Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
a1e5c33bfc |
@@ -55,12 +55,3 @@ GITEA_MCP_PROFILE=prgs
|
||||
# GITEA_MERGER_WORKTREE=/path/to/repo/branches/merge-pr456
|
||||
# GITEA_RECONCILER_WORKTREE=/path/to/repo/branches/reconcile-pr456
|
||||
# GITEA_ACTIVE_WORKTREE=/path/to/repo/branches/session-override
|
||||
|
||||
# Durable HMAC key for irrecoverable decision-lock provenance artifacts (#709 F4).
|
||||
# REQUIRED in production native MCP processes that mint or verify recovery
|
||||
# authorization (reconciler + merger must share the same key). Hex (preferred),
|
||||
# base64, or utf-8 literal (>=16 bytes). Never generate an ephemeral per-process
|
||||
# key — cross-process / post-restart verification would fail closed.
|
||||
# GITEA_IRRECOVERABLE_AUTH_HMAC_KEY=0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef
|
||||
# Optional key version string bound into the signature (for rotation).
|
||||
# GITEA_IRRECOVERABLE_AUTH_HMAC_KEY_VERSION=v1
|
||||
|
||||
@@ -9,37 +9,22 @@ formal reviews then looked identical to native approvals.
|
||||
|
||||
## Rule
|
||||
|
||||
Mutation auth, keychain fill, and controller quarantine require a **production
|
||||
native MCP transport runtime** established only by:
|
||||
|
||||
1. the **resolved absolute path** of the canonical entrypoint
|
||||
(`mcp_server.py` / `gitea_mcp_server.py` next to `mcp_daemon_guard.py`), and
|
||||
2. a live **transport bind** (`bind_native_mcp_transport(transport="stdio")`)
|
||||
immediately before `mcp.run`.
|
||||
|
||||
Basename-only trust (a renamed file called `mcp_server.py`), caller-controlled
|
||||
flags (there is **no** `allow_test_bootstrap`), environment variables, stack
|
||||
frame spoofing, or import-only launch are insufficient.
|
||||
Mutation auth, keychain fill, and controller quarantine require a **native MCP
|
||||
transport runtime** established only by the official entrypoint.
|
||||
|
||||
| Context | Allowed |
|
||||
|---------|---------|
|
||||
| Official IDE-native MCP: resolved canonical entrypoint marks + binds stdio, holds process-local runtime token | yes |
|
||||
| pytest (hermetic unit tests) via `is_pytest_runtime()` | yes for unit gates |
|
||||
| `install_test_native_runtime()` under pytest (test-mode record) | unit-test transport gates only — **never** production Gitea mutations |
|
||||
| `allow_test_bootstrap=True` (removed; must not exist) | **no** |
|
||||
| Renamed runner basename `mcp_server.py` outside package root | **no** |
|
||||
| Import/launch of real entrypoint without transport bind | **no** |
|
||||
| Official MCP entrypoint (`mcp_server.py` / `gitea_mcp_server` `__main__`) calls `mark_sanctioned_daemon()` and holds a process-local runtime token | yes |
|
||||
| pytest (hermetic unit tests) | yes |
|
||||
| `GITEA_MCP_SANCTIONED_DAEMON=1` alone (no process-local native runtime) | **no** (#695) |
|
||||
| `GITEA_ALLOW_DIRECT_MCP_IMPORT=1` in LLM sessions | **no** — never set; never authorizes mutations (#695 AC1 / PR #701) |
|
||||
| Override `GITEA_MCP_SESSION_STATE_DIR` mid-session | **no** — production bind pins state root; redirect cannot forge independent decision locks (#695 AC2 / PR #701) |
|
||||
| `GITEA_ALLOW_DIRECT_MCP_IMPORT=1` in LLM sessions | **no** — never set in agent sessions |
|
||||
| `GITEA_ALLOW_KEYCHAIN_CLI=1` in LLM sessions | **no** — human operator only |
|
||||
| bare `python -c 'import gitea_mcp_server; …'` or offline runners | **no** |
|
||||
| keychain fill outside native/pytest | **no** |
|
||||
|
||||
Native runtime is **process-local**: a random token bound to the daemon PID and
|
||||
transport phase. It is never reconstructed from environment variables,
|
||||
session-state files, caller-controlled flags, or importing internals in a
|
||||
fresh Python process.
|
||||
Native runtime is **process-local**: a random token bound to the daemon PID.
|
||||
It is never reconstructed from environment variables, session-state files, or
|
||||
importing internals in a fresh Python process.
|
||||
|
||||
## Contaminated review quarantine (#695 AC8)
|
||||
|
||||
|
||||
@@ -134,22 +134,16 @@ _TARGET_BRANCH_SHA_RE = re.compile(
|
||||
r"target branch sha\s*:\s*[0-9a-f]{40}",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
# #698: structured proof is rendered in several equivalent shapes —
|
||||
# `workflow_hash: abc...`, `workflow_hash=abc...`, or JSON
|
||||
# `"workflow_hash": "abc..."`. Recognize all of them; demanding one exact
|
||||
# punctuation style rejects legitimate structured workflow-load proof.
|
||||
_WORKFLOW_LOAD_HELPER_RE = re.compile(
|
||||
r"workflow[-_ ]load[-_ ]helper[-_ ]result\s*[:=]",
|
||||
r"workflow[- ]load helper result\s*:",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_WORKFLOW_LOAD_HASH_RE = re.compile(
|
||||
r"workflow[-_ ]load[-_ ]helper[-_ ]result[\s\S]{0,400}?"
|
||||
r"workflow[_ ]hash\"?\s*[:=]\s*\"?[0-9a-f]{12}",
|
||||
r"workflow[- ]load helper result[\s\S]{0,400}?workflow[_ ]hash\s*:\s*[0-9a-f]{12}",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_WORKFLOW_LOAD_BOUNDARY_RE = re.compile(
|
||||
r"workflow[-_ ]load[-_ ]helper[-_ ]result[\s\S]{0,400}?"
|
||||
r"boundary[_ ]status\"?\s*[:=]\s*\"?(?:clean|violation)",
|
||||
r"workflow[- ]load helper result[\s\S]{0,400}?boundary[_ ]status\s*:\s*(?:clean|violation)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_WORKFLOW_FILE_VIEW_NARRATIVE_RE = re.compile(
|
||||
@@ -250,59 +244,6 @@ def _normalize_task_kind(task_kind: str | None) -> str:
|
||||
return _TASK_KIND_ALIASES.get(raw, raw)
|
||||
|
||||
|
||||
def _iter_action_entries(action_log: list | None) -> list[dict]:
|
||||
"""Yield only structured (dict) action-log entries (#698).
|
||||
|
||||
Callers must never crash on malformed entries (strings, numbers, null)
|
||||
that reach the validator from LLM-composed or partially parsed logs;
|
||||
:func:`sanitize_action_log` reports them separately.
|
||||
"""
|
||||
return [e for e in (action_log or []) if isinstance(e, dict)]
|
||||
|
||||
|
||||
def sanitize_action_log(
|
||||
action_log: list | None,
|
||||
) -> tuple[list[dict], list[dict[str, str]]]:
|
||||
"""Split an action log into structured entries and sanitized findings (#698).
|
||||
|
||||
Malformed entries become clear, sanitized ``warning`` findings — the
|
||||
offending value's content is never echoed back (only its position and
|
||||
type), so secrets or garbage in a broken log cannot leak into validation
|
||||
errors, and validation itself proceeds without secondary exceptions.
|
||||
"""
|
||||
if action_log is None:
|
||||
return [], []
|
||||
if not isinstance(action_log, (list, tuple)):
|
||||
return [], [
|
||||
validator_finding(
|
||||
"shared.action_log_malformed",
|
||||
"downgrade",
|
||||
"Action log",
|
||||
"action_log is not a list of structured entries "
|
||||
f"(got {type(action_log).__name__}); it was ignored",
|
||||
"pass action_log as a list of dict entries",
|
||||
)
|
||||
]
|
||||
entries: list[dict] = []
|
||||
findings: list[dict[str, str]] = []
|
||||
for index, entry in enumerate(action_log):
|
||||
if isinstance(entry, dict):
|
||||
entries.append(entry)
|
||||
continue
|
||||
findings.append(
|
||||
validator_finding(
|
||||
"shared.action_log_malformed",
|
||||
"downgrade",
|
||||
"Action log",
|
||||
f"action_log entry {index} is not a structured mapping "
|
||||
f"(got {type(entry).__name__}); the entry was ignored",
|
||||
"repair the malformed action_log entry or drop it before "
|
||||
"revalidating",
|
||||
)
|
||||
)
|
||||
return entries, findings
|
||||
|
||||
|
||||
def validator_finding(
|
||||
rule_id: str,
|
||||
severity: str,
|
||||
@@ -480,7 +421,7 @@ def _rule_shared_canonical_comment_post_claim(
|
||||
rejected_in_report = bool(_CANONICAL_VALIDATION_REJECTED_RE.search(text))
|
||||
rejected_in_log = False
|
||||
if action_log:
|
||||
for entry in _iter_action_entries(action_log):
|
||||
for entry in action_log:
|
||||
validation = entry.get("canonical_comment_validation") or {}
|
||||
if validation.get("allowed") is False:
|
||||
rejected_in_log = True
|
||||
@@ -534,13 +475,9 @@ def _rule_reviewer_vague_mutations_none(
|
||||
action_log: list[dict] | None = None,
|
||||
mutations_observed: bool = False,
|
||||
) -> list[dict[str, str]]:
|
||||
# #698: infer review mutations only from authoritative evidence — an
|
||||
# entry proves a mutation only when it affirmatively records
|
||||
# performed=true and was not gated. Read-only diagnostics and pre-API
|
||||
# rejections (entries without a performed flag) are not mutations.
|
||||
performed = any(
|
||||
e.get("performed") is True and not e.get("gated_rejected")
|
||||
for e in _iter_action_entries(action_log)
|
||||
e.get("performed") is not False and not e.get("gated_rejected")
|
||||
for e in (action_log or [])
|
||||
)
|
||||
if not (mutations_observed or performed):
|
||||
return []
|
||||
@@ -599,7 +536,7 @@ def _rule_reviewer_git_fetch_readonly(
|
||||
text = report_text or ""
|
||||
fetch_observed = any(
|
||||
_GIT_FETCH_RE.search(str(e.get("command") or e.get("action") or ""))
|
||||
for e in _iter_action_entries(action_log)
|
||||
for e in (action_log or [])
|
||||
) or _GIT_FETCH_RE.search(text)
|
||||
if not fetch_observed:
|
||||
return []
|
||||
@@ -1040,7 +977,7 @@ def _rule_reviewer_target_branch_freshness(
|
||||
fields = _handoff_fields(text)
|
||||
fetch_reported = bool(_GIT_FETCH_RE.search(text)) or any(
|
||||
_GIT_FETCH_RE.search(str(e.get("command") or e.get("action") or ""))
|
||||
for e in _iter_action_entries(action_log)
|
||||
for e in (action_log or [])
|
||||
)
|
||||
target_sha_reported = bool(_TARGET_BRANCH_SHA_RE.search(text)) or any(
|
||||
"target branch" in key and "sha" in key and _FULL_SHA_RE.search(value)
|
||||
@@ -1798,12 +1735,6 @@ def assess_final_report_validator(
|
||||
checks: dict[str, Any] = {}
|
||||
findings: list[dict[str, str]] = []
|
||||
|
||||
# #698: malformed action_log data must never crash validation with a
|
||||
# secondary exception; malformed entries surface as sanitized findings.
|
||||
sanitized_action_log, action_log_findings = sanitize_action_log(action_log)
|
||||
action_log = sanitized_action_log
|
||||
findings.extend(action_log_findings)
|
||||
|
||||
if normalized_kind == "issue_filing" and issue_filing_lock is not None:
|
||||
checks["issue_filing"] = assess_issue_filing_final_report(
|
||||
report_text,
|
||||
@@ -1832,23 +1763,7 @@ def assess_final_report_validator(
|
||||
}
|
||||
|
||||
for rule in _RULES_BY_TASK.get(normalized_kind, ()):
|
||||
try:
|
||||
findings.extend(
|
||||
_call_rule(rule, report_text, normalized_kind, rule_kwargs)
|
||||
)
|
||||
except Exception as exc: # #698: fail closed with a sanitized error
|
||||
findings.append(
|
||||
validator_finding(
|
||||
"shared.validator_rule_error",
|
||||
"block",
|
||||
"Validator",
|
||||
f"validator rule '{getattr(rule, '__name__', 'unknown')}' "
|
||||
f"failed with {type(exc).__name__} (details withheld; "
|
||||
"sanitized)",
|
||||
"file a validator defect with the rule name; do not "
|
||||
"bypass final-report validation",
|
||||
)
|
||||
)
|
||||
findings.extend(_call_rule(rule, report_text, normalized_kind, rule_kwargs))
|
||||
|
||||
grade, blocked, downgraded = _aggregate_grade(findings)
|
||||
reasons = [f"{f['rule_id']}: {f['reason']}" for f in findings]
|
||||
|
||||
+31
-1396
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
+34
-339
@@ -6,18 +6,12 @@ Direct ``import gitea_mcp_server`` from a shell bypasses native MCP transport.
|
||||
- Environment variables alone cannot reconstruct a native session
|
||||
(``GITEA_MCP_SANCTIONED_DAEMON=1`` / ``GITEA_ALLOW_DIRECT_MCP_IMPORT=1`` are
|
||||
insufficient for mutation gates).
|
||||
- A process-local runtime record is established only by the resolved canonical
|
||||
entrypoint path (not basename) **and** the actual native MCP transport
|
||||
lifecycle (``bind_native_mcp_transport`` before ``mcp.run``). Merely
|
||||
importing or launching the entrypoint offline does not grant mutation
|
||||
authority.
|
||||
- Public caller-controlled flags (including any former
|
||||
``allow_test_bootstrap``) never establish trusted mutation provenance.
|
||||
- A process-local runtime record is created only by the official entrypoint
|
||||
(``mcp_server.py`` calling ``mark_sanctioned_daemon``), bound to PID and a
|
||||
random secret that never leaves process memory.
|
||||
- Offline scripts that import internals fail closed on mutations.
|
||||
- Pytest remains allowed for hermetic unit tests via ``is_pytest_runtime()``.
|
||||
A separate test-only seam may establish a **test-mode** native record for
|
||||
unit tests of transport gates; that record cannot authorize production
|
||||
Gitea mutation endpoints.
