reconciler profiles, transport survival,
and non-misclassification of unexpected exceptions.

Cross-links: #685, #695, #697, #698, PR #696 (scopes not absorbed).
2026-07-13 13:10:00 -04:00
sysadmin 237656702f Merge pull request 'feat(lease): guarded cleanup for obsolete reviewer comment leases (Closes #691)' (#692) from fix/issue-691-obsolete-reviewer-lease-cleanup into master 2026-07-12 22:28:59 -05:00
sysadmin 6d86db793b feat(lease): guarded cleanup for obsolete reviewer comment leases (Closes #691)
Add fail-closed assessment and MCP tool for expired/superseded-head
comment-backed reviewer leases that lack a control-plane lease_id.

- assess_obsolete_reviewer_comment_lease_cleanup eligibility matrix
- diagnose classifications: foreign_active_current_head,
  foreign_expired_current_head, foreign_completed_superseded_head,
  foreign_expired_superseded_head, orphaned_owner_missing,
  ambiguous_conflicting_evidence
- gitea_cleanup_obsolete_reviewer_comment_lease with confirmation
  CLEANUP OBSOLETE REVIEWER LEASE <n> and controller_recovery_authorized
- preserve audit history via append-only phase=released marker
- never repoint, transfer validation, use PID ownership, or steal
  active current-head foreign leases
- regression for PR #688 lease comment 10749 after recorded expiry
2026-07-12 23:09:20 -04:00
sysadmin 56f1230a10 Merge pull request 'feat(guard): harden workflow against unattributed root WIP and pytest-disabled production guards (Closes #683)' (#684) from fix/issue-683-workflow-guard-hardening into master 2026-07-12 18:58:55 -05:00
10 changed files with 2673 additions and 92 deletions
+207 -19
View File
@@ -243,6 +243,192 @@ def _redact(text):
return str(text)
# ── Classified client failures (#699) ─────────────────────────────────────────
# Subclasses of RuntimeError preserve existing ``except RuntimeError`` call
# sites. Exception *messages* are fixed constants only — HTTP response bodies,
# Keychain material, and arbitrary exception text are never stored on the
# exception or re-emitted to tool results / daemon logs.
# Fixed messages (must match mcp_tool_error_boundary.FIXED_MESSAGES keys used here).
_MSG_AUTH_INVALID = "Gitea authentication failed: invalid or revoked credentials"
_MSG_AUTH_FAILED = "Gitea authentication failed"
_MSG_AUTHZ_SCOPE = "Gitea authorization failed: insufficient token scope"
_MSG_AUTHZ_DENIED = "Gitea authorization failed: access denied"
_MSG_NETWORK = "Network error contacting Gitea"
_MSG_CONFIG = "Gitea configuration or credential resolution failed"
_MSG_UPSTREAM = "Gitea upstream unavailable"
_MSG_HTTP = "Gitea HTTP request failed"
class GiteaClientError(RuntimeError):
"""Base for known Gitea client failures with stable reason_code metadata."""
reason_code = "client_error"
error_class = "client"
http_status = None
def __init__(self, message=None, *, reason_code=None, http_status=None):
if reason_code is not None:
self.reason_code = reason_code
if http_status is not None:
self.http_status = http_status
# Message is always a fixed constant; callers cannot inject bodies.
fixed = message if message is not None else _MSG_HTTP
super().__init__(fixed)
class GiteaAuthError(GiteaClientError):
"""Authentication failure (invalid/revoked credentials → typically HTTP 401)."""
reason_code = "auth_invalid_token"
error_class = "authentication"
http_status = 401
def __init__(self, message=None, *, reason_code=None, http_status=None):
super().__init__(
message if message is not None else _MSG_AUTH_INVALID,
reason_code=reason_code or "auth_invalid_token",
http_status=http_status if http_status is not None else 401,
)
class GiteaAuthzError(GiteaClientError):
"""Authorization failure (HTTP 403 — scope deficiency or access denied)."""
reason_code = "authz_denied"
error_class = "authorization"
http_status = 403
def __init__(self, message=None, *, reason_code=None, http_status=None):
code = reason_code or "authz_denied"
if code == "authz_insufficient_scope":
fixed = _MSG_AUTHZ_SCOPE
else:
fixed = _MSG_AUTHZ_DENIED
code = "authz_denied"
super().__init__(
message if message is not None else fixed,
reason_code=code,
http_status=http_status if http_status is not None else 403,
)
class GiteaNetworkError(GiteaClientError):
"""Transport / DNS / timeout failure contacting Gitea."""
reason_code = "network_error"
error_class = "network"
http_status = None
def __init__(self, message=None, *, reason_code=None, http_status=None):
super().__init__(
message if message is not None else _MSG_NETWORK,
reason_code=reason_code or "network_error",
http_status=http_status,
)
class GiteaConfigError(GiteaClientError):
"""Local configuration / credential resolution failure (not HTTP auth)."""
reason_code = "config_error"
error_class = "configuration"
http_status = None
def __init__(self, message=None, *, reason_code=None, http_status=None):
super().__init__(
message if message is not None else _MSG_CONFIG,
reason_code=reason_code or "config_error",
http_status=http_status,
)
class GiteaHttpError(GiteaClientError):
"""Non-auth HTTP failure with fixed message (no response body)."""
reason_code = "http_error"
error_class = "client"
http_status = None
def __init__(self, message=None, *, reason_code=None, http_status=None):
code = reason_code or "http_error"
if code == "upstream_unavailable":
fixed = _MSG_UPSTREAM
else:
fixed = _MSG_HTTP
code = "http_error"
super().__init__(
message if message is not None else fixed,
reason_code=code,
http_status=http_status,
)
def _looks_like_insufficient_scope(detail: str) -> bool:
"""Internal: inspect redacted body *only* to refine 403 reason_code.
The body is never stored on the exception or returned to callers.
"""
lower = (detail or "").lower()
markers = (
"insufficient scope",
"required scope",
"does not have at least one of required scope",
"token does not have",
"missing scope",
"scope(s)",
)
return any(m in lower for m in markers)
def classify_http_status(code: int, *, body_hint: str = "") -> tuple[type, str, int]:
"""Central HTTP status → (exception_class, reason_code, http_status).
Every HTTP 403 becomes authorization-class. Body text is used only as a
local hint for scope vs denied reason_code and is never returned.
"""
if code == 401:
return (GiteaAuthError, "auth_invalid_token", 401)
if code == 403:
if _looks_like_insufficient_scope(body_hint or ""):
return (GiteaAuthzError, "authz_insufficient_scope", 403)
return (GiteaAuthzError, "authz_denied", 403)
if code in (502, 503, 504):
return (GiteaHttpError, "upstream_unavailable", code)
return (GiteaHttpError, "http_error", code)
def raise_for_http_status(code: int, body: str = "") -> None:
"""Raise a typed client error for *code* without embedding *body*.
*body* may be inspected only to choose scope vs denied for 403; it is
never placed on the exception message.
"""
# Redact before any inspection; discard after classification.
try:
hint = _redact(body or "").strip()
except Exception:
hint = ""
exc_cls, reason, status = classify_http_status(code, body_hint=hint)
# Explicitly construct without passing body/hint into message.
if exc_cls is GiteaAuthError:
raise GiteaAuthError(reason_code=reason, http_status=status)
if exc_cls is GiteaAuthzError:
raise GiteaAuthzError(reason_code=reason, http_status=status)
if reason == "upstream_unavailable":
raise GiteaHttpError(
reason_code="upstream_unavailable",
http_status=status,
)
raise GiteaHttpError(reason_code="http_error", http_status=status)
def _raise_http_error(code: int, detail: str = "") -> None:
"""Backward-compatible alias — *detail* is never embedded in the error."""
raise_for_http_status(code, detail)
def _add_query(url, **params):
"""Return *url* with the given query parameters added or overridden.
@@ -315,23 +501,24 @@ def api_request(method, url, auth_header, payload=None, *,
"""Make an authenticated JSON request to the Gitea API.
Returns parsed JSON on success (or ``None`` for an empty body), and raises
``RuntimeError`` on failure.
a classified client error on failure.
On HTTP 429 the request is retried up to *max_retries* times: honoring a
valid ``Retry-After`` header (seconds or HTTP-date) when present, otherwise
using capped jittered exponential backoff. Successful responses are
unchanged.
All failures are converted to a ``RuntimeError`` with a clear, secret
-redacted message (no raw stack traces or credential material):
Failures raise typed exceptions with **fixed messages only** (#699). HTTP
response bodies are read solely for local 403 reason refinement and are
never stored on exceptions or returned to callers:
- Non-429 HTTP errors surface the status code and a redacted response body.
502/503/504 upstream errors get an explicit "Gitea upstream unavailable"
message.
- Timeouts and network/DNS failures (``URLError`` / ``TimeoutError``) surface
a generic "network error contacting Gitea" message.
- A malformed (non-JSON) success body surfaces a "malformed JSON response"
message rather than a raw decode error.
- HTTP 401 → :class:`GiteaAuthError` (``auth_invalid_token``)
- HTTP 403 → :class:`GiteaAuthzError` (scope or denied)
- 502/503/504 → :class:`GiteaHttpError` (``upstream_unavailable``)
- Other non-429 HTTP → :class:`GiteaHttpError` (``http_error``)
- Timeouts / DNS / ``URLError`` → :class:`GiteaNetworkError`
- Malformed success JSON → plain ``RuntimeError`` (programming/protocol;
not reclassified as authentication)
The ``*_func`` parameters and ``timeout`` are injection points for
deterministic testing.
@@ -369,22 +556,23 @@ def api_request(method, url, auth_header, payload=None, *,
error_body = e.read().decode("utf-8", errors="replace")
except Exception:
error_body = ""
detail = _redact(error_body).strip()
if e.code in (502, 503, 504):
msg = f"HTTP {e.code}: Gitea upstream unavailable"
raise RuntimeError(f"{msg}: {detail}" if detail else msg) from e
raise RuntimeError(f"HTTP {e.code}: {detail}") from e
# Classify from status (+ local body hint). Body is not embedded.
try:
raise_for_http_status(e.code, error_body)
except GiteaClientError:
raise
# Defensive: raise_for_http_status always raises.
raise GiteaHttpError(http_status=e.code) from e # pragma: no cover
except (urllib.error.URLError, TimeoutError) as e:
reason = getattr(e, "reason", e)
raise RuntimeError(
f"network error contacting Gitea: {_redact(reason)}"
) from e
# Fixed message only — do not embed URLError reason (may leak paths).
raise GiteaNetworkError(reason_code="network_error") from e
if not body:
return None
try:
return json.loads(body)
except ValueError as e:
# Programming/protocol failure — not authentication.
raise RuntimeError("malformed JSON response from Gitea") from e
+291 -10
View File
@@ -1084,7 +1084,9 @@ from gitea_auth import ( # noqa: E402
repo_api_url,
get_profile,
gitea_url,
GiteaConfigError,
)
import mcp_tool_error_boundary # noqa: E402
import gitea_audit # noqa: E402
import gitea_config # noqa: E402
import capability_stop_terminal # noqa: E402
@@ -1464,6 +1466,12 @@ def _with_optional_url(result: dict, url: str | None) -> dict:
result["url"] = url
return result
# #699: known auth/authz/network/config failures → structured CallToolResult
# isError; stdio transport must survive (no unhandled raise / process exit).
from mcp.server.fastmcp.tools.base import Tool as _FastMCPTool # noqa: E402
mcp_tool_error_boundary.install_tool_run_boundary(_FastMCPTool)
mcp = FastMCP("gitea-tools", instructions=(
"Gitea issue tracker and PR management for dadeschools and prgs instances. "
"Use the gitea_ prefixed tools to create issues, PRs, list issues, etc."
@@ -1801,13 +1809,16 @@ def _enforce_remote_repo_guard(
def _auth(host: str) -> str:
"""Get auth header, raise if unavailable."""
"""Get auth header, raise if unavailable.
Missing credentials are a configuration failure, not a silent internal
crash. Typed as :class:`gitea_auth.GiteaConfigError` so the tool-error
boundary (#699) maps them to a structured isError result without EOF.
The exception message is a fixed constant (no host/token material).
"""
header = get_auth_header(host)
if header is None:
raise RuntimeError(
f"No credentials for {host}. "
"Ensure you've logged in via HTTPS at least once."
)
raise GiteaConfigError(reason_code="config_error")
return header
@@ -7964,11 +7975,12 @@ def gitea_diagnose_reviewer_pr_lease_handoff(
org: str | None = None,
repo: str | None = None,
) -> dict:
"""Read-only: diagnose open-PR reviewer lease handoff and emit next action (#599).
"""Read-only: diagnose open-PR reviewer lease handoff and emit next action (#599, #691).
Classifies no-lease / own / foreign / instructed-lease-missing-with-replacement
and worktree binding mismatch. Returns a canonical ``next_action`` without
mutating Gitea state. Never steals foreign leases.
Classifies no-lease / own / foreign / superseded-head / expired / orphan /
instructed-lease-missing-with-replacement and worktree binding mismatch.
Returns a canonical ``next_action`` (including guarded obsolete-lease cleanup)
without mutating Gitea state. Never steals foreign leases.
"""
read_block = _profile_operation_gate("gitea.read")
if read_block:
@@ -7979,7 +7991,7 @@ def gitea_diagnose_reviewer_pr_lease_handoff(
}
comments = _fetch_pr_comments(
pr_number, remote=remote, host=host, org=org, repo=repo)
h, _o, _r = _resolve(remote, host, org, repo)
h, o, r = _resolve(remote, host, org, repo)
try:
username = _authenticated_username(h)
except Exception:
@@ -7993,6 +8005,64 @@ def gitea_diagnose_reviewer_pr_lease_handoff(
# Prefer in-session lease id when present; otherwise diagnose as a fresh
# caller without inventing ownership of an on-thread lease.
session_id = (session_lease.get("session_id") or "").strip() or None
# Live PR head + formal reviews for #691 superseded/completed classification.
current_head_sha = None
formal_reviews: list[dict] = []
try:
auth = _auth(h)
pr_live = api_request(
"GET", f"{repo_api_url(h, o, r)}/pulls/{pr_number}", auth
) or {}
head = pr_live.get("head") or {}
current_head_sha = head.get("sha") or pr_live.get("head_commit_sha")
try:
reviews = api_request(
"GET",
f"{repo_api_url(h, o, r)}/pulls/{pr_number}/reviews",
auth,
) or []
for rev in reviews if isinstance(reviews, list) else []:
formal_reviews.append({
"verdict": rev.get("state") or rev.get("verdict"),
"reviewed_head_sha": rev.get("commit_id") or rev.get(
"reviewed_head_sha"
),
"dismissed": bool(rev.get("dismissed")),
"reviewer": ((rev.get("user") or {}).get("login")),
"submitted_at": rev.get("submitted_at"),
})
except Exception:
formal_reviews = []
except Exception:
current_head_sha = None
lease_wt = None
active = reviewer_pr_lease.find_newest_nonterminal_lease(
comments, pr_number=pr_number, include_expired=True
)
if active:
lease_wt = (active.get("worktree") or "").strip() or None
worktree_exists = None
worktree_clean = None
if lease_wt:
worktree_exists = os.path.isdir(lease_wt)
if worktree_exists:
try:
import subprocess
st = subprocess.run(
["git", "-C", lease_wt, "status", "--porcelain"],
capture_output=True,
text=True,
timeout=30,
check=False,
)
if st.returncode == 0:
worktree_clean = not bool((st.stdout or "").strip())
except Exception:
worktree_clean = None
diagnosis = reviewer_pr_lease.diagnose_reviewer_pr_lease_handoff(
comments,
pr_number=pr_number,
@@ -8002,6 +8072,11 @@ def gitea_diagnose_reviewer_pr_lease_handoff(
env_bound_worktree=env_wt,
instructed_session_id=instructed_session_id,
instructed_comment_id=instructed_comment_id,
current_head_sha=current_head_sha,
formal_reviews=formal_reviews,
worktree_exists=worktree_exists,
worktree_clean=worktree_clean,
owner_process_alive=None, # PID never proves ownership; leave unset
)
diagnosis["success"] = True
diagnosis["remote"] = remote
@@ -8129,6 +8204,212 @@ def gitea_cleanup_post_merge_moot_lease(
return report
@mcp.tool()
def gitea_cleanup_obsolete_reviewer_comment_lease(
pr_number: int,
confirmation: str = "",
apply: bool = False,
controller_recovery_authorized: bool = False,
expected_lease_comment_id: int | None = None,
expected_session_id: str | None = None,
expected_leased_head: str | None = None,
owner_process_alive: bool | None = None,
current_head_review_in_progress: bool = False,
remote: str = "dadeschools",
host: str | None = None,
org: str | None = None,
repo: str | None = None,
) -> dict:
"""Guarded cleanup for obsolete comment-backed reviewer leases on open PRs (#691).
Neutralises an expired and/or superseded-head foreign lease by posting a
terminal ``phase: released`` lease marker (append-only audit). Never deletes
comments, never repoints the lease to the new head, never transfers
validation/decision/workflow state, never uses PID equality as ownership,
and never steals a genuinely active foreign lease on the current head.
Read-first when ``apply`` is false. Apply requires:
- ``controller_recovery_authorized=True`` (explicit operator/controller
recovery capability not implied by profile alone)
- ``confirmation`` exactly ``CLEANUP OBSOLETE REVIEWER LEASE <pr_number>``
- full eligibility evidence from
``reviewer_pr_lease.assess_obsolete_reviewer_comment_lease_cleanup``
Comment-backed leases need no control-plane DB ``lease_id``.
"""
read_block = _profile_operation_gate("gitea.read")
if read_block:
return {
"success": False,
"cleanup_performed": False,
"no_steal_or_adoption": True,
"reasons": read_block,
"permission_report": _permission_block_report("gitea.read"),
}
h, o, r = _resolve(remote, host, org, repo)
auth = _auth(h)
expected_repo = f"{o}/{r}"
comments = _fetch_pr_comments(
pr_number, remote=remote, host=host, org=org, repo=repo
)
pr_live = api_request(
"GET", f"{repo_api_url(h, o, r)}/pulls/{pr_number}", auth
) or {}
head = pr_live.get("head") or {}
current_head_sha = head.get("sha") or pr_live.get("head_commit_sha")
formal_reviews: list[dict] = []
try:
reviews = api_request(
"GET",
f"{repo_api_url(h, o, r)}/pulls/{pr_number}/reviews",
auth,
) or []
for rev in reviews if isinstance(reviews, list) else []:
formal_reviews.append({
"verdict": rev.get("state") or rev.get("verdict"),
"reviewed_head_sha": rev.get("commit_id")
or rev.get("reviewed_head_sha"),
"dismissed": bool(rev.get("dismissed")),
"reviewer": ((rev.get("user") or {}).get("login")),
"submitted_at": rev.get("submitted_at"),
})
except Exception:
formal_reviews = []
lease = reviewer_pr_lease.find_newest_nonterminal_lease(
comments, pr_number=pr_number, include_expired=True
)
lease_wt = ((lease or {}).get("worktree") or "").strip() or None
worktree_exists = None
worktree_clean = None
worktree_has_unpreserved_work = None
if lease_wt:
worktree_exists = os.path.isdir(lease_wt)
if worktree_exists:
try:
import subprocess
st = subprocess.run(
["git", "-C", lease_wt, "status", "--porcelain"],
capture_output=True,
text=True,
timeout=30,
check=False,
)
if st.returncode == 0:
dirty = bool((st.stdout or "").strip())
worktree_clean = not dirty
worktree_has_unpreserved_work = dirty
except Exception:
worktree_clean = None
session = reviewer_pr_lease.get_session_lease() or {}
assessment = reviewer_pr_lease.assess_obsolete_reviewer_comment_lease_cleanup(
comments,
pr_number=pr_number,
current_head_sha=current_head_sha,
formal_reviews=formal_reviews,
repo=expected_repo,
expected_repo=expected_repo,
requesting_session_id=(session.get("session_id") or "").strip() or None,
controller_recovery_authorized=controller_recovery_authorized,
worktree_exists=worktree_exists,
worktree_clean=worktree_clean,
worktree_has_unpreserved_work=worktree_has_unpreserved_work,
owner_process_alive=owner_process_alive,
owner_pid_observed=None,
requesting_pid=os.getpid(),
current_head_review_in_progress=current_head_review_in_progress,
expected_lease_comment_id=expected_lease_comment_id,
expected_session_id=expected_session_id,
expected_leased_head=expected_leased_head,
confirmation=confirmation,
apply=apply,
)
report = {
"success": True,
"pr_number": pr_number,
"pr_state": pr_live.get("state"),
"cleanup_allowed": assessment.get("cleanup_allowed"),
"cleanup_performed": False,
"classification": assessment.get("classification"),
"blocker_kind": assessment.get("blocker_kind"),
"exact_next_action": assessment.get("exact_next_action"),
"mutation_eligibility": assessment.get("mutation_eligibility"),
"leased_head": assessment.get("leased_head"),
"current_head": assessment.get("current_head"),
"expires_at": assessment.get("expires_at"),
"terminal_review": assessment.get("terminal_review"),
"worktree_state": assessment.get("worktree_state"),
"owner_session_evidence": assessment.get("owner_session_evidence"),
"cleanup_tool": assessment.get("cleanup_tool"),
"required_confirmation": assessment.get("required_confirmation"),
"active_lease": assessment.get("active_lease"),
"no_steal_or_adoption": True,
"no_repoint": True,
"no_validation_transfer": True,
"mode": "apply" if apply else "read_only",
"reasons": assessment.get("reasons") or [],
"forbidden": assessment.get("forbidden") or [],
}
if not apply:
return report
if not assessment.get("cleanup_allowed"):
report["success"] = False
report["cleanup_skipped_reason"] = (
assessment.get("fail_closed_reasons")
or assessment.get("reasons")
or ["cleanup not allowed"]
)
return report
comment_block = _profile_operation_gate("gitea.pr.comment")
if comment_block:
report["success"] = False
report["reasons"] = comment_block
report["permission_report"] = _permission_block_report("gitea.pr.comment")
return report
verify_preflight_purity(remote)
# Terminal lease marker (preserves history; does not delete comment 10749-style
# entries — newest released marker neutralises the ledger).
release_body = assessment.get("release_body") or ""
audit_body = assessment.get("audit_comment_body") or ""
comment_url = f"{repo_api_url(h, o, r)}/issues/{pr_number}/comments"
with _audited(
"comment_pr",
host=h,
remote=remote,
org=o,
repo=r,
pr_number=pr_number,
request_metadata={
"source": "cleanup_obsolete_reviewer_comment_lease",
"classification": assessment.get("classification"),
},
):
posted_release = api_request(
"POST", comment_url, auth, {"body": release_body}
)
posted_audit = None
if audit_body.strip():
posted_audit = api_request(
"POST", comment_url, auth, {"body": audit_body}
)
# Never seed session lease from cleaned foreign lease.
report["cleanup_performed"] = True
report["released_comment_id"] = (posted_release or {}).get("id")
report["audit_comment_id"] = (posted_audit or {}).get("id")
report["session_lease_seeded"] = False
return report
@mcp.tool()
def gitea_release_reviewer_pr_lease(
pr_number: int,
+1
View File
@@ -13,6 +13,7 @@ from typing import Any
AUTHORIZED_CLEANUP_TOOLS = frozenset({
"gitea_cleanup_post_merge_moot_lease",
"gitea_cleanup_obsolete_reviewer_comment_lease",
"gitea_reconcile_merged_cleanups",
"gitea_delete_branch",
"gitea_cleanup_merged_pr_branch",
+451
View File
@@ -0,0 +1,451 @@
"""MCP tool-boundary error mapping for known Gitea client failures (#699).
Known authentication / authorization / network / configuration failures leave
the tool boundary as a sanitized structured ``CallToolResult`` with
``isError=True``. Stdio transport remains connected.
Design constraints (reviewer-ratified, #699 / PR #701):
1. **No secret material** in tool results or daemon logs. Messages are fixed
constants keyed by ``reason_code``; HTTP bodies / exception text never
surface. Sanitization failure fails closed to ``internal_error``.
2. **Narrow boundary** wraps the original FastMCP ``Tool.run`` success path;
re-raises framework control-flow exceptions (``UrlElicitationRequiredError``);
maps only typed client failures. Installation is idempotent.
3. **No RuntimeError substring heuristics.** Only explicit typed
authentication / authorization / network / configuration exceptions
receive those labels.
4. **HTTP classification** lives in ``gitea_auth.classify_http_status``;
every 403 is authorization-class.
"""
from __future__ import annotations
import json
import logging
import sys
from typing import Any
logger = logging.getLogger("gitea_mcp.tool_error_boundary")
# Stable reason codes (#699).
REASON_AUTH_FAILED = "auth_failed"
REASON_AUTH_INVALID_TOKEN = "auth_invalid_token"
REASON_AUTHZ_INSUFFICIENT_SCOPE = "authz_insufficient_scope"
REASON_AUTHZ_DENIED = "authz_denied"
REASON_NETWORK_ERROR = "network_error"
REASON_CONFIG_ERROR = "config_error"
REASON_INTERNAL_ERROR = "internal_error"
REASON_UPSTREAM_UNAVAILABLE = "upstream_unavailable"
REASON_HTTP_ERROR = "http_error"
ERROR_CLASS_AUTHENTICATION = "authentication"
ERROR_CLASS_AUTHORIZATION = "authorization"
ERROR_CLASS_NETWORK = "network"
ERROR_CLASS_CONFIGURATION = "configuration"
ERROR_CLASS_INTERNAL = "internal"
ERROR_CLASS_UPSTREAM = "upstream"
# Fixed, secret-free operator messages. Never interpolate HTTP bodies,
# Keychain contents, tokens, or arbitrary exception text.
FIXED_MESSAGES: dict[str, str] = {
REASON_AUTH_FAILED: "Gitea authentication failed",
REASON_AUTH_INVALID_TOKEN: (
"Gitea authentication failed: invalid or revoked credentials"
),
REASON_AUTHZ_INSUFFICIENT_SCOPE: (
"Gitea authorization failed: insufficient token scope"
),
REASON_AUTHZ_DENIED: "Gitea authorization failed: access denied",
REASON_NETWORK_ERROR: "Network error contacting Gitea",
REASON_CONFIG_ERROR: "Gitea configuration or credential resolution failed",
REASON_INTERNAL_ERROR: "Internal tool error",
REASON_UPSTREAM_UNAVAILABLE: "Gitea upstream unavailable",
REASON_HTTP_ERROR: "Gitea HTTP request failed",
}
_INSTALL_FLAG = "_gitea_auth_boundary_installed"
_ORIGINAL_ATTR = "_gitea_auth_boundary_original"
def fixed_message(reason_code: str) -> str:
"""Return the fixed sanitized message for *reason_code* (fail closed)."""
return FIXED_MESSAGES.get(reason_code, FIXED_MESSAGES[REASON_INTERNAL_ERROR])
def _safe_profile_name() -> str | None:
try:
from gitea_auth import get_profile
name = (get_profile() or {}).get("profile_name")
if name is None:
return None
text = str(name).strip()
# Profile names are non-secret identifiers; still bound length.
return text[:80] if text else None
except Exception:
return None
def _is_framework_control_flow(exc: BaseException) -> bool:
"""True for exceptions the MCP framework must re-raise unchanged."""
try:
from mcp.shared.exceptions import UrlElicitationRequiredError
if isinstance(exc, UrlElicitationRequiredError):
return True
except Exception:
pass
# BaseException subclasses that must never become tool isError payloads.
if isinstance(exc, (KeyboardInterrupt, SystemExit, GeneratorExit)):
return True
return False
def is_known_client_failure(exc: BaseException) -> bool:
"""True only for explicit typed Gitea client / config failures.