|
||||
- Pytest remains allowed (hermetic tests); optional force flags exist for
|
||||
provenance regression tests.
|
||||
|
||||
Manual deletion of session-state files is never a recovery path.
|
||||
"""
|
||||
@@ -29,7 +23,6 @@ import inspect
|
||||
import os
|
||||
import secrets
|
||||
import time
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
SANCTIONED_DAEMON_ENV = "GITEA_MCP_SANCTIONED_DAEMON"
|
||||
@@ -41,18 +34,6 @@ FORCE_PROVENANCE_FAIL_ENV = "GITEA_TEST_FORCE_UNSANCTIONED"
|
||||
# Process-local native runtime (never persisted, never read from env alone).
|
||||
_NATIVE_RUNTIME: dict[str, Any] | None = None
|
||||
|
||||
# Production transport identifiers accepted by bind_native_mcp_transport.
|
||||
_PRODUCTION_TRANSPORTS = frozenset({"stdio"})
|
||||
_RUNTIME_MODE_PRODUCTION = "production"
|
||||
_RUNTIME_MODE_TEST = "test"
|
||||
_PHASE_ENTRYPOINT_CLAIMED = "entrypoint_claimed"
|
||||
_PHASE_TRANSPORT_BOUND = "transport_bound"
|
||||
|
||||
# Default session-state root (mirrors mcp_session_state; kept local to avoid
|
||||
# import cycles). Used only to pin authority at transport bind (#695 AC2).
|
||||
_DEFAULT_SESSION_STATE_DIR = os.path.expanduser("~/.cache/gitea-tools/session-state")
|
||||
SESSION_STATE_DIR_ENV = "GITEA_MCP_SESSION_STATE_DIR"
|
||||
|
||||
|
||||
class UnsanctionedRuntimeError(RuntimeError):
|
||||
"""Raised when mutation/credential code runs outside a native MCP daemon."""
|
||||
@@ -72,261 +53,52 @@ def is_pytest_runtime() -> bool:
|
||||
return bool((os.environ.get("PYTEST_CURRENT_TEST") or "").strip())
|
||||
|
||||
|
||||
def _package_root() -> Path:
|
||||
"""Directory that contains the canonical MCP entrypoint modules."""
|
||||
return Path(__file__).resolve().parent
|
||||
|
||||
|
||||
def canonical_entrypoint_paths() -> frozenset[str]:
|
||||
"""Resolved absolute paths of official entrypoints (not basenames)."""
|
||||
root = _package_root()
|
||||
return frozenset(
|
||||
{
|
||||
str((root / "mcp_server.py").resolve()),
|
||||
str((root / "gitea_mcp_server.py").resolve()),
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
def _resolve_path(path: str | None) -> str | None:
|
||||
if not path:
|
||||
return None
|
||||
try:
|
||||
return str(Path(path).resolve())
|
||||
except (OSError, RuntimeError, ValueError):
|
||||
return None
|
||||
|
||||
|
||||
def _caller_official_entrypoint_path() -> str | None:
|
||||
"""Return the resolved canonical entrypoint path in the call stack, or None.
|
||||
|
||||
Basename-only matches (e.g. an attacker file named ``mcp_server.py``
|
||||
elsewhere) are rejected. The path must equal one of
|
||||
:func:`canonical_entrypoint_paths`.
|
||||
"""
|
||||
canonical = canonical_entrypoint_paths()
|
||||
for frame in inspect.stack()[1:20]:
|
||||
resolved = _resolve_path(frame.filename)
|
||||
if resolved and resolved in canonical:
|
||||
return resolved
|
||||
return None
|
||||
|
||||
|
||||
def _caller_is_official_entrypoint() -> bool:
|
||||
"""True when invoked from a resolved canonical entrypoint path (#695)."""
|
||||
return _caller_official_entrypoint_path() is not None
|
||||
"""True when mark_sanctioned_daemon is invoked from mcp_server.py."""
|
||||
for frame in inspect.stack()[1:12]:
|
||||
path = (frame.filename or "").replace("\\", "/")
|
||||
base = path.rsplit("/", 1)[-1]
|
||||
if base == "mcp_server.py":
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def _new_runtime_token() -> tuple[str, str]:
|
||||
token = secrets.token_hex(32)
|
||||
fingerprint = hashlib.sha256(token.encode()).hexdigest()[:16]
|
||||
return token, fingerprint
|
||||
def mark_sanctioned_daemon(*, allow_test_bootstrap: bool = False) -> dict[str, Any]:
|
||||
"""Mark this process as the official native MCP daemon (#695).
|
||||
|
||||
|
||||
def mark_sanctioned_daemon() -> dict[str, Any]:
|
||||
"""Claim the official entrypoint for this process (#695).
|
||||
|
||||
This alone does **not** authorize mutations. Callers must subsequently
|
||||
bind the native MCP transport via :func:`bind_native_mcp_transport`.
|
||||
|
||||
Only a stack frame whose **resolved absolute path** is the canonical
|
||||
``mcp_server.py`` or ``gitea_mcp_server.py`` next to this module may
|
||||
claim the entrypoint. Basename spoofing is rejected.
|
||||
|
||||
There is no public ``allow_test_bootstrap`` argument: caller-controlled
|
||||
flags must never establish trusted mutation provenance. Hermetic tests
|
||||
use :func:`install_test_native_runtime` (pytest-only, test mode).
|
||||
Only the official ``mcp_server.py`` entrypoint (or pytest test bootstrap)
|
||||
may establish native transport. Setting env vars alone is insufficient.
|
||||
"""
|
||||
global _NATIVE_RUNTIME
|
||||
if is_pytest_runtime():
|
||||
# Under pytest, production mark is a no-op for transport authority.
|
||||
# Tests that need a native-transport record use install_test_native_runtime.
|
||||
return native_runtime_status()
|
||||
|
||||
entrypoint_path = _caller_official_entrypoint_path()
|
||||
if entrypoint_path is None:
|
||||
raise UnsanctionedRuntimeError(
|
||||
"mark_sanctioned_daemon rejected: not called from the resolved "
|
||||
"canonical MCP entrypoint path (#695). Basename-only names "
|
||||
"(e.g. a renamed runner called mcp_server.py) are insufficient. "
|
||||
"Offline import / standalone scripts cannot reconstruct native "
|
||||
"transport. Stop after native MCP failure; do not run offline "
|
||||
"mutation helpers."
|
||||
)
|
||||
|
||||
token, fingerprint = _new_runtime_token()
|
||||
if not is_pytest_runtime() and not allow_test_bootstrap:
|
||||
if not _caller_is_official_entrypoint():
|
||||
raise UnsanctionedRuntimeError(
|
||||
"mark_sanctioned_daemon rejected: not called from official "
|
||||
"mcp_server.py entrypoint (#695). Offline import / standalone "
|
||||
"scripts cannot reconstruct native transport. Stop after native "
|
||||
"MCP failure; do not run offline mutation helpers."
|
||||
)
|
||||
token = secrets.token_hex(32)
|
||||
_NATIVE_RUNTIME = {
|
||||
"token": token,
|
||||
"token_fingerprint": fingerprint,
|
||||
"token_fingerprint": hashlib.sha256(token.encode()).hexdigest()[:16],
|
||||
"pid": os.getpid(),
|
||||
"started_at": time.time(),
|
||||
"entrypoint": "mcp_server",
|
||||
"entrypoint_path": entrypoint_path,
|
||||
"phase": _PHASE_ENTRYPOINT_CLAIMED,
|
||||
"transport": None,
|
||||
"mode": _RUNTIME_MODE_PRODUCTION,
|
||||
}
|
||||
# Legacy signal for older probes; alone does not authorize mutations.
|
||||
os.environ[SANCTIONED_DAEMON_ENV] = "1"
|
||||
return native_runtime_status()
|
||||
|
||||
|
||||
def bind_native_mcp_transport(*, transport: str) -> dict[str, Any]:
|
||||
"""Bind the live native MCP transport lifecycle (#695).
|
||||
|
||||
Must be called from the resolved canonical entrypoint immediately before
|
||||
the real MCP server transport loop (e.g. ``mcp.run(transport=\"stdio\")``).
|
||||
Requires a prior successful :func:`mark_sanctioned_daemon` claim in this
|
||||
process. Import-only or offline launch without this bind leaves
|
||||
:func:`is_native_mcp_transport` false.
|
||||
"""
|
||||
global _NATIVE_RUNTIME
|
||||
transport_name = (transport or "").strip().lower()
|
||||
if transport_name not in _PRODUCTION_TRANSPORTS:
|
||||
raise UnsanctionedRuntimeError(
|
||||
f"bind_native_mcp_transport rejected: transport {transport!r} is "
|
||||
f"not a production MCP transport (#695). Allowed: "
|
||||
f"{sorted(_PRODUCTION_TRANSPORTS)}."
|
||||
)
|
||||
|
||||
entrypoint_path = _caller_official_entrypoint_path()
|
||||
if entrypoint_path is None:
|
||||
raise UnsanctionedRuntimeError(
|
||||
"bind_native_mcp_transport rejected: not called from the resolved "
|
||||
"canonical MCP entrypoint path (#695)."
|
||||
)
|
||||
|
||||
if _NATIVE_RUNTIME is None or int(_NATIVE_RUNTIME.get("pid") or -1) != os.getpid():
|
||||
raise UnsanctionedRuntimeError(
|
||||
"bind_native_mcp_transport rejected: no entrypoint claim in this "
|
||||
"process (#695). Call mark_sanctioned_daemon() from the official "
|
||||
"entrypoint first."
|
||||
)
|
||||
|
||||
if _NATIVE_RUNTIME.get("mode") != _RUNTIME_MODE_PRODUCTION:
|
||||
raise UnsanctionedRuntimeError(
|
||||
"bind_native_mcp_transport rejected: runtime mode is not "
|
||||
"production (#695)."
|
||||
)
|
||||
|
||||
claimed = (_NATIVE_RUNTIME.get("entrypoint_path") or "").strip()
|
||||
if claimed and claimed != entrypoint_path:
|
||||
raise UnsanctionedRuntimeError(
|
||||
"bind_native_mcp_transport rejected: entrypoint path mismatch "
|
||||
"between mark and bind (#695)."
|
||||
)
|
||||
|
||||
# Pin session-state root for this server lifetime (#695 AC2 / PR #701).
|
||||
# Changing GITEA_MCP_SESSION_STATE_DIR after bind must not manufacture a
|
||||
# second authority domain for decision locks / workflow proofs.
|
||||
raw_state = (os.environ.get(SESSION_STATE_DIR_ENV) or "").strip()
|
||||
if not raw_state:
|
||||
raw_state = _DEFAULT_SESSION_STATE_DIR
|
||||
try:
|
||||
pinned_state = str(Path(raw_state).resolve())
|
||||
except (OSError, RuntimeError, ValueError):
|
||||
pinned_state = raw_state
|
||||
|
||||
_NATIVE_RUNTIME["phase"] = _PHASE_TRANSPORT_BOUND
|
||||
_NATIVE_RUNTIME["transport"] = transport_name
|
||||
_NATIVE_RUNTIME["entrypoint_path"] = entrypoint_path
|
||||
_NATIVE_RUNTIME["bound_at"] = time.time()
|
||||
_NATIVE_RUNTIME["session_state_dir"] = pinned_state
|
||||
os.environ[SANCTIONED_DAEMON_ENV] = "1"
|
||||
return native_runtime_status()
|
||||
|
||||
|
||||
def install_test_native_runtime() -> dict[str, Any]:
|
||||
"""Pytest-only seam for hermetic native-transport unit tests (#695).
|
||||
|
||||
Establishes a **test-mode** process-local record so unit tests can exercise
|
||||
gates that require ``is_native_mcp_transport()``. This record:
|
||||
|
||||
- is rejected outside pytest (including a fresh offline interpreter);
|
||||
- never uses production mode;
|
||||
- cannot authorize production Gitea mutation endpoints
|
||||
(:func:`assert_production_mutation_runtime` / production path of
|
||||
:func:`assert_sanctioned_mutation_runtime` when not under pytest).
|
||||
|
||||
There is no public caller-controlled flag that forges production native
|
||||
transport.
|
||||
"""
|
||||
global _NATIVE_RUNTIME
|
||||
if not is_pytest_runtime():
|
||||
raise UnsanctionedRuntimeError(
|
||||
"install_test_native_runtime rejected: test-mode native runtime "
|
||||
"is only available under pytest (#695). allow_test_bootstrap and "
|
||||
"similar caller-controlled flags do not exist and cannot authorize "
|
||||
"a fresh offline interpreter."
|
||||
)
|
||||
token, fingerprint = _new_runtime_token()
|
||||
_NATIVE_RUNTIME = {
|
||||
"token": token,
|
||||
"token_fingerprint": fingerprint,
|
||||
"pid": os.getpid(),
|
||||
"started_at": time.time(),
|
||||
"entrypoint": "test_bootstrap",
|
||||
"entrypoint_path": None,
|
||||
"phase": _PHASE_TRANSPORT_BOUND,
|
||||
"transport": "test",
|
||||
"mode": _RUNTIME_MODE_TEST,
|
||||
"bound_at": time.time(),
|
||||
}
|
||||
return native_runtime_status()
|
||||
|
||||
|
||||
def clear_native_runtime_for_tests() -> None:
|
||||
"""Test helper: drop native runtime (does not clear env)."""
|
||||
global _NATIVE_RUNTIME
|
||||
_NATIVE_RUNTIME = None
|
||||
|
||||
|
||||
def pinned_session_state_dir() -> str | None:
|
||||
"""Session-state root pinned for this production transport lifetime (#695 AC2).
|
||||
|
||||
When production native transport is bound, durable session proofs must use
|
||||
this directory only. Env overrides of ``GITEA_MCP_SESSION_STATE_DIR`` after
|
||||
bind are ignored so redirected dirs (e.g. ``.mcp_session_701``) cannot
|
||||
manufacture independent decision-lock authority (PR #701 recurrence).
|
||||
"""
|
||||
if not is_production_native_mcp_transport():
|
||||
return None
|
||||
pinned = (_NATIVE_RUNTIME or {}).get("session_state_dir")
|
||||
text = (str(pinned) if pinned is not None else "").strip()
|
||||
return text or None
|
||||
|
||||
|
||||
def direct_import_env_enabled() -> bool:
|
||||
"""True when the legacy direct-import opt-in env is set (never authorizes)."""