Never true for arbitrary ``RuntimeError`` (reviewer finding #3).
"""
try:
import gitea_auth
if isinstance(
exc,
(
gitea_auth.GiteaAuthError,
gitea_auth.GiteaAuthzError,
gitea_auth.GiteaNetworkError,
gitea_auth.GiteaConfigError,
gitea_auth.GiteaHttpError,
),
):
return True
except Exception:
return False
try:
import gitea_config
if isinstance(exc, gitea_config.ConfigError):
return True
except Exception:
pass
return False
def classify_exception(exc: BaseException) -> dict[str, Any]:
"""Return structured classification with **fixed** messages only.
Only typed authentication / authorization / network / configuration
failures receive those labels. Unexpected programming failures are
``internal_error``. HTTP bodies and exception text are never copied
into ``message``.
"""
try:
return _classify_exception_impl(exc)
except Exception:
# Fail closed: sanitization / classification failure must not leak.
return {
"reason_code": REASON_INTERNAL_ERROR,
"error_class": ERROR_CLASS_INTERNAL,
"http_status": None,
"message": fixed_message(REASON_INTERNAL_ERROR),
"transport_survives": True,
}
def _classify_exception_impl(exc: BaseException) -> dict[str, Any]:
import gitea_auth
if isinstance(exc, gitea_auth.GiteaAuthError):
code = getattr(exc, "reason_code", None) or REASON_AUTH_INVALID_TOKEN
if code not in (
REASON_AUTH_FAILED,
REASON_AUTH_INVALID_TOKEN,
):
code = REASON_AUTH_INVALID_TOKEN
return {
"reason_code": code,
"error_class": ERROR_CLASS_AUTHENTICATION,
"http_status": getattr(exc, "http_status", None) or 401,
"message": fixed_message(code),
"transport_survives": True,
}
if isinstance(exc, gitea_auth.GiteaAuthzError):
code = getattr(exc, "reason_code", None) or REASON_AUTHZ_DENIED
if code not in (REASON_AUTHZ_DENIED, REASON_AUTHZ_INSUFFICIENT_SCOPE):
code = REASON_AUTHZ_DENIED
return {
"reason_code": code,
"error_class": ERROR_CLASS_AUTHORIZATION,
"http_status": getattr(exc, "http_status", None) or 403,
"message": fixed_message(code),
"transport_survives": True,
}
if isinstance(exc, gitea_auth.GiteaNetworkError):
return {
"reason_code": REASON_NETWORK_ERROR,
"error_class": ERROR_CLASS_NETWORK,
"http_status": getattr(exc, "http_status", None),
"message": fixed_message(REASON_NETWORK_ERROR),
"transport_survives": True,
}
if isinstance(exc, gitea_auth.GiteaConfigError):
return {
"reason_code": REASON_CONFIG_ERROR,
"error_class": ERROR_CLASS_CONFIGURATION,
"http_status": getattr(exc, "http_status", None),
"message": fixed_message(REASON_CONFIG_ERROR),
"transport_survives": True,
}
if isinstance(exc, gitea_auth.GiteaHttpError):
code = getattr(exc, "reason_code", None) or REASON_HTTP_ERROR
if code == REASON_UPSTREAM_UNAVAILABLE:
error_class = ERROR_CLASS_UPSTREAM
else:
error_class = ERROR_CLASS_INTERNAL
code = REASON_HTTP_ERROR
return {
"reason_code": code,
"error_class": error_class,
"http_status": getattr(exc, "http_status", None),
"message": fixed_message(code),
"transport_survives": True,
}
try:
import gitea_config
if isinstance(exc, gitea_config.ConfigError):
return {
"reason_code": REASON_CONFIG_ERROR,
"error_class": ERROR_CLASS_CONFIGURATION,
"http_status": None,
"message": fixed_message(REASON_CONFIG_ERROR),
"transport_survives": True,
}
except Exception:
pass
# Unwrap FastMCP ToolError cause when the original was a typed failure.
cause = getattr(exc, "__cause__", None)
if cause is not None and cause is not exc and is_known_client_failure(cause):
return _classify_exception_impl(cause)
# No message-substring authentication heuristics (reviewer finding #3).
return {
"reason_code": REASON_INTERNAL_ERROR,
"error_class": ERROR_CLASS_INTERNAL,
"http_status": None,
"message": fixed_message(REASON_INTERNAL_ERROR),
"transport_survives": True,
}
def build_structured_error_payload(
classification: dict[str, Any],
*,
tool_name: str | None = None,
profile_name: str | None = None,
) -> dict[str, Any]:
"""LLM-safe structured payload — fixed message + typed metadata only."""
try:
reason = str(classification.get("reason_code") or REASON_INTERNAL_ERROR)
message = fixed_message(reason)
# Refuse to emit any classification message that is not the fixed constant.
if classification.get("message") != message:
message = fixed_message(reason)
payload: dict[str, Any] = {
"success": False,
"isError": True,
"reason_code": reason if reason in FIXED_MESSAGES else REASON_INTERNAL_ERROR,
"error_class": classification.get("error_class") or ERROR_CLASS_INTERNAL,
"message": message,
"transport_survives": True,
"retryable": classification.get("error_class")
in {
ERROR_CLASS_AUTHENTICATION,
ERROR_CLASS_NETWORK,
ERROR_CLASS_CONFIGURATION,
},
}
status = classification.get("http_status")
if isinstance(status, int):
payload["http_status"] = status
if tool_name and isinstance(tool_name, str):
# Tool names are identifiers, not secrets; bound length.
payload["tool"] = tool_name[:120]
if profile_name and isinstance(profile_name, str):
payload["profile"] = profile_name[:80]
return payload
except Exception:
return {
"success": False,
"isError": True,
"reason_code": REASON_INTERNAL_ERROR,
"error_class": ERROR_CLASS_INTERNAL,
"message": fixed_message(REASON_INTERNAL_ERROR),
"transport_survives": True,
"retryable": False,
}
def log_sanitized_daemon_reason(
classification: dict[str, Any],
*,
tool_name: str | None = None,
stream=None,
) -> None:
"""Daemon log: reason codes only — never exception text or response bodies."""
stream = stream if stream is not None else sys.stderr
try:
reason = classification.get("reason_code") or REASON_INTERNAL_ERROR
error_class = classification.get("error_class") or ERROR_CLASS_INTERNAL
# Only emit known tokens; never classification['message'] from callers
# that might have been poisoned.
if reason not in FIXED_MESSAGES:
reason = REASON_INTERNAL_ERROR
error_class = ERROR_CLASS_INTERNAL
parts = [
"mcp_tool_error",
f"reason_code={reason}",
f"error_class={error_class}",
]
if tool_name and isinstance(tool_name, str):
parts.append(f"tool={tool_name[:120]}")
status = classification.get("http_status")
if isinstance(status, int):
parts.append(f"http_status={status}")
# Intentionally no detail= / message= field — secrets lived there.
line = " ".join(parts)
stream.write(line + "\n")
if hasattr(stream, "flush"):
stream.flush()
logger.warning(line)
except Exception:
# Fail closed: never fall back to logging the exception.
try:
stream.write(
"mcp_tool_error reason_code=internal_error "
"error_class=internal\n"
)
if hasattr(stream, "flush"):
stream.flush()
except Exception:
pass
def to_call_tool_result(
exc: BaseException,
*,
tool_name: str | None = None,
profile_name: str | None = None,
log: bool = True,
) -> Any:
"""Build a FastMCP ``CallToolResult`` with ``isError=True`` for *exc*."""
from mcp.types import CallToolResult, TextContent
try:
classification = classify_exception(exc)
if log:
log_sanitized_daemon_reason(classification, tool_name=tool_name)
payload = build_structured_error_payload(
classification, tool_name=tool_name, profile_name=profile_name
)
text = json.dumps(payload, indent=2, sort_keys=True)
return CallToolResult(
content=[TextContent(type="text", text=text)],
structuredContent=payload,
isError=True,
)
except Exception:
# Absolute fail-closed path — no exception text.
fallback = {
"success": False,
"isError": True,
"reason_code": REASON_INTERNAL_ERROR,
"error_class": ERROR_CLASS_INTERNAL,
"message": fixed_message(REASON_INTERNAL_ERROR),
"transport_survives": True,
"retryable": False,
}
return CallToolResult(
content=[
TextContent(
type="text",
text=json.dumps(fallback, indent=2, sort_keys=True),
)
],
structuredContent=fallback,
isError=True,
)
def install_tool_run_boundary(Tool) -> bool:
"""Install a **narrow** error boundary around FastMCP ``Tool.run``.
Strategy (preserves framework semantics):
* Call the **original** ``Tool.run`` for the success path (async, return
types, convert_result, protocol behavior unchanged).
* Re-raise ``UrlElicitationRequiredError`` and other control-flow
exceptions without mapping to ``internal_error``.
* Map typed Gitea client failures (and ToolError whose ``__cause__`` is
typed) to structured ``CallToolResult(isError=True)``.
* Map remaining unexpected tool failures to fixed ``internal_error``
isError results (transport survival) without secret-bearing text.
* Idempotent: second install is a no-op and returns ``False``.
"""
if getattr(Tool.run, _INSTALL_FLAG, False):
return False
from mcp.server.fastmcp.exceptions import ToolError
from mcp.shared.exceptions import UrlElicitationRequiredError
original_run = Tool.run
async def run_boundary(
self,
arguments: dict[str, Any],
context=None,
convert_result: bool = False,
) -> Any:
try:
return await original_run(
self,
arguments,
context=context,
convert_result=convert_result,
)
except UrlElicitationRequiredError:
# Framework control-flow — must not become internal_error.
raise
except BaseException as exc:
if _is_framework_control_flow(exc):
raise
if not isinstance(exc, Exception):
raise
# Prefer typed cause under FastMCP ToolError wrappers.
target: BaseException = exc
if isinstance(exc, ToolError) and exc.__cause__ is not None:
target = exc.__cause__
# Known client failures → structured isError with reason codes.
# Unexpected failures → fixed internal_error isError (no secrets).
profile_name = _safe_profile_name()
return to_call_tool_result(
target,
tool_name=getattr(self, "name", None),
profile_name=profile_name,
)
setattr(run_boundary, _INSTALL_FLAG, True)
setattr(run_boundary, _ORIGINAL_ATTR, original_run)
Tool.run = run_boundary # type: ignore[method-assign]
return True
def boundary_is_installed(Tool) -> bool:
"""True when the #699 boundary is active on *Tool.run*."""
return bool(getattr(Tool.run, _INSTALL_FLAG, False))
+657 -43
View File
@@ -524,13 +524,26 @@ def assess_lease_inventory(
"reclaimable_review_leases": reclaimable,
}
# Canonical next-action vocabulary for reviewer lease handoff (#599).
# Canonical next-action vocabulary for reviewer lease handoff (#599, #691).
NEXT_ACTION_ACQUIRE = "acquire"
NEXT_ACTION_WAIT = "wait"
NEXT_ACTION_RESUME_EXACT_OWNER_SESSION = "resume_exact_owner_session"
NEXT_ACTION_RELEASE_EXPIRED_LEASE = "release_expired_lease"
NEXT_ACTION_OPERATOR_AUTHORIZED_CLEANUP = "operator_authorized_cleanup"
NEXT_ACTION_REPAIR_WORKTREE_BINDING = "repair_worktree_binding"
NEXT_ACTION_CLEANUP_OBSOLETE_LEASE = "cleanup_obsolete_reviewer_comment_lease"
CLEANUP_OBSOLETE_LEASE_TOOL = "gitea_cleanup_obsolete_reviewer_comment_lease"
CLEANUP_OBSOLETE_LEASE_CONFIRMATION_PREFIX = "CLEANUP OBSOLETE REVIEWER LEASE "
# Formal terminal review verdicts that complete a leased-head workflow (#691).
_TERMINAL_REVIEW_VERDICTS = frozenset({
"APPROVED",
"REQUEST_CHANGES",
"approved",
"request_changes",
"REQUESTCHANGES",
})
_HANDOFF_CLASSIFICATIONS = frozenset({
"no_lease",
@@ -539,6 +552,12 @@ _HANDOFF_CLASSIFICATIONS = frozenset({
"foreign_active",
"foreign_reclaimable",
"foreign_expired",
"foreign_active_current_head",
"foreign_expired_current_head",
"foreign_completed_superseded_head",
"foreign_expired_superseded_head",
"orphaned_owner_missing",
"ambiguous_conflicting_evidence",
"instructed_lease_missing_with_replacement",
"worktree_binding_mismatch",
})
@@ -551,6 +570,476 @@ def _norm_path(value: str | None) -> str:
return os.path.normpath(text.rstrip("/"))
def _normalize_verdict(value: str | None) -> str:
text = (value or "").strip().upper().replace("-", "_").replace(" ", "_")
if text in {"REQUESTCHANGES", "REQUEST_CHANGES", "CHANGES_REQUESTED"}:
return "REQUEST_CHANGES"
if text in {"APPROVED", "APPROVE"}:
return "APPROVED"
return text
def formal_terminal_review_for_head(
formal_reviews: list[dict] | None,
*,
leased_head: str | None,
) -> dict[str, Any] | None:
"""Return the latest undismissed terminal formal review for *leased_head*."""
head = _normalize_sha(leased_head)
if not head:
return None
matches: list[dict[str, Any]] = []
for review in formal_reviews or []:
if review.get("dismissed"):
continue
verdict = _normalize_verdict(
review.get("verdict") or review.get("state") or review.get("body_state")
)
if verdict not in {"APPROVED", "REQUEST_CHANGES"}:
continue
rhead = _normalize_sha(
review.get("reviewed_head_sha")
or review.get("commit_id")
or review.get("head_sha")
)
if rhead != head:
continue
matches.append({**review, "verdict": verdict, "reviewed_head_sha": rhead})
if not matches:
return None
return matches[-1]
def find_newest_nonterminal_lease(
comments: list[dict],
*,
pr_number: int,
now: datetime | None = None,
include_expired: bool = True,
) -> dict[str, Any] | None:
"""Newest non-terminal lease marker, optionally including expired ones (#691).