|
||||
return (os.environ.get(ALLOW_DIRECT_IMPORT_ENV) or "").strip().lower() in {
|
||||
"1",
|
||||
"true",
|
||||
"yes",
|
||||
}
|
||||
|
||||
|
||||
def assert_no_direct_import_bypass(context: str = "mutation") -> None:
|
||||
"""Fail closed when GITEA_ALLOW_DIRECT_MCP_IMPORT is used for mutations (#695 AC1).
|
||||
|
||||
The env flag is never a sanctioned recovery path for LLM/agent sessions.
|
||||
Under pytest hermetic tests this is a no-op so unit tests can set the flag
|
||||
to prove it does not grant authority.
|
||||
"""
|
||||
if is_pytest_runtime():
|
||||
return
|
||||
if not direct_import_env_enabled():
|
||||
return
|
||||
raise UnsanctionedRuntimeError(
|
||||
f"{ALLOW_DIRECT_IMPORT_ENV} does not authorize {context} (#695 AC1). "
|
||||
"Direct import of gitea_mcp_server mutation tools is forbidden. "
|
||||
"Stop after native MCP failure; reconnect the official MCP daemon. "
|
||||
"Do not set direct-import flags, offline runners, or redirected "
|
||||
f"{SESSION_STATE_DIR_ENV} directories to reconstruct gates."
|
||||
)
|
||||
|
||||
|
||||
def is_native_mcp_transport() -> bool:
|
||||
"""True when this process holds a transport-bound native runtime (#695)."""
|
||||
"""True when this process holds a live native MCP runtime record (#695)."""
|
||||
if (os.environ.get(FORCE_PROVENANCE_FAIL_ENV) or "").strip() in {
|
||||
"1",
|
||||
"true",
|
||||
@@ -339,23 +111,12 @@ def is_native_mcp_transport() -> bool:
|
||||
return False
|
||||
if not (_NATIVE_RUNTIME.get("token") or "").strip():
|
||||
return False
|
||||
if _NATIVE_RUNTIME.get("phase") != _PHASE_TRANSPORT_BOUND:
|
||||
return False
|
||||
if not (_NATIVE_RUNTIME.get("transport") or "").strip():
|
||||
return False
|
||||
return True
|
||||
|
||||
|
||||
def is_production_native_mcp_transport() -> bool:
|
||||
"""True only for production-mode, transport-bound native runtime."""
|
||||
if not is_native_mcp_transport():
|
||||
return False
|
||||
return (_NATIVE_RUNTIME or {}).get("mode") == _RUNTIME_MODE_PRODUCTION
|
||||
|
||||
|
||||
def is_sanctioned_mcp_daemon() -> bool:
|
||||
"""Backward-compatible name; #695 requires native transport, not env alone."""
|
||||
if is_production_native_mcp_transport():
|
||||
if is_native_mcp_transport():
|
||||
return True
|
||||
if is_pytest_runtime():
|
||||
return True
|
||||
@@ -365,45 +126,10 @@ def is_sanctioned_mcp_daemon() -> bool:
|
||||
return False
|
||||
|
||||
|
||||
def assert_production_mutation_runtime(context: str = "mutation") -> None:
|
||||
"""Fail closed unless production native MCP transport is bound (#695).
|
||||
|
||||
Test-mode bootstrap records and pytest-only hermetic allowances do **not**
|
||||
satisfy this gate. Use for production Gitea mutation endpoints that must
|
||||
never be reachable via test bootstrap.
|
||||
"""
|
||||
if is_production_native_mcp_transport():
|
||||
return
|
||||
mode = (_NATIVE_RUNTIME or {}).get("mode")
|
||||
if mode == _RUNTIME_MODE_TEST:
|
||||
raise UnsanctionedRuntimeError(
|
||||
f"Test-mode native runtime cannot authorize production {context} "
|
||||
"(#695). install_test_native_runtime / former allow_test_bootstrap "
|
||||
"must never reach real Gitea mutation endpoints."
|
||||
)
|
||||
assert_sanctioned_mutation_runtime(context)
|
||||
|
||||
|
||||
def assert_sanctioned_mutation_runtime(context: str = "mutation") -> None:
|
||||
"""Fail closed when mutation code runs outside native MCP transport (#695).
|
||||
|
||||
Under pytest, hermetic unit tests are allowed (profile/permission tests).
|
||||
Outside pytest, requires production-mode transport-bound native runtime.
|
||||
Test-mode records do not authorize non-pytest production mutations.
|
||||
``GITEA_ALLOW_DIRECT_MCP_IMPORT`` never authorizes mutations (#695 AC1).
|
||||
"""
|
||||
if is_pytest_runtime():
|
||||
"""Fail closed when mutation code runs outside native MCP transport (#695)."""
|
||||
if is_sanctioned_mcp_daemon():
|
||||
return
|
||||
# AC1: direct-import env is never a mutation recovery path (PR #701).
|
||||
assert_no_direct_import_bypass(context)
|
||||
if is_production_native_mcp_transport():
|
||||
return
|
||||
mode = (_NATIVE_RUNTIME or {}).get("mode")
|
||||
if mode == _RUNTIME_MODE_TEST:
|
||||
raise UnsanctionedRuntimeError(
|
||||
f"Test-mode native runtime cannot authorize production {context} "
|
||||
"(#695). Test bootstrap cannot reach production mutation endpoints."
|
||||
)
|
||||
env_spoof = (os.environ.get(SANCTIONED_DAEMON_ENV) or "").strip() in {
|
||||
"1",
|
||||
"true",
|
||||
@@ -413,26 +139,14 @@ def assert_sanctioned_mutation_runtime(context: str = "mutation") -> None:
|
||||
if env_spoof:
|
||||
extra = (
|
||||
f" Note: {SANCTIONED_DAEMON_ENV} alone is not sufficient (#695); "
|
||||
"native transport requires the official MCP entrypoint and a live "
|
||||
"transport bind."
|
||||
)
|
||||
phase = (_NATIVE_RUNTIME or {}).get("phase")
|
||||
if phase == _PHASE_ENTRYPOINT_CLAIMED:
|
||||
extra = (
|
||||
(extra + " ") if extra else " "
|
||||
) + (
|
||||
"Entrypoint was claimed but native MCP transport was never bound "
|
||||
"(#695); offline launch/import of the real entrypoint does not "
|
||||
"grant mutation authority."
|
||||
"native transport requires the official MCP entrypoint."
|
||||
)
|
||||
raise UnsanctionedRuntimeError(
|
||||
f"Unsanctioned / non-native runtime blocked {context} (#695). "
|
||||
"Do not import gitea_mcp_server or call mutation helpers from a raw "
|
||||
"shell, offline runner, or ad-hoc script after native MCP failure. "
|
||||
"Stop and reconnect the official MCP daemon (mcp_server.py) over "
|
||||
"native transport. "
|
||||
f"Do not set {ALLOW_DIRECT_IMPORT_ENV}, override "
|
||||
f"{SESSION_STATE_DIR_ENV}, or use raw token env vars in LLM "
|
||||
"Stop and reconnect the official MCP daemon (mcp_server.py). "
|
||||
f"Do not set {ALLOW_DIRECT_IMPORT_ENV} or raw token env vars in LLM "
|
||||
f"sessions.{extra}"
|
||||
)
|
||||
|
||||
@@ -467,23 +181,14 @@ def native_runtime_status() -> dict[str, Any]:
|
||||
rt = _NATIVE_RUNTIME or {}
|
||||
return {
|
||||
"native_mcp_transport": is_native_mcp_transport(),
|
||||
"production_native_mcp_transport": is_production_native_mcp_transport(),
|
||||
"pytest": is_pytest_runtime(),
|
||||
"pid": rt.get("pid"),
|
||||
"token_fingerprint": rt.get("token_fingerprint"),
|
||||
"started_at": rt.get("started_at"),
|
||||
"entrypoint": rt.get("entrypoint"),
|
||||
"entrypoint_path": rt.get("entrypoint_path"),
|
||||
"phase": rt.get("phase"),
|
||||
"transport": rt.get("transport"),
|
||||
"mode": rt.get("mode"),
|
||||
"session_state_dir": pinned_session_state_dir() or rt.get("session_state_dir"),
|
||||
"session_state_dir_pinned": pinned_session_state_dir() is not None,
|
||||
"direct_import_env_set": direct_import_env_enabled(),
|
||||
"env_sanctioned_alone_insufficient": True,
|
||||
"sanctioned_env": SANCTIONED_DAEMON_ENV,
|
||||
"allow_direct_import_env": ALLOW_DIRECT_IMPORT_ENV,
|
||||
"session_state_dir_env": SESSION_STATE_DIR_ENV,
|
||||
"allow_keychain_cli_env": ALLOW_KEYCHAIN_CLI_ENV,
|
||||
}
|
||||
|
||||
@@ -498,20 +203,10 @@ def runtime_status() -> dict[str, Any]:
|
||||
def mutation_provenance_fields() -> dict[str, Any]:
|
||||
"""Fields to attach to live mutation / review audit records (#695 AC6)."""
|
||||
st = native_runtime_status()
|
||||
transport = "native_mcp" if st["native_mcp_transport"] else "untrusted"
|
||||
if st.get("mode") == _RUNTIME_MODE_TEST and st["native_mcp_transport"]:
|
||||
transport = "test_native_mcp"
|
||||
return {
|
||||
"transport": transport,
|
||||
"transport": "native_mcp" if st["native_mcp_transport"] else "untrusted",
|
||||
"native_mcp_transport": bool(st["native_mcp_transport"]),
|
||||
"production_native_mcp_transport": bool(
|
||||
st.get("production_native_mcp_transport")
|
||||
),
|
||||
"native_runtime_pid": st.get("pid"),
|
||||
"native_token_fingerprint": st.get("token_fingerprint"),
|
||||
"entrypoint": st.get("entrypoint"),
|
||||
"phase": st.get("phase"),
|
||||
"mode": st.get("mode"),
|
||||
"session_state_dir": st.get("session_state_dir"),
|
||||
"session_state_dir_pinned": bool(st.get("session_state_dir_pinned")),
|
||||
}
|
||||
|
||||
+3
-5
@@ -41,17 +41,15 @@ def check_conflict_markers():
|
||||
|
||||
check_conflict_markers()
|
||||
|
||||
# #558 / #695: claim the official entrypoint before loading mutation modules.
|
||||
# This alone does NOT authorize mutations — gitea_mcp_server binds the live
|
||||
# native MCP transport (stdio) immediately before mcp.run. Import-only or
|
||||
# offline launch without that bind fails closed on mutations.
|
||||
# #558: official entrypoint marks the process as the sanctioned MCP daemon
|
||||
# before loading mutation modules (blocks raw shell import bypasses).
|
||||
try:
|
||||
import mcp_daemon_guard
|
||||
|
||||
mcp_daemon_guard.mark_sanctioned_daemon()
|
||||
except Exception:
|
||||
# Guard import failures must not hide conflict-marker infra_stop above;
|
||||
# gitea_mcp_server main also marks + binds when run as __main__.
|
||||
# gitea_mcp_server main also marks sanctioned when run as __main__.
|
||||
pass
|
||||
|
||||
# Execute the actual server logic via exec in this namespace.
|
||||
|
||||
+1
-246
@@ -36,24 +36,7 @@ KIND_REVIEW_DRAFT = "review_draft"
|
||||
# other session proofs; a contaminated session fails closed on gated mutations
|
||||
# until a reconciler audits and clears it.
|
||||
KIND_STABLE_BRANCH_CONTAMINATION = "stable_branch_contamination"
|
||||
# #709: archive prior terminal decision ledgers instead of silent overwrite.
|
||||
KIND_DECISION_LOCK_ARCHIVE = "review_decision_lock_archive"
|
||||
# #709: post-merge cleanup/audit reconciliation-required durable record.
|
||||
KIND_POST_MERGE_DECISION_RECOVERY = "post_merge_decision_recovery"
|
||||
# #709: truthful record when historical terminal evidence is irrecoverably gone.
|
||||
KIND_IRRECOVERABLE_DECISION_PROVENANCE = "irrecoverable_decision_provenance"
|
||||
# #709 F1: server-side non-forgeable authorization artifact for recovery.
|
||||
KIND_IRRECOVERABLE_PROVENANCE_AUTH = "irrecoverable_provenance_authorization"
|
||||
|
||||
# Kinds that must survive the default session-state TTL (forensic / recovery).
|
||||
RECOVERY_CRITICAL_KINDS = frozenset(
|
||||
{
|
||||
KIND_DECISION_LOCK_ARCHIVE,
|
||||
KIND_POST_MERGE_DECISION_RECOVERY,
|
||||
KIND_IRRECOVERABLE_DECISION_PROVENANCE,
|
||||
KIND_IRRECOVERABLE_PROVENANCE_AUTH,
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
_SAFE_SEGMENT_RE = re.compile(r"[^A-Za-z0-9._+-]+")
|
||||
@@ -61,34 +44,6 @@ SESSION_PROFILE_LOCK_ENV = "GITEA_SESSION_PROFILE_LOCK"
|
||||
|
||||
|
||||
def default_state_dir() -> str:
|
||||
"""Resolve the durable session-state root.
|
||||
|
||||
When production native MCP transport is bound (#695 AC2), the directory
|
||||
pinned at transport bind is authoritative: later overrides of
|
||||
``GITEA_MCP_SESSION_STATE_DIR`` cannot manufacture a second authority
|
||||
domain (PR #701 recurrence: ``.mcp_session_701`` evasion of cross-PR
|
||||
decision locks).
|
||||
"""
|
||||
try:
|
||||
import mcp_daemon_guard
|
||||
|
||||
pinned = mcp_daemon_guard.pinned_session_state_dir()
|
||||
if pinned:
|
||||
return pinned
|
||||
except Exception:
|
||||
# Fail open to env/default only when guard is unavailable (e.g. partial
|
||||
# import during bootstrap). Mutation gates still fail closed separately.
|
||||
pass
|
||||
raw = (os.environ.get(STATE_DIR_ENV) or DEFAULT_STATE_DIR).strip()
|
||||
return raw or DEFAULT_STATE_DIR
|
||||
|
||||
|
||||
def env_session_state_dir_unpinned() -> str:
|
||||
"""Raw env/default session-state dir ignoring production transport pin.
|
||||
|
||||
Intended for diagnostics and tests that assert pin behavior — not for
|
||||
mutation-sensitive durable proofs under a bound native daemon.