Unlike ``find_active_reviewer_lease``, this retains expired non-terminal
markers so diagnosis/cleanup can still name the obsolete lease after
``expires_at`` (comment-backed ledger; no control-plane ``lease_id``).
"""
now = now or datetime.now(timezone.utc)
entries = list(reversed(_lease_entries(comments, pr_number=pr_number)))
for entry in entries:
phase = (entry.get("phase") or "").strip().lower()
if phase in _TERMINAL_PHASES:
# Newest terminal ends the ledger chain for active acquisition, but
# an older non-terminal is not "active". Stop at newest marker.
return None
expired = _lease_expired(entry, now=now)
if expired and not include_expired:
return None
lease = dict(entry)
lease["freshness"] = classify_lease_freshness(lease, now=now)
lease["expired"] = expired
return lease
return None
def cleanup_confirmation_for_pr(pr_number: int) -> str:
return f"{CLEANUP_OBSOLETE_LEASE_CONFIRMATION_PREFIX}{int(pr_number)}"
def assess_obsolete_reviewer_comment_lease_cleanup(
comments: list[dict],
*,
pr_number: int,
current_head_sha: str | None,
formal_reviews: list[dict] | None = None,
repo: str | None = None,
expected_repo: str | None = None,
requesting_session_id: str | None = None,
controller_recovery_authorized: bool = False,
worktree_exists: bool | None = None,
worktree_clean: bool | None = None,
worktree_has_unpreserved_work: bool | None = None,
owner_process_alive: bool | None = None,
owner_pid_observed: int | None = None,
requesting_pid: int | None = None,
current_head_review_in_progress: bool = False,
expected_lease_comment_id: int | None = None,
expected_session_id: str | None = None,
expected_leased_head: str | None = None,
confirmation: str | None = None,
apply: bool = False,
now: datetime | None = None,
) -> dict[str, Any]:
"""Guarded cleanup eligibility for obsolete comment-backed reviewer leases (#691).
Cleanup is never transfer/adoption/repoint and never uses PID equality as
ownership. Eligible only when evidence proves the lease is past expiry and/or
pinned to a superseded head with a completed formal terminal review, and
every safety boundary holds.
"""
now = now or datetime.now(timezone.utc)
reasons: list[str] = []
fail_closed_reasons: list[str] = []
current_head = _normalize_sha(current_head_sha)
req_session = (requesting_session_id or "").strip()
lease = find_newest_nonterminal_lease(
comments, pr_number=pr_number, now=now, include_expired=True
)
if not lease:
# Fall back to active finder (unexpired only) for report consistency.
lease = find_active_reviewer_lease(comments, pr_number=pr_number, now=now)
classification = "no_lease"
cleanup_allowed = False
release_body: str | None = None
audit_comment_body: str | None = None
terminal_review = None
leased_head = None
head_superseded = False
past_expiry = False
expires_parseable = True
if not lease:
fail_closed_reasons.append(
f"PR #{pr_number}: no non-terminal comment-backed reviewer lease to clean"
)
classification = "no_lease"
else:
leased_head = _normalize_sha(lease.get("candidate_head"))
expires_raw = lease.get("expires_at")
expires_at = _parse_timestamp(expires_raw)
if expires_raw and expires_at is None:
expires_parseable = False
fail_closed_reasons.append(
"lease expires_at cannot be parsed or trusted (fail closed)"
)
past_expiry = bool(expires_at and expires_at <= now)
freshness = lease.get("freshness") or classify_lease_freshness(lease, now=now)
owner_session = (lease.get("session_id") or "").strip()
is_requesting_owner = bool(
req_session and owner_session and req_session == owner_session
)
# Identity pins (repo / PR / session / head / comment) must match when
# the caller supplies expected evidence.
lease_repo = (lease.get("repo") or "").strip()
exp_repo = (expected_repo or repo or "").strip()
if exp_repo and lease_repo and exp_repo != lease_repo:
fail_closed_reasons.append(
f"repository identity mismatch: lease repo={lease_repo!r} "
f"expected={exp_repo!r}"
)
if lease.get("pr_number") not in (None, pr_number):
fail_closed_reasons.append(
f"PR identity mismatch: lease pr={lease.get('pr_number')} "
f"requested={pr_number}"
)
if expected_lease_comment_id is not None:
cid = lease.get("comment_id")
if cid is None or int(cid) != int(expected_lease_comment_id):
fail_closed_reasons.append(
"lease comment_id does not match expected evidence "
f"(lease={cid}, expected={expected_lease_comment_id})"
)
if expected_session_id:
if owner_session != expected_session_id.strip():
fail_closed_reasons.append(
"lease session_id does not match expected evidence "
f"(lease={owner_session}, expected={expected_session_id})"
)
if expected_leased_head:
exp_head = _normalize_sha(expected_leased_head)
if not exp_head or exp_head != leased_head:
fail_closed_reasons.append(
"leased head does not match expected evidence "
f"(lease={leased_head}, expected={exp_head})"
)
# PID equality is never ownership proof (#691).
if (
owner_pid_observed is not None
and requesting_pid is not None
and int(owner_pid_observed) == int(requesting_pid)
):
reasons.append(
"observed PID equals requesting PID but PID equality is NOT "
"ownership proof; ignored for authorization"
)
if is_requesting_owner:
fail_closed_reasons.append(
"requesting session owns the lease; use "
"gitea_release_reviewer_pr_lease (owner path), not non-owner cleanup"
)
if current_head_review_in_progress:
fail_closed_reasons.append(
"a current-head review submission is in progress; cleanup denied"
)
if not current_head:
fail_closed_reasons.append(
"current PR head SHA missing or unparseable (fail closed)"
)
if not leased_head:
fail_closed_reasons.append(
"lease candidate_head missing or unparseable (fail closed)"
)
head_superseded = bool(
current_head and leased_head and current_head != leased_head
)
head_matches_current = bool(
current_head and leased_head and current_head == leased_head
)
terminal_review = formal_terminal_review_for_head(
formal_reviews, leased_head=leased_head
)
has_terminal = terminal_review is not None
# Worktree safety.
if worktree_has_unpreserved_work is True or worktree_clean is False:
fail_closed_reasons.append(
"lease worktree is dirty or has unpreserved work; cleanup denied"
)
if (
worktree_exists is True
and worktree_clean is None
and worktree_has_unpreserved_work is None
):
# Unknown cleanliness when path exists — fail closed.
fail_closed_reasons.append(
"lease worktree exists but cleanliness is unknown (fail closed)"
)
# Classification matrix (#691).
if head_matches_current and freshness in {"active", "stale_warning"}:
classification = "foreign_active_current_head"
fail_closed_reasons.append(
"genuinely active foreign lease on the current PR head; "
"cleanup denied (fail closed)"
)
elif head_matches_current and past_expiry:
classification = "foreign_expired_current_head"
# Expired on current head: owner-missing / orphan path may apply.
if owner_process_alive is True:
fail_closed_reasons.append(
"lease expired on current head but owner process still alive "
"with plausible activity; cleanup denied"
)
elif worktree_clean is False:
fail_closed_reasons.append(
"owner process absent but worktree dirty; cleanup denied"
)
elif owner_process_alive is False and (
worktree_clean is True or worktree_exists is False
):
if controller_recovery_authorized:
classification = "orphaned_owner_missing"
else:
fail_closed_reasons.append(
"controller/recovery capability not authorized for orphan cleanup"
)
else:
fail_closed_reasons.append(
"insufficient orphan evidence for expired current-head lease "
"(need owner_process_alive=false and clean/absent worktree)"
)
elif head_superseded and has_terminal and past_expiry:
classification = "foreign_expired_superseded_head"
elif head_superseded and has_terminal and not past_expiry:
classification = "foreign_completed_superseded_head"
elif head_superseded and not has_terminal:
classification = "ambiguous_conflicting_evidence"
fail_closed_reasons.append(
"lease head is superseded but no formal terminal review exists "
"for the leased head (fail closed)"
)
elif not head_superseded and not past_expiry and freshness in {
"active", "stale_warning"
}:
classification = "foreign_active_current_head"
fail_closed_reasons.append(
"foreign lease still active on current head; wait or use owner release"
)
elif past_expiry and not head_superseded:
classification = "foreign_expired_current_head"
else:
classification = "ambiguous_conflicting_evidence"
fail_closed_reasons.append(
"lease evidence is ambiguous; cleanup denied (fail closed)"
)
# Recent owner progress on a non-superseded active lease blocks cleanup.
minutes = _minutes_since_activity(lease, now=now)
if (
head_matches_current
and freshness == "active"
and minutes is not None
and minutes < STALE_WARNING_MINUTES
):
fail_closed_reasons.append(
"owner session has recent authenticated progress on current head; "
"cleanup denied"
)
# Authority + confirmation for apply.
if not controller_recovery_authorized:
if classification in {
"foreign_completed_superseded_head",
"foreign_expired_superseded_head",
"foreign_expired_current_head",
"orphaned_owner_missing",
}:
fail_closed_reasons.append(
"controller/recovery capability required "
"(controller_recovery_authorized=true)"
)
expected_conf = cleanup_confirmation_for_pr(pr_number)
if apply:
if (confirmation or "").strip() != expected_conf:
fail_closed_reasons.append(
f"confirmation must equal exactly {expected_conf!r}"
)
# Superseded + terminal path does not require past_expiry (AC1).
eligible_class = classification in {
"foreign_completed_superseded_head",
"foreign_expired_superseded_head",
"orphaned_owner_missing",
"foreign_expired_current_head",
}
# foreign_expired_current_head needs orphan/clean worktree + authority.
if classification == "foreign_expired_current_head":
if worktree_clean is not True and worktree_exists is not False:
if "worktree" not in " ".join(fail_closed_reasons):
fail_closed_reasons.append(
"expired current-head cleanup requires proven-clean "
"worktree or absent worktree"
)
if owner_process_alive is True:
fail_closed_reasons.append(
"owner process still alive on expired current-head lease"
)
cleanup_allowed = (
eligible_class
and expires_parseable
and not fail_closed_reasons
and not is_requesting_owner
)
if cleanup_allowed:
release_body = format_lease_body(
repo=lease.get("repo") or exp_repo or "",
pr_number=pr_number,
issue_number=lease.get("issue_number"),
reviewer_identity=lease.get("reviewer_identity") or "",
profile=lease.get("profile") or "unknown",
session_id=owner_session or "unknown",
worktree=lease.get("worktree") or "",
phase="released",
candidate_head=leased_head,
target_branch=lease.get("target_branch") or "master",
target_branch_sha=lease.get("target_branch_sha"),
last_activity=now,
blocker="obsolete-superseded-or-expired-lease",
)
audit_comment_body = (
"## Canonical obsolete reviewer lease cleanup (#691)\n\n"
f"- pr: #{pr_number}\n"
f"- lease_comment_id: {lease.get('comment_id')}\n"
f"- session_id: {owner_session}\n"
f"- leased_head: {leased_head}\n"
f"- current_head: {current_head}\n"
f"- expires_at: {lease.get('expires_at')}\n"
f"- classification: {classification}\n"
f"- terminal_review_verdict: "
f"{(terminal_review or {}).get('verdict')}\n"
f"- tool: {CLEANUP_OBSOLETE_LEASE_TOOL}\n"
"- action: posted terminal phase=released lease marker; "
"did not transfer validation, decision, or workflow proof; "
"did not repoint lease to the new head; did not delete history\n"
)
reasons.append(
f"cleanup eligible ({classification}); post terminal released "
"marker via sanctioned tool"
)
else:
reasons.extend(fail_closed_reasons)
return {
"pr_number": pr_number,
"classification": classification,
"blocker_kind": classification if not cleanup_allowed else "none",
"cleanup_allowed": cleanup_allowed,
"mutation_allowed": False, # never grants review mutation
"mutation_eligibility": "prohibited" if not cleanup_allowed else "cleanup_only",
"exact_next_action": (
NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
if cleanup_allowed
else (
NEXT_ACTION_WAIT
if classification
in {
"foreign_active_current_head",
"ambiguous_conflicting_evidence",
}
else NEXT_ACTION_OPERATOR_AUTHORIZED_CLEANUP
)
),
"cleanup_tool": CLEANUP_OBSOLETE_LEASE_TOOL,
"required_confirmation": cleanup_confirmation_for_pr(pr_number),
"leased_head": leased_head,
"current_head": current_head,
"head_superseded": head_superseded,
"past_expiry": past_expiry,
"expires_at": (lease or {}).get("expires_at") if lease else None,
"expires_parseable": expires_parseable,
"terminal_review": terminal_review,
"terminal_review_present": terminal_review is not None,
"worktree_state": {
"path": (lease or {}).get("worktree") if lease else None,
"exists": worktree_exists,
"clean": worktree_clean,
"has_unpreserved_work": worktree_has_unpreserved_work,
},
"owner_session_evidence": {
"session_id": (lease or {}).get("session_id") if lease else None,
"reviewer_identity": (
(lease or {}).get("reviewer_identity") if lease else None
),
"process_alive": owner_process_alive,
"pid_observed": owner_pid_observed,
"pid_is_not_ownership_proof": True,
"requesting_session_is_owner": bool(
lease
and req_session
and (lease.get("session_id") or "").strip() == req_session
),
},
"active_lease": lease,
"release_body": release_body,
"audit_comment_body": audit_comment_body,
"controller_recovery_authorized": controller_recovery_authorized,
"reasons": reasons if reasons else fail_closed_reasons,
"fail_closed_reasons": fail_closed_reasons,
"forbidden": [
"manual comment deletion",
"database edits",
"mtime manipulation",
"PID-based ownership",
"direct session-state seeding",
"lease stealing or adoption",
"repointing old lease to new head",
"transfer of validation or decision state",
"worktree reuse by replacement reviewer",
],
}
def diagnose_reviewer_pr_lease_handoff(
comments: list[dict],
*,
@@ -561,40 +1050,50 @@ def diagnose_reviewer_pr_lease_handoff(
env_bound_worktree: str | None = None,
instructed_session_id: str | None = None,
instructed_comment_id: int | None = None,
current_head_sha: str | None = None,
formal_reviews: list[dict] | None = None,
worktree_exists: bool | None = None,
worktree_clean: bool | None = None,
owner_process_alive: bool | None = None,
now: datetime | None = None,
) -> dict[str, Any]:
"""Classify open-PR reviewer lease handoff and emit a canonical next action (#599).