|
||||
"""
|
||||
raw = (os.environ.get(STATE_DIR_ENV) or DEFAULT_STATE_DIR).strip()
|
||||
return raw or DEFAULT_STATE_DIR
|
||||
|
||||
@@ -287,11 +242,7 @@ def identity_match_reasons(
|
||||
reasons.append("session state missing recorded_at timestamp (fail closed)")
|
||||
else:
|
||||
age = _now_utc() - recorded_at
|
||||
kind = (record.get("kind") or "").strip()
|
||||
ttl_exempt = kind in RECOVERY_CRITICAL_KINDS or bool(
|
||||
record.get("recovery_critical")
|
||||
)
|
||||
if age > timedelta(hours=ttl_hours()) and not ttl_exempt:
|
||||
if age > timedelta(hours=ttl_hours()):
|
||||
reasons.append(
|
||||
f"session state expired after {ttl_hours():g}h (fail closed)"
|
||||
)
|
||||
@@ -411,26 +362,6 @@ def save_state(
|
||||
body["org"] = key_org
|
||||
if key_repo is not None:
|
||||
body["repo"] = key_repo
|
||||
# Stamp session-state authority used for this write (#695 AC2 / AC6).
|
||||
body.setdefault("session_state_dir", root)
|
||||
try:
|
||||
import mcp_daemon_guard
|
||||
|
||||
prov = mcp_daemon_guard.mutation_provenance_fields()
|
||||
body.setdefault(
|
||||
"native_token_fingerprint", prov.get("native_token_fingerprint")
|
||||
)
|
||||
body.setdefault(
|
||||
"native_mcp_transport", bool(prov.get("native_mcp_transport"))
|
||||
)
|
||||
body.setdefault(
|
||||
"production_native_mcp_transport",
|
||||
bool(prov.get("production_native_mcp_transport")),
|
||||
)
|
||||
body.setdefault("transport", prov.get("transport"))
|
||||
except Exception:
|
||||
body.setdefault("native_mcp_transport", False)
|
||||
body.setdefault("transport", "untrusted")
|
||||
|
||||
envelope = {
|
||||
"kind": kind,
|
||||
@@ -442,8 +373,6 @@ def save_state(
|
||||
"recorded_at": body["recorded_at"],
|
||||
"updated_at": body["updated_at"],
|
||||
"writer_pid": body["writer_pid"],
|
||||
"session_state_dir": body.get("session_state_dir"),
|
||||
"transport": body.get("transport"),
|
||||
"payload": body,
|
||||
}
|
||||
_write_json(path, envelope)
|
||||
@@ -468,177 +397,3 @@ def clear_state(
|
||||
profile_identity=profile_identity,
|
||||
state_dir=state_dir,
|
||||
)
|
||||
|
||||
def list_decision_lock_profile_identities(
|
||||
state_dir: str | None = None,
|
||||
) -> list[str]:
|
||||
"""Return profile identities that have a durable review_decision_lock file (#709).
|
||||
|
||||
Filename form: ``review_decision_lock-<profile>.json`` (see ``state_key``).
|
||||
Does not validate TTL or identity — callers must load via ``load_state``.
|
||||
"""
|
||||
root = (state_dir or default_state_dir()).strip()
|
||||
if not root or not os.path.isdir(root):
|
||||
return []
|
||||
prefix = f"{_sanitize_segment(KIND_DECISION_LOCK)}-"
|
||||
suffix = ".json"
|
||||
found: list[str] = []
|
||||
try:
|
||||
names = os.listdir(root)
|
||||
except OSError:
|
||||
return []
|
||||
for name in names:
|
||||
if not name.startswith(prefix) or not name.endswith(suffix):
|
||||
continue
|
||||
if name.endswith(".lock"):
|
||||
continue
|
||||
mid = name[len(prefix) : -len(suffix)]
|
||||
if mid:
|
||||
found.append(mid)
|
||||
return sorted(set(found))
|
||||
|
||||
|
||||
def load_state_for_profile(
|
||||
*,
|
||||
kind: str,
|
||||
profile_identity: str,
|
||||
remote: str | None = None,
|
||||
org: str | None = None,
|
||||
repo: str | None = None,
|
||||
state_dir: str | None = None,
|
||||
skip_identity_match: bool = False,
|
||||
enforce_repo_scope: bool = True,
|
||||
) -> dict[str, Any] | None:
|
||||
"""Load durable state for an explicit profile identity (#709 cross-profile).
|
||||
|
||||
When *skip_identity_match* is True, still requires the file's recorded
|
||||
profile_identity to equal the requested profile (anti-stomp), but does not
|
||||
require the *active* session identity to match — needed so a merger can
|
||||
inspect a reviewer lock after merge.
|
||||
|
||||
#709 F3: remote/org/repo filter reasons are **enforced** (not merely
|
||||
computed). When *enforce_repo_scope* is True (default) and the caller
|
||||
supplies remote/org/repo, mismatches fail closed with ``None``.
|
||||
"""
|
||||
# #709 F3: refuse traversal / malformed profile identities.
|
||||
try:
|
||||
from irrecoverable_provenance import assess_profile_path_identity
|
||||
|
||||
path_gate = assess_profile_path_identity(profile_identity)
|
||||
if not path_gate.get("valid"):
|
||||
return None
|
||||
except Exception:
|
||||
# Module may be mid-import in edge bootstraps; fall through to
|
||||
# conservative checks below.
|
||||
raw = str(profile_identity or "")
|
||||
if ".." in raw or "/" in raw or "\\" in raw or "\x00" in raw:
|
||||
return None
|
||||
|
||||
profile = current_profile_identity(profile_identity=profile_identity)
|
||||
root = _ensure_state_dir(state_dir)
|
||||
# Refuse symlink escape of the state root (#709 F3).
|
||||
try:
|
||||
real_root = os.path.realpath(root)
|
||||
path = state_file_path(
|
||||
kind=kind,
|
||||
remote=remote,
|
||||
org=org,
|
||||
repo=repo,
|
||||
profile_identity=profile,
|
||||
state_dir=root,
|
||||
)
|
||||
real_path = os.path.realpath(path) if os.path.exists(path) else path
|
||||
if os.path.exists(path) and not str(real_path).startswith(
|
||||
str(real_root) + os.sep
|
||||
) and str(real_path) != str(real_root):
|
||||
return None
|
||||
except OSError:
|
||||
return None
|
||||
|
||||
path = state_file_path(
|
||||
kind=kind,
|
||||
remote=remote,
|
||||
org=org,
|
||||
repo=repo,
|
||||
profile_identity=profile,
|
||||
state_dir=root,
|
||||
)
|
||||
lock_path = f"{path}.lock"
|
||||
with _exclusive_file_lock(lock_path):
|
||||
envelope = _read_json(path)
|
||||
if not envelope:
|
||||
return None
|
||||
payload = envelope.get("payload")
|
||||
if not isinstance(payload, dict):
|
||||
return None
|
||||
merged = dict(payload)
|
||||
for key in (
|
||||
"kind",
|
||||
"remote",
|
||||
"org",
|
||||
"repo",
|
||||
"profile_identity",
|
||||
"session_profile_lock",
|
||||
"recorded_at",
|
||||
"updated_at",
|
||||
"writer_pid",
|
||||
):
|
||||
if key in envelope and key not in merged:
|
||||
merged[key] = envelope[key]
|
||||
stored = (merged.get("profile_identity") or "").strip()
|
||||
if stored and stored != profile:
|
||||
return None
|
||||
if skip_identity_match:
|
||||
# Enforce remote/org/repo when caller provides them (#709 F3).
|
||||
# Drop only *active session* profile-identity mismatches; keep
|
||||
# expiry, spoof, and repository-scope reasons.
|
||||
scope_remote = remote if enforce_repo_scope else None
|
||||
scope_org = org if enforce_repo_scope else None
|
||||
scope_repo = repo if enforce_repo_scope else None
|
||||
reasons = identity_match_reasons(
|
||||
merged,
|
||||
remote=scope_remote,
|
||||
org=scope_org,
|
||||
repo=scope_repo,
|
||||
profile_identity=stored or profile,
|
||||
)
|
||||
filtered = [
|
||||
r
|
||||
for r in reasons
|
||||
if "profile identity mismatch" not in r
|
||||
or (stored and stored != profile)
|
||||
]
|
||||
# When caller requested a specific remote/org/repo, also fail if the
|
||||
# stored record lacks those identity fields entirely (legacy incomplete).
|
||||
if enforce_repo_scope:
|
||||
for field, want in (
|
||||
("remote", remote),
|
||||
("org", org),
|
||||
("repo", repo),
|
||||
):
|
||||
want_s = (want or "").strip()
|
||||
if not want_s:
|
||||
continue
|
||||
have = (str(merged.get(field) or "")).strip()
|
||||
if not have:
|
||||
filtered.append(
|
||||
f"session state {field} missing on durable record "
|
||||
f"(expected={want_s!r}; fail closed, #709 F3)"
|
||||
)
|
||||
elif have != want_s:
|
||||
# identity_match_reasons already adds mismatch; ensure kept
|
||||
pass
|
||||
if filtered:
|
||||
return None
|
||||
return merged
|
||||
reasons = identity_match_reasons(
|
||||
merged,
|
||||
remote=remote,
|
||||
org=org,
|
||||
repo=repo,
|
||||
profile_identity=profile,
|
||||
)
|
||||
if reasons:
|
||||
return None
|
||||
return merged
|
||||
|
||||
|
||||
@@ -86,22 +86,6 @@ _WRONG_BRANCH_RE = re.compile(
|
||||
r"deleted branch (?:does not match|!=|differs from) (?:merged )?pr head",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
# #698: canonical reviewer lease lifecycle operations are NOT post-merge
|
||||
# cleanup. Releasing a reviewer PR lease (or posting its terminal
|
||||
# phase=released marker) happens after every review — merged or not — and
|
||||
# must never trigger the post-merge branch/worktree cleanup checklist.
|
||||
_LEASE_LIFECYCLE_RE = re.compile(
|
||||
r"(?:gitea_release_reviewer_pr_lease|gitea_abandon_workflow_lease|"
|
||||
r"release[d]? (?:the )?(?:reviewer|workflow) (?:pr )?lease|"
|
||||
r"reviewer (?:pr )?lease release[d]?|"
|
||||
r"lease (?:marker|comment).{0,40}phase\s*[:=]\s*released|"
|
||||
r"phase\s*[:=]\s*released)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_CLEANUP_MUTATIONS_VALUE_RE = re.compile(
|
||||
r"cleanup mutations\s*:\s*([^\n]+)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
|
||||
def _claims_remote_delete(text: str) -> bool:
|
||||
@@ -220,19 +204,16 @@ def assess_post_merge_cleanup_proof(
|
||||
for field in _worktree_cleanup_fields_present(text)
|
||||
)
|
||||
|
||||
if (remote_delete or worktree_remove) and not (remote_delete or worktree_remove):
|
||||
pass
|
||||
|
||||
if not remote_delete and not worktree_remove:
|
||||
value_match = _CLEANUP_MUTATIONS_VALUE_RE.search(text)
|
||||
value = (value_match.group(1).strip() if value_match else "")
|
||||
value_lower = value.lower()
|
||||
substantive = bool(value) and value_lower not in {
|
||||
"none", "n/a", "not applicable",
|
||||
}
|
||||
# #698: reviewer lease release / terminal lease markers are lease
|
||||
# lifecycle, not post-merge cleanup — no checklist owed.
|
||||
lease_lifecycle_only = substantive and bool(
|
||||
_LEASE_LIFECYCLE_RE.search(value)
|
||||
cleanup_mutations = re.search(
|
||||
r"cleanup mutations\s*:\s*(?!none\b)\S",
|
||||
text,
|
||||
re.IGNORECASE,
|
||||
)
|
||||
if substantive and not lease_lifecycle_only:
|
||||
if cleanup_mutations:
|
||||
reasons.append(
|
||||
"cleanup mutations reported without post-merge cleanup proof checklist"
|
||||
)
|
||||
|
||||
+6
-67
@@ -403,37 +403,10 @@ _REVIEWER_ACTIVE_RE = re.compile(
|
||||
r"whether any reviewer was active\s*:\s*(yes|no|true|false)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
# #698 phase detection for phase-specific head proofs.
|
||||
_NO_REVIEWED_HEAD_RE = re.compile(
|
||||
r"(?:reviewed head sha|candidate head sha)\s*:\s*none\b",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_VERDICT_RECORDED_RE = re.compile(
|
||||
r"review decision\s*:\s*(?:approve[d]?|request[_ ]changes)\b"
|
||||
r"|review_status\s*:\s*(?:approved|request_changes)\b"
|
||||
r"|terminal review mutation\s*:\s*(?!none\b)\S",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_MERGE_ATTEMPTED_RE = re.compile(
|
||||
r"merge result\s*:\s*(?:merged|success|performed|failed|attempted)\b"
|
||||
r"|merge mutations\s*:\s*(?!none\b|not applicable\b)\S",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_VALIDATION_STARTED_RE = re.compile(
|
||||
r"validation\s*:\s*(?!none\b|not run\b|not applicable\b|not started\b)"
|
||||
r"[^\n]*(?:pass|fail|ran|executed|\d+\s+passed)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
|
||||
def assess_reviewer_stale_head_final_report(report_text: str) -> dict[str, Any]:
|
||||
"""Final-report proof for reviewed vs live head SHAs (#399 AC 6).
|
||||
|
||||
#698: head proofs are phase-specific. A legitimately blocked run that
|
||||
never began validation (no reviewed head, no formal verdict, no merge)
|
||||
owes none of them; approval-time and merge-time live-head proofs are
|
||||
owed only once the corresponding phase actually begins.
|
||||
"""
|
||||
"""Final-report proof for reviewed vs live head SHAs (#399 AC 6)."""
|
||||
text = report_text or ""
|
||||
reasons: list[str] = []
|
||||
reviewed = _normalize_sha(_REVIEWED_HEAD_RE.search(text).group(1) if _REVIEWED_HEAD_RE.search(text) else None)
|
||||
@@ -449,49 +422,15 @@ def assess_reviewer_stale_head_final_report(report_text: str) -> dict[str, Any]:
|
||||
)
|
||||
push_during = _PUSH_DURING_VALIDATION_RE.search(text)
|
||||
|
||||
# Phase detection from the report's own claims.
|
||||
no_head_stated = bool(_NO_REVIEWED_HEAD_RE.search(text))
|
||||
verdict_recorded = bool(_VERDICT_RECORDED_RE.search(text))
|
||||
merge_attempted = bool(_MERGE_ATTEMPTED_RE.search(text))
|
||||
validation_started = bool(reviewed) or bool(_VALIDATION_STARTED_RE.search(text))
|
||||
blocked_before_validation = (
|
||||
no_head_stated
|
||||
and not reviewed
|
||||
and not verdict_recorded
|
||||
and not merge_attempted
|
||||
and not validation_started
|
||||
)
|
||||
|
||||
if blocked_before_validation:
|
||||
return {
|
||||
"proven": True,
|
||||
"block": False,
|
||||
"reasons": [],
|
||||
"reviewed_head_sha": None,
|
||||
"live_head_sha_before_approval": None,
|
||||
"live_head_sha_before_merge": None,
|
||||
"push_during_validation": (
|
||||
push_during.group(1).lower() if push_during else None
|
||||
),
|
||||
"phase": "blocked_before_validation",
|
||||
}
|
||||
|
||||
if not reviewed and not no_head_stated:
|
||||
# The head must always be STATED — either a SHA or an explicit
|
||||
# 'none'. Silence is not a phase claim and fails closed.
|
||||
reasons.append(
|
||||
"reviewed head SHA not stated in final report "
|
||||
"(state the SHA or an explicit 'none')"
|
||||
)
|
||||
elif not reviewed and (validation_started or verdict_recorded or merge_attempted):
|
||||
if not reviewed:
|
||||
reasons.append("reviewed head SHA not stated in final report")
|
||||
if verdict_recorded and not live_approval:
|
||||
if not live_approval:
|
||||
reasons.append("final live head SHA before approval not stated")
|
||||
if merge_attempted and not live_merge:
|
||||
if not live_merge:
|
||||
reasons.append("final live head SHA before merge not stated")
|
||||
if validation_started and not push_during:
|
||||
if not push_during:
|
||||
reasons.append("whether push occurred during validation not stated")
|
||||
if reviewed and live_approval and reviewed != live_approval:
|
||||
elif reviewed and live_approval and reviewed != live_approval:
|
||||
reasons.append("live head before approval differs from reviewed head SHA")
|
||||
elif reviewed and live_merge and reviewed != live_merge:
|
||||
reasons.append("live head before merge differs from reviewed head SHA")
|
||||
|
||||
@@ -25,13 +25,8 @@ _REVIEWED_HEAD_RE = re.compile(
|
||||
r"(?:pinned reviewed head|reviewed head sha)\s*:\s*([0-9a-f]{7,40})",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
# #698: validation pass proof appears in several legitimate shapes —
|
||||
# "Validation: pass", "Validation: focused 50 passed; full 2665 passed",
|
||||
# or structured "validation_status: pass". Accept pass evidence anywhere in
|
||||
# the Validation field's value, not only as its first token.
|
||||
_VALIDATION_PASS_RE = re.compile(
|
||||
r"validation(?:_status)?\s*:[^\n]{0,300}?"
|
||||
r"(?:\bpass(?:ed)?\b|\bstrong\b|\bok\b|\bgreen\b|\d+\s+passed)",
|
||||
r"validation\s*:\s*(?:pass|passed|strong|ok|green)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_MERGED_CLAIM_RE = re.compile(
|
||||
|
||||
+9
-36
@@ -858,16 +858,9 @@ _WALKTHROUGH_ARTIFACT_RE = re.compile(r"walkthrough\.md", re.I)
|
||||
|
||||
|
||||
def _performed_file_mutations(action_log: list[dict] | None) -> list[dict]:
|
||||
"""Return performed local file mutations, excluding gated rejections.
|
||||
|
||||
Non-dict entries (malformed JSON, LLM mistakes) are ignored instead of
|
||||
raising ``AttributeError`` (#698): a malformed ledger entry can never be
|
||||
authoritative mutation evidence.
|
||||
"""
|
||||
"""Return performed local file mutations, excluding gated rejections."""
|
||||
performed: list[dict] = []
|
||||
for entry in action_log or []:
|
||||
if not isinstance(entry, dict):
|
||||
continue
|
||||
if entry.get("gated_rejected") or entry.get("performed") is False:
|
||||
continue
|
||||
action = (entry.get("action") or "").strip().lower()
|
||||
@@ -2235,31 +2228,24 @@ HANDOFF_REVIEW_MUTATION_FIELDS = (
|
||||
)
|
||||
|
||||
HANDOFF_ROLE_FIELDS = {
|
||||
# #698: the review/merger required-field sets must stay aligned with the
|
||||
# canonical schema (skills/llm-project-workflow/schemas/
|
||||
# review-merge-final-report.md). The schema explicitly FORBIDS the legacy
|
||||
# fields 'Pinned reviewed head', 'Scratch worktree used', and 'Workspace
|
||||
# mutations' — a validator must never demand a field the schema bans.
|
||||
"review": (
|
||||
("Selected PR", ("selected pr",)),
|
||||
("Reviewer eligibility", ("reviewer eligibility", "eligibility")),
|
||||
("Reviewed head SHA", ("reviewed head sha", "candidate head sha")),
|
||||
("Review worktree path", ("review worktree path", "worktree path",
|
||||
"starting worktree path")),
|
||||
("Review worktree dirty", ("review worktree dirty", "worktree dirty",
|
||||
"whether worktree was dirty")),
|
||||
("Pinned reviewed head", ("pinned reviewed head", "pinned head")),
|
||||
("Worktree path", ("worktree path", "starting worktree path")),
|
||||
("Worktree dirty", ("worktree dirty", "whether worktree was dirty")),
|
||||
("Scratch worktree used", ("scratch worktree used", "scratch clone used",
|
||||
"scratch worktree")),
|
||||
("Unrelated local mutations", ("unrelated local mutations",
|
||||
"unrelated files modified",
|
||||
"file edits by reviewer")),
|
||||
"unrelated files modified")),
|
||||
("Review decision", ("review decision", "decision")),
|
||||
("Merge result", ("merge result",)),
|
||||
("Linked issue status", ("linked issue status", "linked issue")),
|
||||
("Cleanup status", ("cleanup status", "cleanup")),
|
||||
("Safe next action", ("safe next action", "next")),
|
||||
) + HANDOFF_REVIEW_MUTATION_FIELDS,
|
||||
"merger": (
|
||||
("Selected PR", ("selected pr",)),
|
||||
("Reviewed head SHA", ("reviewed head sha", "candidate head sha")),
|
||||
("Pinned reviewed head", ("pinned reviewed head", "pinned head")),
|
||||
("Active profile", ("active profile",)),
|
||||
("Role kind", ("role kind",)),
|
||||
("Merge capability source", ("merge capability source",)),
|
||||
@@ -2447,22 +2433,9 @@ def assess_controller_handoff(report_text, role=None, local_edits=False):
|
||||
# Issue #320: reviewer and merger handoffs use the precise mutation categories
|
||||
# in HANDOFF_REVIEW_MUTATION_FIELDS instead of the legacy ambiguous
|
||||
# "Workspace mutations" field, which is rejected below.
|
||||
# Issue #698: the canonical review-merge schema has no 'Mutations',
|
||||
# 'Next', 'Issue/PR', 'Branch/SHA', or 'Files changed' fields — their
|
||||
# content lives in the precise mutation categories, 'Safe next
|
||||
# action', 'Selected PR'/'Linked issue', head-SHA fields, and 'Files
|
||||
# reviewed'. Requiring the legacy names rejects canonical reports.
|
||||
_non_canonical_for_review = {
|
||||
"Workspace mutations",
|
||||
"Mutations",
|
||||
"Next",
|
||||
"Issue/PR",
|
||||
"Branch/SHA",
|
||||
"Files changed",
|
||||
}
|
||||
required = [
|
||||
field for field in required
|
||||
if field[0] not in _non_canonical_for_review
|
||||
if field[0] != "Workspace mutations"
|
||||
]
|
||||
if any(label.startswith("workspace mutations") for label in labels):
|
||||
return {
|
||||
|
||||
@@ -438,252 +438,3 @@ def format_cleanup_audit_comment(audit: dict[str, Any]) -> str:
|
||||
"This path only clears a lock when the referenced PR is merged/closed.",
|
||||
]
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# #709 cross-profile cleanup, overwrite protection, recovery provenance
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def has_unresolved_terminal_evidence(lock: dict | None) -> bool:
|
||||
"""True when *lock* still carries a terminal live mutation ledger."""
|
||||
return last_terminal_mutation(lock) is not None
|
||||
|
||||
|
||||
def assess_init_overwrite(
|
||||
existing_lock: dict | None,
|
||||
*,
|
||||
force: bool = False,
|
||||
) -> dict[str, Any]:
|
||||
"""Whether init_review_decision_lock may replace an existing durable lock (#709 AC2).
|
||||
|
||||
Unresolved terminal evidence must never be silently replaced by an empty
|
||||
initialized lock. *force* does not authorize destruction of terminal
|
||||
ledgers — only explicit cleanup / archive transitions may remove them.
|
||||
"""
|
||||
result: dict[str, Any] = {
|
||||
"overwrite_allowed": True,
|
||||
"has_existing": existing_lock is not None,
|
||||
"has_unresolved_terminal": False,
|
||||
"reasons": [],
|
||||
"last_terminal_pr": None,
|
||||
"last_terminal_action": None,
|
||||
"existing_profile_identity": None,
|
||||
}
|
||||
if existing_lock is None:
|
||||
result["reasons"].append("no existing lock; empty init allowed")
|
||||
return result
|
||||
result["existing_profile_identity"] = (
|
||||
existing_lock.get("profile_identity")
|
||||
or existing_lock.get("session_profile_lock")
|
||||
or existing_lock.get("session_profile")
|
||||
)
|
||||
last = last_terminal_mutation(existing_lock)
|
||||
if last is None:
|
||||
result["reasons"].append(
|
||||
"existing lock has no terminal mutations; re-init allowed"
|
||||
)
|
||||
return result
|
||||
result["has_unresolved_terminal"] = True
|
||||
result["overwrite_allowed"] = False
|
||||
result["last_terminal_pr"] = last.get("pr_number")
|
||||
result["last_terminal_action"] = last.get("action")
|
||||
result["reasons"].append(
|
||||
"refuse empty re-init: unresolved terminal decision-lock evidence "
|
||||
f"present ({last.get('action')} on PR #{last.get('pr_number')}); "
|
||||
"use gitea_cleanup_stale_review_decision_lock when moot, or archive "
|
||||
f"via sanctioned recovery — force={force!r} does not authorize overwrite "
|
||||
"(#709 AC2)"
|
||||
)
|
||||
return result
|
||||
|
||||
|
||||
def lock_targets_merged_pr_approval(
|
||||
lock: dict | None,
|
||||
*,
|
||||
pr_number: int,
|
||||
expected_head_sha: str | None = None,
|
||||
) -> bool:
|
||||
"""True when *lock*'s last terminal mutation is approve of *pr_number*.
|
||||
|
||||
When *expected_head_sha* is provided, a **recorded** terminal head must
|
||||
match. Legacy same-repo approve locks with no recorded head do **not**
|
||||
match (fail closed, #709 F3 residual / review 435) — callers must use the
|
||||
strict secondary path that refuses no-head clears.
|
||||
"""
|
||||
last = last_terminal_mutation(lock)
|
||||
if last is None:
|
||||
return False
|
||||
if last.get("action") != "approve":
|
||||
return False
|
||||
if last.get("pr_number") != pr_number:
|
||||
return False
|
||||
if expected_head_sha:
|
||||
want = normalize_head_sha(expected_head_sha)
|
||||
if not want:
|
||||
return False
|
||||
locked = mutation_head_sha(last, lock)
|
||||
# Require recorded-head match; unrecorded head is not a match (#709 F3).
|
||||
if not locked or not heads_equal(locked, want):
|
||||
return False
|
||||
return True
|
||||
|
||||
|
||||
def build_post_merge_recovery_record(
|
||||
*,
|
||||
pr_number: int,
|
||||
head_sha: str | None,
|
||||
merge_commit_sha: str | None,
|
||||
target_profile_identity: str | None,
|
||||
failed_step: str,
|
||||
error: str | None,
|
||||
remote: str | None,
|
||||
org: str | None,
|
||||
repo: str | None,
|
||||
actor_username: str | None,
|
||||
profile_name: str | None,
|
||||
) -> dict[str, Any]:
|
||||
"""Durable recovery-required payload after irreversible merge (#709 AC3)."""
|
||||
return {
|
||||
"event": "post_merge_decision_lock_recovery_required",
|
||||
"status": "recovery_required",
|
||||
"issue_ref": "#709",
|
||||
"recovery_critical": True,
|
||||
"applied": False, # never claim historical cleanup succeeded
|
||||
"timestamp": datetime.now(timezone.utc).isoformat(),
|
||||
"pr_number": pr_number,
|
||||
"head_sha": normalize_head_sha(head_sha),
|
||||
"merge_commit_sha": merge_commit_sha,
|
||||
"target_profile_identity": target_profile_identity,
|
||||
"failed_step": failed_step,
|
||||
"error": error,
|
||||
"remote": remote,
|
||||
"org": org,
|
||||
"repo": repo,
|
||||
"actor_username": actor_username,
|
||||
"profile_name": profile_name,
|
||||
"required_recovery_action": (
|
||||
"retry cross-profile decision-lock cleanup and audit publication "
|
||||
"for the merged PR; if terminal evidence is gone, use "
|
||||
"gitea_record_irrecoverable_decision_lock_provenance"
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
def build_irrecoverable_provenance_record(
|
||||
*,
|
||||
pr_number: int,
|
||||
head_sha: str | None,
|
||||
remote: str | None,
|
||||
org: str | None,
|
||||
repo: str | None,
|
||||
actor_username: str | None,
|
||||
profile_name: str | None,
|
||||
reason: str,
|
||||
incident_ref: str | None = None,
|
||||
# Deprecated kwargs retained only so stale call sites fail closed:
|
||||
operator_authorized: bool | None = None,
|
||||
# Required for merger-acceptable records (#709 F1):
|
||||
authorization: dict[str, Any] | None = None,
|
||||
incident_issue: int | None = None,
|
||||
incident_comment_id: int | None = None,
|
||||
destroyed_subject: str | None = None,
|
||||
historical_provenance_subject: str | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""Truthful absence-of-proof record (#709 AC5). Never sets applied=True.