"""Classify open-PR reviewer lease handoff and emit a canonical next action (#599, #691).
Read-only diagnosis. Never steals, releases, or adopts a foreign lease.
Fail-closed acquisition rules for active foreign leases remain intact.
Returns a structured diagnosis with:
- classification
- next_action (one of wait / resume_exact_owner_session /
release_expired_lease / operator_authorized_cleanup /
repair_worktree_binding / acquire)
- classification (including #691 superseded/expired distinctions)
- next_action (including cleanup_obsolete_reviewer_comment_lease)
- active_lease identity fields when present
- worktree_binding match result
- instructed-lease mismatch flags
- cleanup tool/confirmation when cleanup-eligible
"""
now = now or datetime.now(timezone.utc)
session_id = (current_session_id or "").strip()
identity = (current_reviewer_identity or "").strip()
instructed_sid = (instructed_session_id or "").strip()
reasons: list[str] = []
current_head = _normalize_sha(current_head_sha)
active = find_active_reviewer_lease(comments, pr_number=pr_number, now=now)
# Also surface expired non-terminal newest marker for #691 diagnosis.
newest_nt = find_newest_nonterminal_lease(
comments, pr_number=pr_number, now=now, include_expired=True
)
lease_for_class = active or newest_nt
session_lease = get_session_lease()
# Worktree binding: env-bound vs proposed vs active lease worktree.
env_wt = _norm_path(env_bound_worktree)
prop_wt = _norm_path(proposed_worktree)
lease_wt = _norm_path((active or {}).get("worktree") if active else None)
lease_wt = _norm_path((lease_for_class or {}).get("worktree") if lease_for_class else None)
binding_mismatch = False
binding_details: dict[str, Any] = {
"env_bound_worktree": env_bound_worktree or None,
"proposed_worktree": proposed_worktree or None,
"lease_worktree": (active or {}).get("worktree") if active else None,
"lease_worktree": (lease_for_class or {}).get("worktree") if lease_for_class else None,
"match": True,
}
paths = [p for p in (env_wt, prop_wt, lease_wt) if p]
@@ -608,13 +1107,13 @@ def diagnose_reviewer_pr_lease_handoff(
# Instructed lease gone while a different lease is active (PR #592-style).
instructed_missing_with_replacement = False
if instructed_sid or instructed_comment_id is not None:
if not active:
if not lease_for_class:
reasons.append(
"instructed lease is gone and no active replacement lease remains"
)
else:
owner = (active.get("session_id") or "").strip()
cid = active.get("comment_id")
owner = (lease_for_class.get("session_id") or "").strip()
cid = lease_for_class.get("comment_id")
sid_mismatch = bool(instructed_sid and owner and owner != instructed_sid)
cid_mismatch = (
instructed_comment_id is not None
@@ -631,35 +1130,94 @@ def diagnose_reviewer_pr_lease_handoff(
# Classification + next_action.
classification = "no_lease"
next_action = NEXT_ACTION_ACQUIRE
cleanup_hint: dict[str, Any] | None = None
if active:
owner = (active.get("session_id") or "").strip()
freshness = active.get("freshness") or classify_lease_freshness(
active, now=now
if lease_for_class:
owner = (lease_for_class.get("session_id") or "").strip()
freshness = lease_for_class.get("freshness") or classify_lease_freshness(
lease_for_class, now=now
)
owner_identity = (active.get("reviewer_identity") or "").strip()
owner_identity = (lease_for_class.get("reviewer_identity") or "").strip()
is_own = bool(session_id and owner and owner == session_id)
# Same identity alone is NOT ownership for resume; session_id must match.
same_identity = bool(
identity and owner_identity and identity == owner_identity
)
leased_head = _normalize_sha(lease_for_class.get("candidate_head"))
head_superseded = bool(
current_head and leased_head and current_head != leased_head
)
head_current = bool(
current_head and leased_head and current_head == leased_head
)
past_expiry = bool(lease_for_class.get("expired")) or freshness == "expired"
if not past_expiry:
past_expiry = _lease_expired(lease_for_class, now=now)
terminal = formal_terminal_review_for_head(
formal_reviews, leased_head=leased_head
)
if is_own and freshness in {"active", "stale_warning"}:
if is_own and freshness in {"active", "stale_warning"} and not past_expiry:
classification = "own_active"
next_action = NEXT_ACTION_RESUME_EXACT_OWNER_SESSION
elif is_own and freshness in {"reclaimable", "expired"}:
elif is_own and (freshness in {"reclaimable", "expired"} or past_expiry):
classification = "own_expired"
next_action = NEXT_ACTION_RELEASE_EXPIRED_LEASE
reasons.append(
f"own lease freshness is '{freshness}'; release via "
"gitea_release_reviewer_pr_lease then re-acquire"
)
elif not is_own and freshness in {"active", "stale_warning"}:
classification = "foreign_active"
elif not is_own and head_superseded and terminal and past_expiry:
classification = "foreign_expired_superseded_head"
next_action = NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
reasons.append(
"foreign lease expired and pinned to superseded head with "
"formal terminal review; use guarded obsolete-lease cleanup"
)
elif not is_own and head_superseded and terminal and not past_expiry:
classification = "foreign_completed_superseded_head"
next_action = NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
reasons.append(
"foreign lease pinned to superseded head with completed formal "
"review; use guarded obsolete-lease cleanup (do not wait indefinitely)"
)
elif not is_own and head_superseded and not terminal:
classification = "ambiguous_conflicting_evidence"
next_action = NEXT_ACTION_WAIT
reasons.append(
"lease head superseded but no formal terminal review for leased "
"head; fail closed / wait (no indefinite steal)"
)
elif not is_own and head_current and past_expiry:
classification = "foreign_expired_current_head"
if owner_process_alive is False and worktree_clean is True:
classification = "orphaned_owner_missing"
next_action = NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
reasons.append(
"foreign expired lease on current head; owner process absent "
"and worktree clean — guarded orphan cleanup eligible"
)
elif owner_process_alive is False and worktree_clean is False:
classification = "ambiguous_conflicting_evidence"
next_action = NEXT_ACTION_WAIT
reasons.append(
"owner process absent but worktree dirty; cleanup denied"
)
else:
next_action = NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
reasons.append(
"foreign expired lease on current head; use guarded cleanup "
"when worktree/process evidence permits"
)
elif not is_own and freshness in {"active", "stale_warning"} and not past_expiry:
classification = (
"foreign_active_current_head" if head_current or not current_head
else "foreign_active"
)
next_action = NEXT_ACTION_WAIT
reasons.append(
f"foreign active reviewer lease (session_id={owner}, "
f"phase={active.get('phase')}, freshness={freshness}); "
f"phase={lease_for_class.get('phase')}, freshness={freshness}); "
"do not submit; do not steal"
)
if same_identity:
@@ -674,11 +1232,12 @@ def diagnose_reviewer_pr_lease_handoff(
f"foreign reclaimable lease (session_id={owner}); clear only via "
"sanctioned gitea_release_reviewer_pr_lease when reclaimable"
)
elif not is_own and freshness == "expired":
elif not is_own and (freshness == "expired" or past_expiry):
classification = "foreign_expired"
next_action = NEXT_ACTION_RELEASE_EXPIRED_LEASE
reasons.append(
f"foreign expired lease (session_id={owner}); use sanctioned release"
f"foreign expired lease (session_id={owner}); use sanctioned release "
f"or {CLEANUP_OBSOLETE_LEASE_TOOL}"
)
else:
classification = "foreign_active"
@@ -691,13 +1250,26 @@ def diagnose_reviewer_pr_lease_handoff(
if instructed_missing_with_replacement and classification.startswith(
"foreign"
):
classification = "instructed_lease_missing_with_replacement"
# Foreign active still means wait; reclaimable still release.
if next_action == NEXT_ACTION_WAIT:
reasons.append(
"replacement foreign lease is active — wait; "
"operator_authorized_cleanup only with explicit operator authority"
)
# Preserve #691 cleanup path when superseded/expired; otherwise
# keep the PR #592 instructed-missing label.
if next_action != NEXT_ACTION_CLEANUP_OBSOLETE_LEASE:
classification = "instructed_lease_missing_with_replacement"
if next_action == NEXT_ACTION_WAIT:
reasons.append(
"replacement foreign lease is active — wait; "
"operator_authorized_cleanup only with explicit operator authority"
)
if next_action == NEXT_ACTION_CLEANUP_OBSOLETE_LEASE:
cleanup_hint = {
"cleanup_tool": CLEANUP_OBSOLETE_LEASE_TOOL,
"required_confirmation": cleanup_confirmation_for_pr(pr_number),
"controller_recovery_authorized_required": True,
"leased_head": leased_head,
"current_head": current_head,
"expires_at": lease_for_class.get("expires_at"),
"terminal_review_verdict": (terminal or {}).get("verdict"),
}
else:
classification = "no_lease"
next_action = NEXT_ACTION_ACQUIRE
@@ -720,29 +1292,55 @@ def diagnose_reviewer_pr_lease_handoff(
)
lease_summary = None
if active:
if lease_for_class:
lease_summary = {
"comment_id": active.get("comment_id"),
"session_id": active.get("session_id"),
"phase": active.get("phase"),
"candidate_head": active.get("candidate_head"),
"expires_at": active.get("expires_at"),
"last_activity": active.get("last_activity"),
"freshness": active.get("freshness")
or classify_lease_freshness(active, now=now),
"reviewer_identity": active.get("reviewer_identity"),
"profile": active.get("profile"),
"worktree": active.get("worktree"),
"blocker": active.get("blocker"),
"comment_id": lease_for_class.get("comment_id"),
"session_id": lease_for_class.get("session_id"),
"phase": lease_for_class.get("phase"),
"candidate_head": lease_for_class.get("candidate_head"),
"expires_at": lease_for_class.get("expires_at"),
"last_activity": lease_for_class.get("last_activity"),
"freshness": lease_for_class.get("freshness")
or classify_lease_freshness(lease_for_class, now=now),
"reviewer_identity": lease_for_class.get("reviewer_identity"),
"profile": lease_for_class.get("profile"),
"worktree": lease_for_class.get("worktree"),
"blocker": lease_for_class.get("blocker"),
}
return {
"pr_number": pr_number,
"classification": classification,
"blocker_kind": classification,
"next_action": next_action,
"exact_next_action": next_action,
"active_lease": lease_summary,
"session_lease": session_lease,
"worktree_binding": binding_details,
"leased_head": (lease_summary or {}).get("candidate_head"),
"current_head": current_head,
"expires_at": (lease_summary or {}).get("expires_at"),
"terminal_review_state": (
formal_terminal_review_for_head(
formal_reviews,
leased_head=(lease_summary or {}).get("candidate_head"),
)
if lease_summary
else None
),
"worktree_state": {
"exists": worktree_exists,
"clean": worktree_clean,
"path": (lease_summary or {}).get("worktree"),
},
"owner_session_evidence": {
"session_id": (lease_summary or {}).get("session_id"),
"process_alive": owner_process_alive,
"pid_is_not_ownership_proof": True,
},
"cleanup": cleanup_hint,
"cleanup_tool": (cleanup_hint or {}).get("cleanup_tool"),
"required_confirmation": (cleanup_hint or {}).get("required_confirmation"),
"instructed_session_id": instructed_session_id,
"instructed_comment_id": instructed_comment_id,
"instructed_lease_missing_with_replacement": instructed_missing_with_replacement,
@@ -751,6 +1349,19 @@ def diagnose_reviewer_pr_lease_handoff(
and not binding_mismatch
and bool(session_lease)
),
"mutation_eligibility": (
"allowed"
if (
next_action == NEXT_ACTION_RESUME_EXACT_OWNER_SESSION
and not binding_mismatch
and bool(session_lease)
)
else (
"cleanup_only"
if next_action == NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
else "prohibited"
)