|
||||
|
||||
Caller-supplied ``operator_authorized`` is **ignored** as authorization
|
||||
evidence (review 434 F1). Prefer
|
||||
:func:`irrecoverable_provenance.build_irrecoverable_provenance_record`
|
||||
with a verified server-side authorization artifact.
|
||||
"""
|
||||
# Explicitly ignore deprecated self-assertable Boolean.
|
||||
_ = operator_authorized
|
||||
if authorization is not None and incident_issue is not None and incident_comment_id is not None:
|
||||
from irrecoverable_provenance import (
|
||||
build_irrecoverable_provenance_record as _build,
|
||||
)
|
||||
|
||||
return _build(
|
||||
pr_number=int(pr_number),
|
||||
head_sha=str(head_sha or ""),
|
||||
remote=str(remote or ""),
|
||||
org=str(org or ""),
|
||||
repo=str(repo or ""),
|
||||
actor_username=actor_username,
|
||||
profile_name=profile_name,
|
||||
reason=reason,
|
||||
incident_issue=int(incident_issue),
|
||||
incident_comment_id=int(incident_comment_id),
|
||||
authorization=authorization,
|
||||
destroyed_subject=destroyed_subject,
|
||||
historical_provenance_subject=historical_provenance_subject
|
||||
or destroyed_subject,
|
||||
)
|
||||
# Fail-closed skeleton when no server authorization is supplied: never
|
||||
# sets merger_may_accept True (even if operator_authorized was True).
|
||||
return {
|
||||
"event": "irrecoverable_decision_lock_provenance",
|
||||
"status": "provenance_irrecoverable",
|
||||
"record_type": "irrecoverable_decision_provenance",
|
||||
"operator_recovery_required": True,
|
||||
"issue_ref": "#709",
|
||||
"recovery_critical": True,
|
||||
"applied": False,
|
||||
"historical_cleanup_proven": False,
|
||||
"timestamp": datetime.now(timezone.utc).isoformat(),
|
||||
"pr_number": pr_number,
|
||||
"head_sha": normalize_head_sha(head_sha),
|
||||
"remote": remote,
|
||||
"org": org,
|
||||
"repo": repo,
|
||||
"actor_username": actor_username,
|
||||
"profile_name": profile_name,
|
||||
"reason": reason,
|
||||
"incident_ref": incident_ref,
|
||||
"incident_issue": incident_issue,
|
||||
"incident_comment_id": incident_comment_id,
|
||||
"authorization_verified": False,
|
||||
"merger_may_accept": False,
|
||||
"acceptance_rule": (
|
||||
"Merger may accept this record only when a server-side "
|
||||
"authorization artifact verifies for remote/org/repo/PR/exact "
|
||||
"head/incident, the record is durable and read back, and normal "
|
||||
"merge gates still pass. Caller Booleans never authorize. This "
|
||||
"does not prove historical cleanup."
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
def format_irrecoverable_audit_comment(record: dict[str, Any]) -> str:
|
||||
"""Markdown body for irrecoverable provenance audit (no applied=true claim)."""
|
||||
from irrecoverable_provenance import (
|
||||
format_irrecoverable_audit_comment as _fmt,
|
||||
)
|
||||
|
||||
return _fmt(record)
|
||||
|
||||
|
||||
def format_post_merge_recovery_comment(record: dict[str, Any]) -> str:
|
||||
"""Markdown body for post-merge recovery-required audit."""
|
||||
lines = [
|
||||
"## Post-merge decision-lock recovery required (#709)",
|
||||
"",
|
||||
"Status: **RECOVERY_REQUIRED** (merge is irreversible; cleanup/audit incomplete)",
|
||||
"",
|
||||
f"- actor: `{record.get('actor_username')}`",
|
||||
f"- profile: `{record.get('profile_name')}`",
|
||||
f"- timestamp: `{record.get('timestamp')}`",
|
||||
f"- PR: `#{record.get('pr_number')}`",
|
||||
f"- head_sha: `{record.get('head_sha')}`",
|
||||
f"- merge_commit_sha: `{record.get('merge_commit_sha')}`",
|
||||
f"- target_profile_identity: `{record.get('target_profile_identity')}`",
|
||||
f"- failed_step: `{record.get('failed_step')}`",
|
||||
f"- error: `{record.get('error')}`",
|
||||
"",
|
||||
f"Required action: {record.get('required_recovery_action')}",
|
||||
"",
|
||||
"applied=false — do not treat this as successful cleanup evidence.",
|
||||
]
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
@@ -127,32 +127,6 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
|
||||
"permission": "gitea.pr.review",
|
||||
"role": "reviewer",
|
||||
},
|
||||
# #709: truthful absence-of-proof recovery (server-side auth + record + consume).
|
||||
# Dedicated mutation capability — gitea.read is insufficient (review 434 F1).
|
||||
"issue_irrecoverable_provenance_authorization": {
|
||||
"permission": "gitea.decision_lock.irrecoverable_recovery",
|
||||
"role": "reconciler",
|
||||
},
|
||||
"gitea_issue_irrecoverable_provenance_authorization": {
|
||||
"permission": "gitea.decision_lock.irrecoverable_recovery",
|
||||
"role": "reconciler",
|
||||
},
|
||||
"record_irrecoverable_decision_lock_provenance": {
|
||||
"permission": "gitea.decision_lock.irrecoverable_recovery",
|
||||
"role": "reconciler",
|
||||
},
|
||||
"gitea_record_irrecoverable_decision_lock_provenance": {
|
||||
"permission": "gitea.decision_lock.irrecoverable_recovery",
|
||||
"role": "reconciler",
|
||||
},
|
||||
"consume_irrecoverable_decision_lock_provenance": {
|
||||
"permission": "gitea.pr.merge",
|
||||
"role": "merger",
|
||||
},
|
||||
"gitea_consume_irrecoverable_decision_lock_provenance": {
|
||||
"permission": "gitea.pr.merge",
|
||||
"role": "merger",
|
||||
},
|
||||
"delete_branch": {
|
||||
"permission": "gitea.branch.delete",
|
||||
"role": "author",
|
||||
|
||||
@@ -58,17 +58,6 @@ def _reset_mutation_authority(monkeypatch):
|
||||
_fallback: str = state_dir,
|
||||
_env_key: str = mcp_session_state.STATE_DIR_ENV,
|
||||
) -> str:
|
||||
# #695 AC2: when production native transport has pinned a session
|
||||
# state root, that pin is authoritative even under test isolation
|
||||
# (PR #701 redirected-state regression).
|
||||
try:
|
||||
import mcp_daemon_guard
|
||||
|
||||
pinned = mcp_daemon_guard.pinned_session_state_dir()
|
||||
if pinned:
|
||||
return pinned
|
||||
except Exception:
|
||||
pass
|
||||
raw = (os.environ.get(_env_key) or "").strip()
|
||||
return raw or _fallback
|
||||
|
||||
|
||||
@@ -1,18 +1,14 @@
|
||||
"""Regression tests for Issue #695 — second incident (PR #694 / review 427).
|
||||
|
||||
Reproduces offline import, env-only runtime spoof, exposed-token invocation,
|
||||
direct imports, basename entrypoint spoof, allow_test_bootstrap forgery,
|
||||
standalone quarantine attempts, and false “official workflow” canonical claims.
|
||||
Gates must fail closed.
|
||||
direct imports, locally generated runtime keys, standalone quarantine attempts,
|
||||
and false “official workflow” canonical claims. Gates must fail closed.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import subprocess
|
||||
import sys
|
||||
import tempfile
|
||||
import textwrap
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
from unittest.mock import patch
|
||||
@@ -24,26 +20,6 @@ import canonical_comment_validator as ccv
|
||||
|
||||
HEAD_694 = "1844e298809373be19a526fd39b7d8b0669eb5bd"
|
||||
HEAD_OTHER = "bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb"
|
||||
REPO_ROOT = Path(__file__).resolve().parent.parent
|
||||
|
||||
|
||||
def _run_offline_snippet(snippet: str, *, env_extra: dict[str, str] | None = None) -> subprocess.CompletedProcess:
|
||||
"""Execute snippet in a fresh interpreter (no pytest modules)."""
|
||||
env = os.environ.copy()
|
||||
env.pop("PYTEST_CURRENT_TEST", None)
|
||||
env.pop(mcp_daemon_guard.FORCE_PROVENANCE_FAIL_ENV, None)
|
||||
env["PYTHONPATH"] = str(REPO_ROOT) + os.pathsep + env.get("PYTHONPATH", "")
|
||||
if env_extra:
|
||||
env.update(env_extra)
|
||||
return subprocess.run(
|
||||
[sys.executable, "-c", snippet],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
cwd=str(REPO_ROOT),
|
||||
env=env,
|
||||
timeout=30,
|
||||
check=False,
|
||||
)
|
||||
|
||||
|
||||
class TestNativeTransportBinding(unittest.TestCase):
|
||||
@@ -63,53 +39,35 @@ class TestNativeTransportBinding(unittest.TestCase):
|
||||
mcp_daemon_guard.assert_sanctioned_mutation_runtime("offline_import")
|
||||
msg = str(ctx.exception)
|
||||
self.assertIn("#695", msg)
|
||||
# FORCE disables pytest allowance; direct-import env is rejected first
|
||||
# (AC1). Without ALLOW_DIRECT, env-alone also yields "not sufficient".
|
||||
lowered = msg.lower()
|
||||
self.assertTrue(
|
||||
"direct" in lowered
|
||||
or "not sufficient" in lowered
|
||||
or "allow_direct" in lowered
|
||||
or "gitea_allow_direct" in lowered,
|
||||
msg,
|
||||
)
|
||||
self.assertIn("not sufficient", msg.lower() + " " + msg)
|
||||
|
||||
def test_direct_import_mark_rejected_outside_entrypoint(self):
|
||||
mcp_daemon_guard.clear_native_runtime_for_tests()
|
||||
os.environ[mcp_daemon_guard.FORCE_PROVENANCE_FAIL_ENV] = "1"
|
||||
with self.assertRaises(mcp_daemon_guard.UnsanctionedRuntimeError) as ctx:
|
||||
mcp_daemon_guard.mark_sanctioned_daemon()
|
||||
self.assertIn("canonical", str(ctx.exception).lower())
|
||||
self.assertIn("mcp_server.py", str(ctx.exception))
|
||||
self.assertFalse(mcp_daemon_guard.is_native_mcp_transport())
|
||||
|
||||
def test_locally_generated_runtime_key_without_entrypoint_rejected(self):
|
||||
"""Spoofing process-local fields via mark outside entrypoint fails."""
|
||||
mcp_daemon_guard.clear_native_runtime_for_tests()
|
||||
os.environ[mcp_daemon_guard.FORCE_PROVENANCE_FAIL_ENV] = "1"
|
||||
# Even if a caller tries allow_test_bootstrap under force-unsanctioned
|
||||
# pytest path is also forced off — only real entrypoint may mark.
|
||||
with self.assertRaises(mcp_daemon_guard.UnsanctionedRuntimeError):
|
||||
mcp_daemon_guard.mark_sanctioned_daemon()
|
||||
mcp_daemon_guard.mark_sanctioned_daemon(allow_test_bootstrap=False)
|
||||
|
||||
def test_test_native_runtime_for_hermetic_tests_not_production(self):
|
||||
def test_test_bootstrap_establishes_native_for_hermetic_tests(self):
|
||||
mcp_daemon_guard.clear_native_runtime_for_tests()
|
||||
st = mcp_daemon_guard.install_test_native_runtime()
|
||||
st = mcp_daemon_guard.mark_sanctioned_daemon(allow_test_bootstrap=True)
|
||||
self.assertTrue(st["native_mcp_transport"])
|
||||
self.assertTrue(mcp_daemon_guard.is_native_mcp_transport())
|
||||
self.assertFalse(mcp_daemon_guard.is_production_native_mcp_transport())
|
||||
mcp_daemon_guard.assert_sanctioned_mutation_runtime("test-bootstrap")
|
||||
fields = mcp_daemon_guard.mutation_provenance_fields()
|
||||
self.assertEqual(fields["transport"], "test_native_mcp")
|
||||
self.assertEqual(fields["transport"], "native_mcp")
|
||||
self.assertTrue(fields["native_mcp_transport"])
|
||||
self.assertFalse(fields["production_native_mcp_transport"])
|
||||
self.assertIsNotNone(fields["native_token_fingerprint"])
|
||||
with self.assertRaises(mcp_daemon_guard.UnsanctionedRuntimeError) as ctx:
|
||||
mcp_daemon_guard.assert_production_mutation_runtime("prod-endpoint")
|
||||
self.assertIn("Test-mode", str(ctx.exception))
|
||||
|
||||
def test_no_allow_test_bootstrap_parameter_on_mark(self):
|
||||
import inspect
|
||||
|
||||
sig = inspect.signature(mcp_daemon_guard.mark_sanctioned_daemon)
|
||||
self.assertNotIn("allow_test_bootstrap", sig.parameters)
|
||||
|
||||
def test_exposed_token_env_never_grants_native(self):
|
||||
"""Raw / exposed token env vars must never reconstruct native transport."""
|
||||
@@ -138,249 +96,6 @@ class TestNativeTransportBinding(unittest.TestCase):
|
||||
os.environ.pop(key, None)
|
||||
|
||||
|
||||
class TestAC9BypassRegressions(unittest.TestCase):
|
||||
"""AC9: empirically reproduced offline bypasses must fail closed (#695)."""
|
||||
|
||||
def tearDown(self) -> None:
|
||||
mcp_daemon_guard.clear_native_runtime_for_tests()
|
||||
os.environ.pop(mcp_daemon_guard.FORCE_PROVENANCE_FAIL_ENV, None)
|
||||
|
||||
def test_allow_test_bootstrap_cannot_authorize_fresh_offline_interpreter(self):
|
||||
"""Finding 1: former allow_test_bootstrap forge is gone and rejected offline."""
|
||||
snippet = textwrap.dedent(
|
||||
"""
|
||||
import inspect
|
||||
import mcp_daemon_guard as g
|
||||
sig = inspect.signature(g.mark_sanctioned_daemon)
|
||||
assert "allow_test_bootstrap" not in sig.parameters, "bootstrap flag must not exist"
|
||||
try:
|
||||
g.mark_sanctioned_daemon(allow_test_bootstrap=True)
|
||||
except TypeError:
|
||||
pass
|
||||
else:
|
||||
raise SystemExit("mark_sanctioned_daemon accepted allow_test_bootstrap")
|
||||
try:
|
||||
g.install_test_native_runtime()
|
||||
except g.UnsanctionedRuntimeError as exc:
|
||||
assert "pytest" in str(exc).lower() or "#695" in str(exc)
|
||||
else:
|
||||
raise SystemExit("install_test_native_runtime authorized offline interpreter")
|
||||
assert g.is_native_mcp_transport() is False
|
||||
try:
|
||||
g.assert_sanctioned_mutation_runtime("offline-bootstrap")
|
||||
except g.UnsanctionedRuntimeError:
|
||||
pass
|
||||
else:
|
||||
raise SystemExit("mutation runtime authorized after offline bootstrap attempt")
|
||||
print("OK")
|
||||
"""
|
||||
)
|
||||
proc = _run_offline_snippet(snippet)
|
||||
self.assertEqual(proc.returncode, 0, proc.stdout + proc.stderr)
|
||||
self.assertIn("OK", proc.stdout)
|
||||
|
||||
def test_renamed_runner_named_mcp_server_py_rejected(self):
|
||||
"""Finding 2: basename-only entrypoint trust is insufficient."""