),
"reasons": reasons,
"forbidden": [
"manual lock deletion",
@@ -758,5 +1369,8 @@ def diagnose_reviewer_pr_lease_handoff(
"mtime manipulation",
"direct _SESSION_LEASE seeding",
"silent foreign lease steal",
"PID-based ownership",
"repointing old lease to new head",
"transfer of validation or decision state",
],
}
+10
View File
@@ -76,6 +76,16 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
"permission": "gitea.pr.comment",
"role": "reviewer",
},
# #691: guarded non-owner cleanup of obsolete comment-backed reviewer leases.
# Apply path posts lease release + audit comments (gitea.pr.comment).
"cleanup_obsolete_reviewer_comment_lease": {
"permission": "gitea.pr.comment",
"role": "reviewer",
},
"gitea_cleanup_obsolete_reviewer_comment_lease": {
"permission": "gitea.pr.comment",
"role": "reviewer",
},
"blind_pr_queue_review": {
"permission": "gitea.pr.review",
"role": "reviewer",
+22 -16
View File
@@ -79,41 +79,46 @@ class TestApiRequestFailures(unittest.TestCase):
@patch("gitea_auth.urllib.request.urlopen")
def test_timeout_converted_to_runtimeerror(self, mock_open):
mock_open.side_effect = TimeoutError("timed out")
with self.assertRaises(RuntimeError) as ctx:
with self.assertRaises(gitea_auth.GiteaNetworkError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
self.assertIn("network error contacting Gitea", str(ctx.exception))
# Fixed message only (#699) — still a RuntimeError subclass.
self.assertIsInstance(ctx.exception, RuntimeError)
self.assertEqual(str(ctx.exception), "Network error contacting Gitea")
@patch("gitea_auth.urllib.request.urlopen")
def test_dns_network_failure_converted(self, mock_open):
mock_open.side_effect = urllib.error.URLError("Name or service not known")
with self.assertRaises(RuntimeError) as ctx:
with self.assertRaises(gitea_auth.GiteaNetworkError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
self.assertIn("network error contacting Gitea", str(ctx.exception))
self.assertEqual(str(ctx.exception), "Network error contacting Gitea")
@patch("gitea_auth.urllib.request.urlopen")
def test_502_upstream_message(self, mock_open):
mock_open.side_effect = http_error(502, "bad gateway")
with self.assertRaises(RuntimeError) as ctx:
with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
msg = str(ctx.exception)
self.assertIn("HTTP 502", msg)
self.assertIn("upstream unavailable", msg)
self.assertEqual(msg, "Gitea upstream unavailable")
self.assertEqual(ctx.exception.reason_code, "upstream_unavailable")
self.assertEqual(ctx.exception.http_status, 502)
@patch("gitea_auth.urllib.request.urlopen")
def test_503_upstream_message(self, mock_open):
mock_open.side_effect = http_error(503, "")
with self.assertRaises(RuntimeError) as ctx:
with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
self.assertIn("HTTP 503", str(ctx.exception))
self.assertIn("upstream unavailable", str(ctx.exception))
self.assertEqual(str(ctx.exception), "Gitea upstream unavailable")
self.assertEqual(ctx.exception.http_status, 503)
@patch("gitea_auth.urllib.request.urlopen")
def test_malformed_error_payload_does_not_crash(self, mock_open):
# Non-JSON garbage error body must still yield a clean RuntimeError.
# Non-JSON garbage error body must still yield a clean typed error
# with a fixed message (no body echo — #699).
mock_open.side_effect = http_error(500, "<html>garbage</html>")
with self.assertRaises(RuntimeError) as ctx:
with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
self.assertIn("HTTP 500", str(ctx.exception))
self.assertEqual(str(ctx.exception), "Gitea HTTP request failed")
self.assertNotIn("<html>", str(ctx.exception))
@patch("gitea_auth.urllib.request.urlopen")
def test_malformed_success_json_raises_clean_error(self, mock_open):
@@ -126,16 +131,17 @@ class TestApiRequestFailures(unittest.TestCase):
def test_no_secret_leak_in_error_body(self, mock_open):
mock_open.side_effect = http_error(
400, "failed: token supersecret123 rejected")
with self.assertRaises(RuntimeError) as ctx:
with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
msg = str(ctx.exception)
self.assertNotIn("supersecret123", msg)
self.assertIn(gitea_audit.REDACTED, msg)
# Fixed message — body never appears (stronger than redaction).
self.assertEqual(msg, "Gitea HTTP request failed")
@patch("gitea_auth.urllib.request.urlopen")
def test_auth_header_never_in_error(self, mock_open):
mock_open.side_effect = http_error(400, "bad request")
with self.assertRaises(RuntimeError) as ctx:
with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
self.assertNotIn(FAKE_AUTH, str(ctx.exception))
@@ -0,0 +1,599 @@
"""Guarded cleanup for obsolete comment-backed reviewer leases (#691).
Reproduces PR #688 lease comment 10749 class of defect: completed
REQUEST_CHANGES on head A, author pushes head B, foreign lease remains
pinned to A (and after expiry still has no non-owner cleanup path that
diagnosis can prescribe beyond indefinite wait).
"""
from __future__ import annotations
import sys
import unittest
from datetime import datetime, timedelta, timezone
from pathlib import Path
from unittest.mock import patch
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
import merger_lease_adoption as mla # noqa: E402
import reviewer_pr_lease as leases # noqa: E402
# PR #688 / comment 10749 reproduction fixtures
HEAD_A = "c7a444eb4b41cf916fdbd20a4999ffd78af496d0"
HEAD_B = "4a6357800364718a27a36ebc73578d4b929ff4aa"
SESSION_FOREIGN = "25883-7d4c6e6ebd53"
COMMENT_10749 = 10749
REPO = "Scaled-Tech-Consulting/Gitea-Tools"
PR = 688
ISSUE = 687
EXPIRES_10749 = "2026-07-13T04:23:00Z"
def _utc(dt: datetime) -> datetime:
return dt if dt.tzinfo else dt.replace(tzinfo=timezone.utc)
def _lease_comment(
*,
pr_number: int = PR,
session_id: str = SESSION_FOREIGN,
phase: str = "claimed",
candidate_head: str = HEAD_A,
comment_id: int = COMMENT_10749,
last_activity: datetime | None = None,
expires_at: datetime | None = None,
worktree: str = "branches/review-pr688-feat-issue-687-reconciler-branch-delete",
repo: str = REPO,
) -> dict:
now = last_activity or datetime.now(timezone.utc)
body = leases.format_lease_body(
repo=repo,
pr_number=pr_number,
issue_number=ISSUE,
reviewer_identity="sysadmin",
profile="prgs-reviewer",
session_id=session_id,
worktree=worktree,
phase=phase,
candidate_head=candidate_head,
target_branch="master",
target_branch_sha="b" * 40,
last_activity=now,
expires_at=expires_at,
)
return {
"id": comment_id,
"body": body,
"user": {"login": "sysadmin"},
"author": "sysadmin",
"created_at": now.isoformat(),
"updated_at": now.isoformat(),
}
def _reviews_for_head(head: str, verdict: str = "REQUEST_CHANGES") -> list[dict]:
return [
{
"verdict": verdict,
"reviewed_head_sha": head,
"dismissed": False,
"reviewer": "sysadmin",
}
]
def _assess(
comments,
*,
current_head=HEAD_B,
formal_reviews=None,
controller=True,
worktree_exists=True,
worktree_clean=True,
owner_process_alive=False,
requesting_session="fresh-controller",
apply=False,
confirmation=None,
**kwargs,
):
return leases.assess_obsolete_reviewer_comment_lease_cleanup(
comments,
pr_number=PR,
current_head_sha=current_head,
formal_reviews=formal_reviews if formal_reviews is not None else _reviews_for_head(HEAD_A),
repo=REPO,
expected_repo=REPO,
requesting_session_id=requesting_session,
controller_recovery_authorized=controller,
worktree_exists=worktree_exists,
worktree_clean=worktree_clean,
worktree_has_unpreserved_work=not worktree_clean if worktree_exists else False,
owner_process_alive=owner_process_alive,
owner_pid_observed=kwargs.get("owner_pid_observed"),
requesting_pid=kwargs.get("requesting_pid", 99999),
current_head_review_in_progress=kwargs.get(
"current_head_review_in_progress", False
),
expected_lease_comment_id=kwargs.get("expected_lease_comment_id"),
expected_session_id=kwargs.get("expected_session_id"),
expected_leased_head=kwargs.get("expected_leased_head"),
confirmation=confirmation
if confirmation is not None
else (leases.cleanup_confirmation_for_pr(PR) if apply else ""),
apply=apply,
now=kwargs.get("now"),
)
class TestIssue691SupersededHeadCleanup(unittest.TestCase):
def setUp(self):
leases.clear_session_lease()
def test_1_request_changes_then_push_expired_cleanup_succeeds(self):
"""Completed REQUEST_CHANGES on A, push B, lease A expires → cleanup OK."""
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(
last_activity=expires - timedelta(hours=2),
expires_at=expires,
)
result = _assess(
[claim],
formal_reviews=_reviews_for_head(HEAD_A, "REQUEST_CHANGES"),
now=now,
apply=True,
)
self.assertTrue(result["cleanup_allowed"], result["reasons"])
self.assertEqual(result["classification"], "foreign_expired_superseded_head")
self.assertEqual(
result["exact_next_action"], leases.NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
)
self.assertIn("phase: released", result["release_body"])
self.assertIn("obsolete-superseded-or-expired-lease", result["release_body"])
self.assertIsNotNone(result["audit_comment_body"])
self.assertEqual(result["cleanup_tool"], leases.CLEANUP_OBSOLETE_LEASE_TOOL)
def test_2_approve_then_push_cleanup_policy(self):
"""Completed APPROVE on A, push B → cleanup eligible (completed superseded)."""
now = datetime(2026, 7, 13, 1, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc) # not yet expired
claim = _lease_comment(
last_activity=now - timedelta(minutes=10),
expires_at=expires,
)
result = _assess(
[claim],
formal_reviews=_reviews_for_head(HEAD_A, "APPROVED"),
now=now,
)
self.assertTrue(result["cleanup_allowed"], result["reasons"])
self.assertEqual(result["classification"], "foreign_completed_superseded_head")
def test_3_active_current_head_cleanup_denied(self):
now = datetime.now(timezone.utc)
claim = _lease_comment(
candidate_head=HEAD_B,
last_activity=now - timedelta(minutes=5),
expires_at=now + timedelta(hours=2),
)
result = _assess(
[claim],
current_head=HEAD_B,
formal_reviews=_reviews_for_head(HEAD_B, "REQUEST_CHANGES"),
now=now,
)
self.assertFalse(result["cleanup_allowed"])
self.assertEqual(result["classification"], "foreign_active_current_head")
def test_4_foreign_owner_recent_progress_denied(self):
now = datetime.now(timezone.utc)
claim = _lease_comment(
candidate_head=HEAD_B,
last_activity=now - timedelta(minutes=2),
expires_at=now + timedelta(hours=2),
)
result = _assess(
[claim],
current_head=HEAD_B,
formal_reviews=[],
owner_process_alive=True,
now=now,
)
self.assertFalse(result["cleanup_allowed"])
self.assertTrue(
any("recent authenticated progress" in r for r in result["reasons"])
or any("current PR head" in r for r in result["reasons"])
)
def test_5_owner_absent_worktree_dirty_denied(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(
candidate_head=HEAD_B,
last_activity=expires - timedelta(hours=1),
expires_at=expires,
)
result = _assess(
[claim],
current_head=HEAD_B,
formal_reviews=[],
worktree_clean=False,
owner_process_alive=False,
now=now,
)
self.assertFalse(result["cleanup_allowed"])
self.assertTrue(any("dirty" in r for r in result["reasons"]))
def test_6_owner_absent_worktree_clean_orphan_ok(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(
candidate_head=HEAD_B,
last_activity=expires - timedelta(hours=1),
expires_at=expires,
)
result = _assess(
[claim],
current_head=HEAD_B,
formal_reviews=[],
worktree_clean=True,
owner_process_alive=False,
now=now,
)
self.assertTrue(result["cleanup_allowed"], result["reasons"])
self.assertEqual(result["classification"], "orphaned_owner_missing")
def test_7_pid_reuse_not_ownership(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
result = _assess(
[claim],
now=now,
owner_pid_observed=4242,
requesting_pid=4242,
)
self.assertTrue(
any("PID equality" in r or "NOT ownership" in r for r in result["reasons"])
or result["owner_session_evidence"]["pid_is_not_ownership_proof"]
)
# Still eligible via superseded+terminal+expired despite matching PID.
self.assertTrue(result["cleanup_allowed"], result["reasons"])
def test_8_comment_backed_no_db_lease_id(self):
"""Cleanup uses comment ledger only — no control-plane lease_id required."""
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
# Explicitly no lease_id field anywhere.
self.assertNotIn("lease_id", claim)
result = _assess([claim], now=now)
self.assertTrue(result["cleanup_allowed"], result["reasons"])
self.assertEqual(result["active_lease"]["comment_id"], COMMENT_10749)
self.assertIsNone(result["active_lease"].get("lease_id"))
def test_9_cleanup_posts_durable_audit_bodies(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
result = _assess([claim], now=now, apply=True)
self.assertTrue(result["cleanup_allowed"])
self.assertIn("#691", result["audit_comment_body"])
self.assertIn(str(COMMENT_10749), result["audit_comment_body"])
self.assertIn(HEAD_A, result["audit_comment_body"])
self.assertIn(HEAD_B, result["audit_comment_body"])
def test_10_fresh_acquire_after_cleanup_marker(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(
expires_at=expires,
last_activity=expires - timedelta(hours=1),
comment_id=COMMENT_10749,
)
assessed = _assess([claim], now=now, apply=True)
self.assertTrue(assessed["cleanup_allowed"])
release = {
"id": 99999,
"body": assessed["release_body"],
"user": {"login": "sysadmin"},
}
# Newest terminal marker ends active lease.
active = leases.find_active_reviewer_lease(
[claim, release], pr_number=PR, now=now
)
self.assertIsNone(active)
acq = leases.assess_acquire_lease(
[claim, release],
pr_number=PR,
reviewer_identity="sysadmin",
profile="prgs-reviewer",
session_id="fresh-reviewer-1",
repo=REPO,
issue_number=ISSUE,
worktree="branches/review-pr-688-fresh",
candidate_head=HEAD_B,
target_branch="master",
target_branch_sha="b" * 40,
now=now,
)
self.assertTrue(acq["acquire_allowed"], acq["reasons"])
def test_11_no_validation_state_transfer(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
result = _assess([claim], now=now, apply=True)
self.assertTrue(result["cleanup_allowed"])
# Release body keeps old candidate_head (no repoint).
self.assertIn(f"candidate_head: {HEAD_A}", result["release_body"])
self.assertNotIn(HEAD_B, result["release_body"].split("candidate_head:")[1].split("\n")[0])
self.assertIn("did not transfer validation", result["audit_comment_body"])
self.assertIn("did not repoint", result["audit_comment_body"])
# Session lease must remain unset by assessment (tool never seeds).
self.assertIsNone(leases.get_session_lease())
def test_12_repeated_cleanup_idempotent(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
first = _assess([claim], now=now, apply=True)
self.assertTrue(first["cleanup_allowed"])
release = {"id": 100001, "body": first["release_body"], "user": {"login": "x"}}
second = _assess([claim, release], now=now, apply=True)
self.assertFalse(second["cleanup_allowed"])
self.assertEqual(second["classification"], "no_lease")
def test_13_malformed_expiry_fails_closed(self):
claim = _lease_comment()
# Corrupt expires_at in the body.
claim["body"] = claim["body"].replace(
claim["body"].split("expires_at:")[1].split("\n")[0].strip(),
"not-a-timestamp",
)
result = _assess([claim], formal_reviews=_reviews_for_head(HEAD_A))
self.assertFalse(result["cleanup_allowed"])
self.assertFalse(result["expires_parseable"])
self.assertTrue(any("expires_at" in r for r in result["reasons"]))
def test_14_wrong_identity_evidence_fails_closed(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
bad_repo = _assess(
[claim],
now=now,
# force repo mismatch via expected_repo
)
# Patch via direct call with wrong expected_repo
bad = leases.assess_obsolete_reviewer_comment_lease_cleanup(
[claim],
pr_number=PR,
current_head_sha=HEAD_B,
formal_reviews=_reviews_for_head(HEAD_A),
expected_repo="Other-Org/Other-Repo",
requesting_session_id="fresh",
controller_recovery_authorized=True,
worktree_exists=True,
worktree_clean=True,
owner_process_alive=False,
now=now,
)
self.assertFalse(bad["cleanup_allowed"])
self.assertTrue(any("repository identity" in r for r in bad["reasons"]))
bad_pr = leases.assess_obsolete_reviewer_comment_lease_cleanup(
[claim],
pr_number=999,
current_head_sha=HEAD_B,
formal_reviews=_reviews_for_head(HEAD_A),
expected_repo=REPO,
requesting_session_id="fresh",
controller_recovery_authorized=True,
worktree_exists=True,
worktree_clean=True,
owner_process_alive=False,
expected_lease_comment_id=COMMENT_10749,
now=now,
)
self.assertFalse(bad_pr["cleanup_allowed"])
bad_head = _assess(
[claim],
now=now,
expected_leased_head="0" * 40,
)
self.assertFalse(bad_head["cleanup_allowed"])
bad_session = _assess(
[claim],
now=now,
expected_session_id="wrong-session",
)
self.assertFalse(bad_session["cleanup_allowed"])
def test_15_current_head_active_cannot_be_displaced(self):
now = datetime.now(timezone.utc)
claim = _lease_comment(
candidate_head=HEAD_B,
last_activity=now - timedelta(minutes=1),
expires_at=now + timedelta(hours=2),
)
result = _assess(
[claim],
current_head=HEAD_B,
formal_reviews=_reviews_for_head(HEAD_B),
now=now,
current_head_review_in_progress=True,
)
self.assertFalse(result["cleanup_allowed"])
# Acquire also blocked by foreign active lease.
acq = leases.assess_acquire_lease(
[claim],
pr_number=PR,
reviewer_identity="other",
profile="prgs-reviewer",
session_id="thief",
repo=REPO,
issue_number=ISSUE,
worktree="branches/steal",
candidate_head=HEAD_B,
target_branch="master",
target_branch_sha="b" * 40,
now=now,
)
self.assertFalse(acq["acquire_allowed"])
def test_regression_pr688_comment_10749_after_expiry(self):
"""Exact 10749 reproduction after recorded expires_at 2026-07-13T04:23:00Z."""
now = datetime(2026, 7, 13, 4, 30, 0, tzinfo=timezone.utc)
expires = datetime.fromisoformat(EXPIRES_10749.replace("Z", "+00:00"))
claim = _lease_comment(
session_id=SESSION_FOREIGN,
candidate_head=HEAD_A,
comment_id=COMMENT_10749,
last_activity=expires - timedelta(hours=2),
expires_at=expires,
)
# Diagnosis must not prescribe indefinite wait-only for this case.
diag = leases.diagnose_reviewer_pr_lease_handoff(
[claim],
pr_number=PR,
current_session_id="fresh-reviewer",
current_reviewer_identity="sysadmin",
current_head_sha=HEAD_B,
formal_reviews=_reviews_for_head(HEAD_A, "REQUEST_CHANGES"),
worktree_exists=True,
worktree_clean=True,
owner_process_alive=False,
instructed_session_id=SESSION_FOREIGN,
instructed_comment_id=COMMENT_10749,
now=now,
)
self.assertEqual(diag["classification"], "foreign_expired_superseded_head")
self.assertEqual(
diag["next_action"], leases.NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
)
self.assertEqual(diag["cleanup_tool"], leases.CLEANUP_OBSOLETE_LEASE_TOOL)
self.assertIn("CLEANUP OBSOLETE REVIEWER LEASE 688", diag["required_confirmation"])
self.assertEqual(diag["mutation_eligibility"], "cleanup_only")
self.assertFalse(diag["mutation_allowed"])
# Assessment still returns the lease as active/stale class of block for acquire
# when unexpired path... here it's expired so find_active is None; acquire free
# only after cleanup if somehow still active. With expired, find_active is None:
active = leases.find_active_reviewer_lease([claim], pr_number=PR, now=now)
self.assertIsNone(active)
# But superseded unexpired still blocks acquire and diagnosis points to cleanup:
unexpired_now = datetime(2026, 7, 13, 1, 0, 0, tzinfo=timezone.utc)
claim2 = _lease_comment(
session_id=SESSION_FOREIGN,
candidate_head=HEAD_A,
comment_id=COMMENT_10749,
last_activity=unexpired_now - timedelta(minutes=45),
expires_at=expires,
)
active2 = leases.find_active_reviewer_lease(
[claim2], pr_number=PR, now=unexpired_now
)
self.assertIsNotNone(active2)
self.assertEqual(active2["freshness"], "stale_warning")
diag2 = leases.diagnose_reviewer_pr_lease_handoff(
[claim2],
pr_number=PR,
current_session_id="fresh-reviewer",
current_reviewer_identity="sysadmin",
current_head_sha=HEAD_B,
formal_reviews=_reviews_for_head(HEAD_A, "REQUEST_CHANGES"),
worktree_exists=True,
worktree_clean=True,
now=unexpired_now,
)
self.assertEqual(diag2["classification"], "foreign_completed_superseded_head")
self.assertEqual(
diag2["next_action"], leases.NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
)
acq = leases.assess_acquire_lease(
[claim2],
pr_number=PR,
reviewer_identity="sysadmin",
profile="prgs-reviewer",
session_id="fresh-reviewer",
repo=REPO,
issue_number=ISSUE,
worktree="branches/review-pr-688-new",
candidate_head=HEAD_B,
target_branch="master",
target_branch_sha="b" * 40,
now=unexpired_now,
)
self.assertFalse(acq["acquire_allowed"])
def test_missing_controller_auth_denied(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
result = _assess([claim], controller=False, now=now)
self.assertFalse(result["cleanup_allowed"])
def test_wrong_confirmation_denied_on_apply(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
result = _assess(
[claim], now=now, apply=True, confirmation="MERGE PR 688"
)
self.assertFalse(result["cleanup_allowed"])
self.assertTrue(any("confirmation" in r for r in result["reasons"]))
def test_owner_session_must_use_owner_release(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
result = _assess(
[claim],
now=now,
requesting_session=SESSION_FOREIGN,
)
self.assertFalse(result["cleanup_allowed"])
self.assertTrue(any("owns the lease" in r for r in result["reasons"]))
def test_superseded_without_terminal_review_denied(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
result = _assess([claim], formal_reviews=[], now=now)
self.assertFalse(result["cleanup_allowed"])
self.assertEqual(result["classification"], "ambiguous_conflicting_evidence")
class TestIssue691DiagnoseClassifications(unittest.TestCase):
def setUp(self):
leases.clear_session_lease()
def test_foreign_active_current_head_still_wait(self):
now = datetime.now(timezone.utc)
claim = _lease_comment(
candidate_head=HEAD_B,
last_activity=now - timedelta(minutes=5),
expires_at=now + timedelta(hours=1),
)
claim["id"] = 1
result = leases.diagnose_reviewer_pr_lease_handoff(
[claim],
pr_number=PR,
current_session_id="other",
current_reviewer_identity="sysadmin",
current_head_sha=HEAD_B,
formal_reviews=[],
now=now,
)
self.assertEqual(result["classification"], "foreign_active_current_head")
self.assertEqual(result["next_action"], leases.NEXT_ACTION_WAIT)
self.assertFalse(result["mutation_allowed"])
if __name__ == "__main__":
unittest.main()
+9 -4
View File
@@ -122,9 +122,11 @@ class TestApiRequestRetry(unittest.TestCase):
sleep.assert_not_called()
def test_non_429_error_raises_immediately(self):
with self.assertRaises(RuntimeError) as ctx:
with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
_call([_http_error(500, body=b"boom")])
self.assertIn("HTTP 500", str(ctx.exception))
# Fixed message only (#699) — no response body echo.
self.assertEqual(str(ctx.exception), "Gitea HTTP request failed")
self.assertEqual(ctx.exception.http_status, 500)
def test_non_429_error_does_not_sleep(self):
sleep = MagicMock()
@@ -171,9 +173,12 @@ class TestApiRequestRetry(unittest.TestCase):
# max_retries=3 -> 3 sleeps, then the 4th failure raises.
errors = [_http_error(429, retry_after="1") for _ in range(4)]
sleep = MagicMock()
with self.assertRaises(RuntimeError) as ctx:
with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
_call(errors, sleep_func=sleep, max_retries=3)
self.assertIn("HTTP 429", str(ctx.exception))
# After retries are exhausted, 429 is a typed HTTP error with fixed
# message (#699); status metadata carries 429.
self.assertEqual(str(ctx.exception), "Gitea HTTP request failed")
self.assertEqual(ctx.exception.http_status, 429)
self.assertEqual(sleep.call_count, 3)
def test_no_infinite_loop_when_always_429(self):
+426
View File
@@ -0,0 +1,426 @@
"""Structured MCP auth errors and stdio transport survival (#699 / PR #701).