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
attacker = Path(tmp) / "mcp_server.py"
|
||||
attacker.write_text(
|
||||
textwrap.dedent(
|
||||
"""
|
||||
import mcp_daemon_guard as g
|
||||
try:
|
||||
g.mark_sanctioned_daemon()
|
||||
except g.UnsanctionedRuntimeError as exc:
|
||||
print("REJECTED:" + str(exc))
|
||||
raise SystemExit(0)
|
||||
print("AUTHORIZED")
|
||||
raise SystemExit(1)
|
||||
"""
|
||||
),
|
||||
encoding="utf-8",
|
||||
)
|
||||
env = os.environ.copy()
|
||||
env.pop("PYTEST_CURRENT_TEST", None)
|
||||
env["PYTHONPATH"] = str(REPO_ROOT) + os.pathsep + env.get("PYTHONPATH", "")
|
||||
proc = subprocess.run(
|
||||
[sys.executable, str(attacker)],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
cwd=tmp,
|
||||
env=env,
|
||||
timeout=30,
|
||||
check=False,
|
||||
)
|
||||
self.assertEqual(proc.returncode, 0, proc.stdout + proc.stderr)
|
||||
self.assertIn("REJECTED:", proc.stdout)
|
||||
self.assertIn("canonical", proc.stdout.lower())
|
||||
self.assertNotIn("AUTHORIZED", proc.stdout)
|
||||
|
||||
def test_direct_launch_import_canonical_entrypoint_without_transport_rejected(self):
|
||||
"""Merely importing/launching real entrypoint offline must not authorize."""
|
||||
snippet = textwrap.dedent(
|
||||
f"""
|
||||
import importlib.util
|
||||
import mcp_daemon_guard as g
|
||||
# Simulate claim-only phase (no transport bind).
|
||||
g.clear_native_runtime_for_tests()
|
||||
# Direct mark from non-entrypoint must fail.
|
||||
try:
|
||||
g.mark_sanctioned_daemon()
|
||||
except g.UnsanctionedRuntimeError:
|
||||
pass
|
||||
assert g.is_native_mcp_transport() is False
|
||||
# Even if someone forges entrypoint_claimed without transport bind:
|
||||
g._NATIVE_RUNTIME = {{
|
||||
"token": "x" * 64,
|
||||
"token_fingerprint": "deadbeefdeadbeef",
|
||||
"pid": __import__("os").getpid(),
|
||||
"started_at": 0,
|
||||
"entrypoint": "mcp_server",
|
||||
"entrypoint_path": {str(REPO_ROOT / "mcp_server.py")!r},
|
||||
"phase": "entrypoint_claimed",
|
||||
"transport": None,
|
||||
"mode": "production",
|
||||
}}
|
||||
assert g.is_native_mcp_transport() is False
|
||||
try:
|
||||
g.assert_sanctioned_mutation_runtime("import-only")
|
||||
except g.UnsanctionedRuntimeError as exc:
|
||||
assert "transport" in str(exc).lower() or "entrypoint" in str(exc).lower() or "#695" in str(exc)
|
||||
else:
|
||||
raise SystemExit("import-only claim authorized mutation")
|
||||
print("OK")
|
||||
"""
|
||||
)
|
||||
proc = _run_offline_snippet(snippet)
|
||||
self.assertEqual(proc.returncode, 0, proc.stdout + proc.stderr)
|
||||
self.assertIn("OK", proc.stdout)
|
||||
|
||||
def test_spoofed_pytest_env_stack_path_rejected(self):
|
||||
"""Spoofed pytest/env/call-stack/path evidence must not authorize offline."""
|
||||
snippet = textwrap.dedent(
|
||||
f"""
|
||||
import os
|
||||
import mcp_daemon_guard as g
|
||||
os.environ["PYTEST_CURRENT_TEST"] = "spoofed::test"
|
||||
os.environ[g.SANCTIONED_DAEMON_ENV] = "1"
|
||||
os.environ[g.ALLOW_DIRECT_IMPORT_ENV] = "1"
|
||||
# Fresh interpreter has no pytest module; PYTEST_CURRENT_TEST alone
|
||||
# might still trip is_pytest_runtime — force-unsanctioned is not set.
|
||||
# But install_test_native_runtime requires real pytest path; if
|
||||
# PYTEST_CURRENT_TEST alone grants is_pytest_runtime, production
|
||||
# mutation still requires production transport outside true pytest.
|
||||
if g.is_pytest_runtime():
|
||||
# Env-only pytest spoof: test install may succeed, but production
|
||||
# mutation gate must still reject test mode.
|
||||
g.install_test_native_runtime()
|
||||
assert g.is_production_native_mcp_transport() is False
|
||||
try:
|
||||
g.assert_production_mutation_runtime("spoofed-pytest")
|
||||
except g.UnsanctionedRuntimeError:
|
||||
pass
|
||||
else:
|
||||
raise SystemExit("production mutation accepted test-mode under spoofed pytest env")
|
||||
else:
|
||||
try:
|
||||
g.install_test_native_runtime()
|
||||
except g.UnsanctionedRuntimeError:
|
||||
pass
|
||||
else:
|
||||
raise SystemExit("test install without pytest evidence")
|
||||
# Basename path spoof via inspect is covered elsewhere; env alone:
|
||||
g.clear_native_runtime_for_tests()
|
||||
os.environ.pop("PYTEST_CURRENT_TEST", None)
|
||||
assert g.is_native_mcp_transport() is False
|
||||
try:
|
||||
g.assert_sanctioned_mutation_runtime("env-path-spoof")
|
||||
except g.UnsanctionedRuntimeError:
|
||||
pass
|
||||
else:
|
||||
raise SystemExit("env/path spoof authorized mutation")
|
||||
print("OK")
|
||||
"""
|
||||
)
|
||||
proc = _run_offline_snippet(snippet)
|
||||
self.assertEqual(proc.returncode, 0, proc.stdout + proc.stderr)
|
||||
self.assertIn("OK", proc.stdout)
|
||||
|
||||
def test_test_bootstrap_cannot_reach_production_mutation_endpoints(self):
|
||||
"""Under pytest, test-mode runtime cannot satisfy production mutation gate."""
|
||||
mcp_daemon_guard.clear_native_runtime_for_tests()
|
||||
mcp_daemon_guard.install_test_native_runtime()
|
||||
with self.assertRaises(mcp_daemon_guard.UnsanctionedRuntimeError) as ctx:
|
||||
mcp_daemon_guard.assert_production_mutation_runtime(
|
||||
"gitea_quarantine_contaminated_review"
|
||||
)
|
||||
msg = str(ctx.exception)
|
||||
self.assertIn("Test-mode", msg)
|
||||
self.assertIn("#695", msg)
|
||||
|
||||
# Offline: install_test_native_runtime must not authorize production mutations.
|
||||
snippet = textwrap.dedent(
|
||||
"""
|
||||
import mcp_daemon_guard as g
|
||||
try:
|
||||
g.install_test_native_runtime()
|
||||
except g.UnsanctionedRuntimeError:
|
||||
pass
|
||||
assert g.is_production_native_mcp_transport() is False
|
||||
try:
|
||||
g.assert_production_mutation_runtime("gitea_quarantine_contaminated_review")
|
||||
except g.UnsanctionedRuntimeError:
|
||||
pass
|
||||
else:
|
||||
raise SystemExit("production mutation authorized offline")
|
||||
try:
|
||||
g.assert_sanctioned_mutation_runtime("gitea_mutation")
|
||||
except g.UnsanctionedRuntimeError:
|
||||
pass
|
||||
else:
|
||||
raise SystemExit("sanctioned mutation authorized offline")
|
||||
print("OK")
|
||||
"""
|
||||
)
|
||||
proc = _run_offline_snippet(snippet)
|
||||
self.assertEqual(proc.returncode, 0, proc.stdout + proc.stderr)
|
||||
self.assertIn("OK", proc.stdout)
|
||||
|
||||
def test_legitimate_native_transport_bind_succeeds(self):
|
||||
"""Canonical entrypoint path + stdio bind establishes production native."""
|
||||
mcp_daemon_guard.clear_native_runtime_for_tests()
|
||||
# Simulate production path under force-unsanctioned (no pytest allowance)
|
||||
# by calling internal claim/bind with patched caller path.
|
||||
canonical = str((REPO_ROOT / "mcp_server.py").resolve())
|
||||
|
||||
def _fake_caller():
|
||||
return canonical
|
||||
|
||||
with patch.object(
|
||||
mcp_daemon_guard, "_caller_official_entrypoint_path", side_effect=_fake_caller
|
||||
):
|
||||
# Force non-pytest path for mark/bind logic.
|
||||
with patch.object(mcp_daemon_guard, "is_pytest_runtime", return_value=False):
|
||||
st1 = mcp_daemon_guard.mark_sanctioned_daemon()
|
||||
self.assertFalse(st1["native_mcp_transport"])
|
||||
self.assertEqual(st1["phase"], "entrypoint_claimed")
|
||||
st2 = mcp_daemon_guard.bind_native_mcp_transport(transport="stdio")
|
||||
self.assertTrue(st2["native_mcp_transport"])
|
||||
self.assertTrue(st2["production_native_mcp_transport"])
|
||||
self.assertEqual(st2["transport"], "stdio")
|
||||
self.assertEqual(st2["mode"], "production")
|
||||
mcp_daemon_guard.assert_sanctioned_mutation_runtime("native-ide")
|
||||
mcp_daemon_guard.assert_production_mutation_runtime("native-ide")
|
||||
fields = mcp_daemon_guard.mutation_provenance_fields()
|
||||
self.assertEqual(fields["transport"], "native_mcp")
|
||||
self.assertTrue(fields["production_native_mcp_transport"])
|
||||
|
||||
def test_canonical_entrypoint_paths_are_resolved_absolute(self):
|
||||
paths = mcp_daemon_guard.canonical_entrypoint_paths()
|
||||
self.assertTrue(any(p.endswith("mcp_server.py") for p in paths))
|
||||
for p in paths:
|
||||
self.assertTrue(os.path.isabs(p), p)
|
||||
self.assertEqual(p, str(Path(p).resolve()))
|
||||
|
||||
|
||||
class TestQuarantineWriteNativeOnly(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self._tmp = tempfile.TemporaryDirectory()
|
||||
@@ -418,12 +133,7 @@ class TestQuarantineWriteNativeOnly(unittest.TestCase):
|
||||
forensic_comment_ids=[10883, 10886],
|
||||
)
|
||||
with self.assertRaises(mcp_daemon_guard.UnsanctionedRuntimeError):
|
||||
# Force non-pytest and non-native for write path.
|
||||
with patch.object(mcp_daemon_guard, "is_pytest_runtime", return_value=False):
|
||||
with patch.object(
|
||||
mcp_daemon_guard, "is_native_mcp_transport", return_value=False
|
||||
):
|
||||
review_quarantine.write_quarantine_record(record)
|
||||
review_quarantine.write_quarantine_record(record)
|
||||
|
||||
def test_confirmation_must_match_exactly(self):
|
||||
assessment = review_quarantine.assess_quarantine_write(
|
||||
@@ -460,7 +170,7 @@ class TestQuarantineWriteNativeOnly(unittest.TestCase):
|
||||
"review_quarantine.mcp_session_state.default_state_dir",
|
||||
return_value=self._tmp.name,
|
||||
):
|
||||
mcp_daemon_guard.install_test_native_runtime()
|
||||
mcp_daemon_guard.mark_sanctioned_daemon(allow_test_bootstrap=True)
|
||||
record = review_quarantine.build_quarantine_record(
|
||||
remote="prgs",
|
||||
org="org",
|
||||
@@ -595,7 +305,7 @@ class TestFeedbackQuarantineIntegration(unittest.TestCase):
|
||||
self._tmp = tempfile.TemporaryDirectory()
|
||||
self.addCleanup(self._tmp.cleanup)
|
||||
mcp_daemon_guard.clear_native_runtime_for_tests()
|
||||
mcp_daemon_guard.install_test_native_runtime()
|
||||
mcp_daemon_guard.mark_sanctioned_daemon(allow_test_bootstrap=True)
|
||||
|
||||
def tearDown(self) -> None:
|
||||
mcp_daemon_guard.clear_native_runtime_for_tests()
|
||||
@@ -686,163 +396,5 @@ class TestDocsStopAfterNativeFailure(unittest.TestCase):
|
||||
self.assertIn("GITEA_ALLOW_DIRECT_MCP_IMPORT", doc)
|
||||
|
||||
|
||||
class TestPR701DirectImportSessionOverrideSequence(unittest.TestCase):
|
||||
"""AC9 regression: exact PR #701 contaminated-approval sequence must fail closed.
|
||||
|
||||
Observed attack:
|
||||
- GITEA_ALLOW_DIRECT_MCP_IMPORT=1
|
||||
- import mutation tools from gitea_mcp_server
|
||||
- GITEA_MCP_SESSION_STATE_DIR=.mcp_session_701 (cross-PR lock evasion)
|
||||
- mark_final + submit_pr_review
|
||||
"""
|
||||
|
||||
def tearDown(self) -> None:
|
||||
mcp_daemon_guard.clear_native_runtime_for_tests()
|
||||
os.environ.pop(mcp_daemon_guard.FORCE_PROVENANCE_FAIL_ENV, None)
|
||||
os.environ.pop(mcp_daemon_guard.SANCTIONED_DAEMON_ENV, None)
|
||||
os.environ.pop(mcp_daemon_guard.ALLOW_DIRECT_IMPORT_ENV, None)
|
||||
os.environ.pop(mcp_daemon_guard.SESSION_STATE_DIR_ENV, None)
|
||||
|
||||
def test_offline_run_submit_sequence_fails_closed(self):
|
||||
"""Fresh interpreter: direct import + state-dir override cannot mark/submit."""