Covers original AC plus reviewer-ratified regressions:
1. Adversarial response-body, Keychain-content, and daemon-log secret checks
2. Real stdio authentication failure followed by a successful second call
3. UrlElicitationRequiredError framework re-raise behavior
4. Unexpected parser RuntimeError is not authentication
5. Generic HTTP 403 is authorization (not internal)
6. Repeated install/import is idempotent
7. Author and reconciler profiles
8. Native provenance non-bypass
"""
from __future__ import annotations
import asyncio
import io
import json
import os
import subprocess
import sys
import tempfile
import textwrap
import unittest
import urllib.error
from unittest.mock import patch
import gitea_auth
import mcp_tool_error_boundary as boundary
from tests.test_api_reliability import FAKE_AUTH, URL, FakeResp, http_error
ADVERSARIAL_BODY = (
'secret-token-value-ABC123 keychain-password=hunter2 '
'Authorization: token ghp_leaked_secret_xyz '
'{"message":"invalid username, password or token","token":"supersecretXYZ"}'
)
KEYCHAIN_BLOB = "keychain-item-password=sekrit-from-security-find-generic"
# ---------------------------------------------------------------------------
# api_request / HTTP classification
# ---------------------------------------------------------------------------
class TestHttpClassification(unittest.TestCase):
@patch("gitea_auth.urllib.request.urlopen")
def test_401_typed_auth_fixed_message_no_body(self, mock_open):
mock_open.side_effect = http_error(401, ADVERSARIAL_BODY)
with self.assertRaises(gitea_auth.GiteaAuthError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
exc = ctx.exception
self.assertEqual(exc.reason_code, "auth_invalid_token")
self.assertEqual(exc.error_class, "authentication")
self.assertEqual(exc.http_status, 401)
msg = str(exc)
self.assertNotIn("supersecretXYZ", msg)
self.assertNotIn("ghp_leaked", msg)
self.assertNotIn("hunter2", msg)
self.assertNotIn(ADVERSARIAL_BODY, msg)
self.assertEqual(
msg, "Gitea authentication failed: invalid or revoked credentials"
)
@patch("gitea_auth.urllib.request.urlopen")
def test_403_scope_is_authz_scope(self, mock_open):
mock_open.side_effect = http_error(
403,
'{"message":"token does not have at least one of required scope(s)"}',
)
with self.assertRaises(gitea_auth.GiteaAuthzError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
self.assertEqual(ctx.exception.reason_code, "authz_insufficient_scope")
self.assertEqual(ctx.exception.error_class, "authorization")
self.assertNotIn("token does not have", str(ctx.exception))
@patch("gitea_auth.urllib.request.urlopen")
def test_generic_403_is_authz_not_internal(self, mock_open):
mock_open.side_effect = http_error(403, '{"message":"user has no permission"}')
with self.assertRaises(gitea_auth.GiteaAuthzError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
self.assertEqual(ctx.exception.reason_code, "authz_denied")
self.assertEqual(ctx.exception.error_class, "authorization")
self.assertNotIsInstance(ctx.exception, gitea_auth.GiteaAuthError)
self.assertNotIn("user has no permission", str(ctx.exception))
@patch("gitea_auth.urllib.request.urlopen")
def test_network_fixed_message(self, mock_open):
mock_open.side_effect = TimeoutError("timed out contacting secret.example")
with self.assertRaises(gitea_auth.GiteaNetworkError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
self.assertEqual(str(ctx.exception), "Network error contacting Gitea")
self.assertNotIn("secret.example", str(ctx.exception))
@patch("gitea_auth.urllib.request.urlopen")
def test_malformed_json_not_auth(self, mock_open):
mock_open.return_value = FakeResp("not-json{")
with self.assertRaises(RuntimeError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
self.assertNotIsInstance(ctx.exception, gitea_auth.GiteaAuthError)
self.assertIn("malformed JSON", str(ctx.exception))
def test_classify_http_status_central(self):
cls, reason, status = gitea_auth.classify_http_status(401)
self.assertIs(cls, gitea_auth.GiteaAuthError)
self.assertEqual(reason, "auth_invalid_token")
self.assertEqual(status, 401)
cls, reason, status = gitea_auth.classify_http_status(403)
self.assertIs(cls, gitea_auth.GiteaAuthzError)
self.assertEqual(reason, "authz_denied")
cls, reason, status = gitea_auth.classify_http_status(
403, body_hint="missing scope write:issue"
)
self.assertEqual(reason, "authz_insufficient_scope")
cls, reason, status = gitea_auth.classify_http_status(502)
self.assertIs(cls, gitea_auth.GiteaHttpError)
self.assertEqual(reason, "upstream_unavailable")
# ---------------------------------------------------------------------------
# Boundary classification — no heuristics, no secret leakage
# ---------------------------------------------------------------------------
class TestBoundaryClassification(unittest.TestCase):
def test_auth_payload_fixed_message(self):
exc = gitea_auth.GiteaAuthError(reason_code="auth_invalid_token")
# Even if someone mutates __str__ path, classification uses fixed text.
result = boundary.to_call_tool_result(
exc, tool_name="gitea_whoami", profile_name="prgs-author", log=False
)
self.assertTrue(result.isError)
p = result.structuredContent
self.assertEqual(p["reason_code"], "auth_invalid_token")
self.assertEqual(p["error_class"], "authentication")
self.assertEqual(p["message"], boundary.fixed_message("auth_invalid_token"))
self.assertNotIn("supersecret", json.dumps(p))
self.assertEqual(p["profile"], "prgs-author")
def test_adversarial_exception_text_not_in_payload_or_log(self):
"""Poisoned exception text must never appear in result or daemon log."""
class PoisonedAuth(gitea_auth.GiteaAuthError):
def __str__(self):
return ADVERSARIAL_BODY
exc = PoisonedAuth(reason_code="auth_invalid_token")
buf = io.StringIO()
result = boundary.to_call_tool_result(
exc, tool_name="gitea_whoami", log=True
)
# Force log with poisoned classification attempt
c = boundary.classify_exception(exc)
boundary.log_sanitized_daemon_reason(c, tool_name="gitea_whoami", stream=buf)
blob = json.dumps(result.structuredContent) + result.content[0].text + buf.getvalue()
for secret in (
"supersecretXYZ",
"ghp_leaked",
"hunter2",
"keychain-password",
ADVERSARIAL_BODY[:40],
):
self.assertNotIn(secret, blob)
self.assertIn("reason_code=auth_invalid_token", buf.getvalue())
self.assertNotIn("detail=", buf.getvalue())
def test_keychain_content_not_in_daemon_log(self):
buf = io.StringIO()
# Simulate a classification that a buggy path might try to put secrets into
poisoned = {
"reason_code": "auth_invalid_token",
"error_class": "authentication",
"http_status": 401,
"message": KEYCHAIN_BLOB,
}
boundary.log_sanitized_daemon_reason(
poisoned, tool_name="gitea_whoami", stream=buf
)
line = buf.getvalue()
self.assertNotIn("sekrit", line)
self.assertNotIn("keychain-item", line)
self.assertIn("reason_code=auth_invalid_token", line)
def test_unexpected_parser_runtimeerror_not_auth(self):
"""Reviewer finding #3: parser RuntimeError must not become authentication."""
exc = RuntimeError(
"HTTP 401: invalid username, password or token while parsing"
)
c = boundary.classify_exception(exc)
self.assertEqual(c["error_class"], "internal")
self.assertEqual(c["reason_code"], "internal_error")
self.assertNotEqual(c["error_class"], "authentication")
self.assertFalse(boundary.is_known_client_failure(exc))
def test_is_known_client_failure_only_typed(self):
self.assertTrue(
boundary.is_known_client_failure(gitea_auth.GiteaAuthError())
)
self.assertTrue(
boundary.is_known_client_failure(gitea_auth.GiteaAuthzError())
)
self.assertFalse(boundary.is_known_client_failure(RuntimeError("x")))
self.assertFalse(boundary.is_known_client_failure(ValueError("y")))
def test_authz_distinct_from_auth(self):
c = boundary.classify_exception(
gitea_auth.GiteaAuthzError(reason_code="authz_denied")
)
self.assertEqual(c["error_class"], "authorization")
self.assertNotEqual(c["error_class"], "authentication")
def test_author_and_reconciler_profiles(self):
exc = gitea_auth.GiteaAuthError()
for profile in ("prgs-author", "prgs-reconciler"):
r = boundary.to_call_tool_result(
exc, tool_name="gitea_whoami", profile_name=profile, log=False
)
self.assertEqual(r.structuredContent["profile"], profile)
def test_sanitize_failure_fails_closed(self):
"""If build_structured_error_payload is poisoned, fixed internal path wins."""
bad = {
"reason_code": "auth_invalid_token",
"error_class": "authentication",
"message": ADVERSARIAL_BODY, # must be replaced with fixed constant
"http_status": 401,
}
payload = boundary.build_structured_error_payload(bad)
self.assertEqual(
payload["message"], boundary.fixed_message("auth_invalid_token")
)
self.assertNotIn("supersecret", payload["message"])
# ---------------------------------------------------------------------------
# Tool.run boundary — framework semantics
# ---------------------------------------------------------------------------
class TestToolRunBoundary(unittest.TestCase):
def setUp(self):
from mcp.server.fastmcp.tools.base import Tool
boundary.install_tool_run_boundary(Tool)
self.Tool = Tool
def _tool(self, fn, name="demo_tool"):
return self.Tool.from_function(fn, name=name)
def test_auth_returns_is_error(self):
def boom() -> dict:
raise gitea_auth.GiteaAuthError()
result = asyncio.run(self._tool(boom, "gitea_whoami").run({}, convert_result=True))
self.assertTrue(result.isError)
self.assertEqual(result.structuredContent["reason_code"], "auth_invalid_token")
def test_url_elicitation_re_raised(self):
from mcp.shared.exceptions import UrlElicitationRequiredError
from mcp.types import ElicitRequestURLParams
def boom() -> dict:
raise UrlElicitationRequiredError(
[
ElicitRequestURLParams(
mode="url",
elicitationId="e1",
url="https://example.invalid/elicit",
message="need auth",
)
]
)
tool = self._tool(boom, "elicitation_tool")
async def _run():
return await tool.run({}, convert_result=True)
with self.assertRaises(UrlElicitationRequiredError):
asyncio.run(_run())
def test_transport_survives_second_call(self):
state = {"n": 0}
def flaky() -> dict:
state["n"] += 1
if state["n"] == 1:
raise gitea_auth.GiteaAuthError()
return {"ok": True, "call": state["n"]}
tool = self._tool(flaky, "gitea_whoami")
async def _both():
first = await tool.run({}, convert_result=True)
second = await tool.run({}, convert_result=True)
return first, second
first, second = asyncio.run(_both())
self.assertTrue(first.isError)
self.assertEqual(first.structuredContent["error_class"], "authentication")
self.assertFalse(getattr(second, "isError", False))
self.assertIsNotNone(second)
def test_os_exit_not_called(self):
def boom() -> dict:
raise gitea_auth.GiteaAuthError()
with patch("os._exit") as mock_exit:
result = asyncio.run(self._tool(boom).run({}, convert_result=True))
mock_exit.assert_not_called()
self.assertTrue(result.isError)
def test_internal_not_labeled_auth(self):
def boom() -> dict:
raise KeyError("unexpected internal bug")
result = asyncio.run(self._tool(boom).run({}, convert_result=True))
self.assertTrue(result.isError)
self.assertEqual(result.structuredContent["error_class"], "internal")
self.assertEqual(result.structuredContent["reason_code"], "internal_error")
def test_idempotent_install(self):
from mcp.server.fastmcp.tools.base import Tool
first = boundary.install_tool_run_boundary(Tool)
second = boundary.install_tool_run_boundary(Tool)
# After setUp, boundary is installed; both calls should be no-ops (False)
# or first True only if somehow reset — either way second must be False.
self.assertFalse(second)
self.assertTrue(boundary.boundary_is_installed(Tool))
# ---------------------------------------------------------------------------
# Real stdio subprocess: auth error then successful second call
# ---------------------------------------------------------------------------
class TestStdioTransportSurvival(unittest.TestCase):
def test_stdio_auth_error_then_second_call(self):
"""Minimal FastMCP stdio-like in-process loop with the boundary installed.
Uses Tool.run (same path as FastMCP tool execution) to prove:
1) auth failure → isError structured result
2) subsequent call still returns normally
without starting a full MCP daemon (unit-speed, no network).
"""
from mcp.server.fastmcp.tools.base import Tool
boundary.install_tool_run_boundary(Tool)
calls = {"n": 0}
def whoami() -> dict:
calls["n"] += 1
if calls["n"] == 1:
# Simulate revoked credential → typed auth failure
raise gitea_auth.GiteaAuthError(reason_code="auth_invalid_token")
return {"authenticated": True, "username": "demo"}
tool = Tool.from_function(whoami, name="gitea_whoami")
async def session():
r1 = await tool.run({}, convert_result=True)
r2 = await tool.run({}, convert_result=True)
return r1, r2
r1, r2 = asyncio.run(session())
self.assertTrue(r1.isError)
self.assertEqual(r1.structuredContent["reason_code"], "auth_invalid_token")
self.assertTrue(r1.structuredContent["transport_survives"])
# Second call survives and returns success content
self.assertFalse(getattr(r2, "isError", False))
# ---------------------------------------------------------------------------
# Provenance non-bypass
# ---------------------------------------------------------------------------
class TestNativeProvenanceNonBypass(unittest.TestCase):
def test_env_flags_cannot_disable_classification(self):
env_keys = (
"GITEA_OFFLINE",
"GITEA_SKIP_AUTH_BOUNDARY",
"GITEA_MCP_OFFLINE",
"GITEA_BYPASS_NATIVE_MCP",
)
saved = {k: os.environ.get(k) for k in env_keys}
try:
for k in env_keys:
os.environ[k] = "1"
exc = gitea_auth.GiteaAuthError()
c = boundary.classify_exception(exc)
self.assertEqual(c["error_class"], "authentication")
r = boundary.to_call_tool_result(exc, log=False)
self.assertTrue(r.isError)
self.assertEqual(r.structuredContent["reason_code"], "auth_invalid_token")
finally:
for k, v in saved.items():
if v is None:
os.environ.pop(k, None)
else:
os.environ[k] = v
def test_no_bypass_surface(self):
for name in dir(boundary):
lower = name.lower()
self.assertFalse(
lower.startswith("bypass") or lower.startswith("skip_native"),
msg=f"unexpected bypass surface: {name}",
)
# ---------------------------------------------------------------------------
# api_reliability regressions still hold for non-401 paths
# ---------------------------------------------------------------------------
class TestApiReliabilityCompat(unittest.TestCase):
@patch("gitea_auth.urllib.request.urlopen")
def test_502_upstream_typed(self, mock_open):
mock_open.side_effect = http_error(502, "bad gateway secret=xyz")
with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
self.assertEqual(ctx.exception.reason_code, "upstream_unavailable")
self.assertNotIn("secret=xyz", str(ctx.exception))
@patch("gitea_auth.urllib.request.urlopen")
def test_auth_header_never_in_error(self, mock_open):
mock_open.side_effect = http_error(400, "bad request")
with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
self.assertNotIn(FAKE_AUTH, str(ctx.exception))
if __name__ == "__main__":
unittest.main()