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
redirect = str(Path(tmp) / ".mcp_session_701")
|
||||
snippet = textwrap.dedent(
|
||||
f"""
|
||||
import os
|
||||
import sys
|
||||
os.environ["GITEA_ALLOW_DIRECT_MCP_IMPORT"] = "1"
|
||||
os.environ["GITEA_MCP_SESSION_STATE_DIR"] = {redirect!r}
|
||||
os.environ["GITEA_MCP_PROFILE"] = "prgs-reviewer"
|
||||
# No pytest modules in this subprocess.
|
||||
import mcp_daemon_guard as g
|
||||
assert g.is_native_mcp_transport() is False
|
||||
assert g.is_production_native_mcp_transport() is False
|
||||
try:
|
||||
g.assert_sanctioned_mutation_runtime("run_submit_mark")
|
||||
except g.UnsanctionedRuntimeError as exc:
|
||||
msg = str(exc)
|
||||
assert "GITEA_ALLOW_DIRECT_MCP_IMPORT" in msg or "#695" in msg
|
||||
else:
|
||||
raise SystemExit("direct-import env authorized mutation runtime")
|
||||
try:
|
||||
g.mark_sanctioned_daemon()
|
||||
except g.UnsanctionedRuntimeError:
|
||||
pass
|
||||
else:
|
||||
raise SystemExit("mark_sanctioned_daemon authorized offline import")
|
||||
# Simulate decision-lock write into redirected dir only — must not
|
||||
# establish native authority.
|
||||
import mcp_session_state as ss
|
||||
wrote = ss.save_state(
|
||||
kind=ss.KIND_DECISION_LOCK,
|
||||
payload={{
|
||||
"final_review_decision_ready": True,
|
||||
"ready_pr_number": 701,
|
||||
"ready_action": "approve",
|
||||
"ready_expected_head_sha": "6b675f5c834b41f9d74e8a54294ff44dddf28ae4",
|
||||
"session_profile": "prgs-reviewer",
|
||||
"session_profile_lock": "prgs-reviewer",
|
||||
"remote": "prgs",
|
||||
}},
|
||||
profile_identity="prgs-reviewer",
|
||||
state_dir={redirect!r},
|
||||
)
|
||||
assert wrote is not None
|
||||
assert g.is_native_mcp_transport() is False
|
||||
try:
|
||||
g.assert_no_direct_import_bypass("gitea_submit_pr_review")
|
||||
except g.UnsanctionedRuntimeError:
|
||||
pass
|
||||
else:
|
||||
raise SystemExit("direct-import bypass accepted for submit")
|
||||
print("OK")
|
||||
"""
|
||||
)
|
||||
proc = _run_offline_snippet(snippet)
|
||||
self.assertEqual(proc.returncode, 0, proc.stdout + proc.stderr)
|
||||
self.assertIn("OK", proc.stdout)
|
||||
|
||||
def test_session_state_dir_pin_ignores_post_bind_redirect(self):
|
||||
"""AC2: after production bind, env STATE_DIR override is ignored."""
|
||||
mcp_daemon_guard.clear_native_runtime_for_tests()
|
||||
import mcp_session_state
|
||||
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
legitimate = str(Path(tmp) / "legitimate-state")
|
||||
rogue = str(Path(tmp) / ".mcp_session_701")
|
||||
os.makedirs(legitimate, mode=0o700, exist_ok=True)
|
||||
os.makedirs(rogue, mode=0o700, exist_ok=True)
|
||||
os.environ[mcp_daemon_guard.SESSION_STATE_DIR_ENV] = legitimate
|
||||
canonical = str((REPO_ROOT / "mcp_server.py").resolve())
|
||||
|
||||
def _fake_caller():
|
||||
return canonical
|
||||
|
||||
with patch.object(
|
||||
mcp_daemon_guard,
|
||||
"_caller_official_entrypoint_path",
|
||||
side_effect=_fake_caller,
|
||||
):
|
||||
with patch.object(
|
||||
mcp_daemon_guard, "is_pytest_runtime", return_value=False
|
||||
):
|
||||
mcp_daemon_guard.mark_sanctioned_daemon()
|
||||
mcp_daemon_guard.bind_native_mcp_transport(transport="stdio")
|
||||
pinned = mcp_daemon_guard.pinned_session_state_dir()
|
||||
self.assertEqual(pinned, str(Path(legitimate).resolve()))
|
||||
# Attacker redirects env after bind (PR #701).
|
||||
os.environ[mcp_daemon_guard.SESSION_STATE_DIR_ENV] = rogue
|
||||
self.assertEqual(
|
||||
mcp_daemon_guard.pinned_session_state_dir(),
|
||||
str(Path(legitimate).resolve()),
|
||||
)
|
||||
self.assertEqual(
|
||||
mcp_session_state.default_state_dir(),
|
||||
str(Path(legitimate).resolve()),
|
||||
)
|
||||
self.assertNotEqual(
|
||||
mcp_session_state.default_state_dir(),
|
||||
str(Path(rogue).resolve()),
|
||||
)
|
||||
# Unpinned env view still sees rogue (diagnostics only).
|
||||
unpinned = mcp_session_state.env_session_state_dir_unpinned()
|
||||
self.assertTrue(
|
||||
unpinned == rogue
|
||||
or Path(unpinned).resolve() == Path(rogue).resolve(),
|
||||
unpinned,
|
||||
)
|
||||
|
||||
def test_direct_import_env_does_not_authorize_under_force_unsanctioned(self):
|
||||
mcp_daemon_guard.clear_native_runtime_for_tests()
|
||||
os.environ[mcp_daemon_guard.ALLOW_DIRECT_IMPORT_ENV] = "1"
|
||||
os.environ[mcp_daemon_guard.FORCE_PROVENANCE_FAIL_ENV] = "1"
|
||||
self.assertTrue(mcp_daemon_guard.direct_import_env_enabled())
|
||||
# Under pytest, assert_no_direct_import_bypass is a no-op; FORCE path
|
||||
# still blocks is_native / assert_sanctioned via force-unsanctioned.
|
||||
self.assertFalse(mcp_daemon_guard.is_native_mcp_transport())
|
||||
with self.assertRaises(mcp_daemon_guard.UnsanctionedRuntimeError):
|
||||
mcp_daemon_guard.assert_sanctioned_mutation_runtime("direct-import")
|
||||
|
||||
def test_quarantine_voids_merge_approval_for_contaminated_review(self):
|
||||
"""AC6–AC8: quarantined APPROVED does not satisfy merge approval head."""
|
||||
entry = {
|
||||
"verdict": "APPROVED",
|
||||
"dismissed": False,
|
||||
"reviewed_head_sha": "6b675f5c834b41f9d74e8a54294ff44dddf28ae4",
|
||||
"review_id": 431,
|
||||
"submitted_at": "2026-07-13T23:52:34Z",
|
||||
"quarantined": True,
|
||||
}
|
||||
result = merge_approval_gate.assess_merge_approval_head(
|
||||
current_head_sha="6b675f5c834b41f9d74e8a54294ff44dddf28ae4",
|
||||
latest_by_reviewer={"sysadmin": entry},
|
||||
quarantined_review_ids={431},
|
||||
)
|
||||
self.assertFalse(result["approval_at_current_head"])
|
||||
self.assertEqual(result["quarantined_approvals_at_current_head"], 1)
|
||||
self.assertIn("quarantined", (result["stale_approval_block_reason"] or ""))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
|
||||
@@ -1,461 +0,0 @@
|
||||
"""Regression tests for #698: final-report validator vs canonical schema.
|
||||
|
||||
Covers the original #698 lead plus the independent reproduction recorded
|
||||
during the PR #703 formal review (issue #698 comment 11246):
|
||||
|
||||
1. non-dict ``action_log`` entries must fail structured, never crash;
|
||||
2. the validator must not demand legacy fields the canonical schema forbids
|
||||
(``Pinned reviewed head``, ``Scratch worktree used``, ``Worktree path``,
|
||||
``Worktree dirty``, ``Mutations``, ``Next``);
|
||||
3. a legitimately blocked report (``Candidate head SHA: none``, no formal
|
||||
verdict) must not owe approval/merge live-head proofs;
|
||||
4. canonical reviewer lease release must not be misclassified as post-merge
|
||||
cleanup;
|
||||
5. structured workflow-load and validation proof must be recognized;
|
||||
6. review mutations are inferred only from authoritative evidence.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import sys
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
|
||||
|
||||
import final_report_validator as frv # noqa: E402
|
||||
import post_merge_cleanup_proof as pmcp # noqa: E402
|
||||
import pr_work_lease as pwl # noqa: E402
|
||||
import review_proofs as rp # noqa: E402
|
||||
from review_final_report_schema import ( # noqa: E402
|
||||
assess_review_final_report_schema,
|
||||
)
|
||||
|
||||
REVIEWED_HEAD = "a" * 40
|
||||
LIVE_HEAD = "a" * 40
|
||||
|
||||
|
||||
def _pr703_style_report(
|
||||
*,
|
||||
decision: str = "request_changes",
|
||||
cleanup_mutations: str = (
|
||||
"released reviewer PR lease via gitea_release_reviewer_pr_lease "
|
||||
"(terminal lease marker phase=released posted)"
|
||||
),
|
||||
) -> str:
|
||||
"""Canonical-schema report modeled on the PR #703 formal review handoff."""
|
||||
return f"""
|
||||
Formal review completed with a REQUEST_CHANGES verdict submitted and read
|
||||
back via the native review API.
|
||||
|
||||
## Controller Handoff
|
||||
|
||||
- Task: review-merge-pr
|
||||
- Repo: Scaled-Tech-Consulting/Gitea-Tools
|
||||
- Role: reviewer
|
||||
- Identity: sysadmin / prgs-reviewer
|
||||
- Active profile: prgs-reviewer
|
||||
- Runtime context: neutral workspace binding
|
||||
- Selected PR: 703
|
||||
- Linked issue: #702 open
|
||||
- Eligibility class: reviewable
|
||||
- Queue ordering policy: oldest eligible first
|
||||
- Inventory pagination proof: has_more=false, total_count=8
|
||||
- Earlier PRs skipped: none
|
||||
- Candidate head SHA: {REVIEWED_HEAD}
|
||||
- Reviewed head SHA: {REVIEWED_HEAD}
|
||||
- Target branch: master
|
||||
- Target branch SHA: {"2" * 40}
|
||||
- Already-landed gate: not landed
|
||||
- Author-safety result: pass (author differs from reviewer)
|
||||
- Prior request-changes state: none
|
||||
- Review worktree used: true
|
||||
- Review worktree path: branches/review-pr-703-independent
|
||||
- Review worktree inside branches: true
|
||||
- Review worktree HEAD state: detached at pinned head
|
||||
- Review worktree dirty before validation: clean
|
||||
- Review worktree dirty after validation: clean
|
||||
- Baseline worktree used: false
|
||||
- Baseline worktree path: none
|
||||
- Files reviewed: 4
|
||||
- Validation: focused 50 passed; related 94 passed; full 2665 passed, 6 skipped
|
||||
- Official validation integrity status: intact
|
||||
- Terminal review mutation: one REQUEST_CHANGES review submitted and read back
|
||||
- Review decision: {decision}
|
||||
- Merge preflight: not run
|
||||
- Merge result: none
|
||||
- Linked issue status: open (live fetch proof: gitea_view_issue)
|
||||
- Main checkout branch: master
|
||||
- Main checkout dirty state: clean
|
||||
- Main checkout updated: false
|
||||
- File edits by reviewer: none
|
||||
- Worktree/index mutations: none
|
||||
- Git ref mutations: git fetch prgs (recorded)
|
||||
- MCP/Gitea mutations: review submission and lease comments only
|
||||
- Review mutations: one formal REQUEST_CHANGES verdict
|
||||
- Merge mutations: none
|
||||
- Cleanup mutations: {cleanup_mutations}
|
||||
- External-state mutations: none
|
||||
- Read-only diagnostics: gitea_view_pr, gitea_get_pr_review_feedback
|
||||
- Blockers: findings F1-F6 recorded on the PR thread
|
||||
- Current status: review complete; author remediation required
|
||||
- Safe next action: author addresses findings and pushes a new head
|
||||
- Safety statement: no merge attempted; no self-review; no root-checkout edits
|
||||
- Workflow-load helper result: workflow_hash=da045d1e1f1f boundary_status=clean
|
||||
- Live head SHA before approval: {LIVE_HEAD}
|
||||
- Pushes occurred during validation: no
|
||||
"""
|
||||
|
||||
|
||||
def _blocked_preflight_report() -> str:
|
||||
"""Blocked-run report modeled on the #702 comment 11164 reproduction."""
|
||||
return """
|
||||
Fresh review preflight stopped before any worktree or validation work.
|
||||
|
||||
## Controller Handoff
|
||||
|
||||
- Task: review-merge-pr
|
||||
- Repo: Scaled-Tech-Consulting/Gitea-Tools
|
||||
- Role: reviewer
|
||||
- Identity: sysadmin / prgs-reviewer
|
||||
- Active profile: prgs-reviewer
|
||||
- Runtime context: stale workspace binding detected
|
||||
- Selected PR: 701
|
||||
- Linked issue: #699 open
|
||||
- Eligibility class: blocked-before-validation
|
||||
- Queue ordering policy: oldest eligible first
|
||||
- Inventory pagination proof: has_more=false, total_count=8
|
||||
- Earlier PRs skipped: none
|
||||
- Candidate head SHA: none
|
||||
- Reviewed head SHA: none
|
||||
- Target branch: master
|
||||
- Target branch SHA: none
|
||||
- Already-landed gate: not run
|
||||
- Author-safety result: not run
|
||||
- Prior request-changes state: none
|
||||
- Review worktree used: false
|
||||
- Review worktree path: none
|
||||
- Review worktree inside branches: not applicable
|
||||
- Review worktree HEAD state: not applicable
|
||||
- Review worktree dirty before validation: not applicable
|
||||
- Review worktree dirty after validation: not applicable
|
||||
- Baseline worktree used: false
|
||||
- Baseline worktree path: none
|
||||
- Files reviewed: 0
|
||||
- Validation: not run
|
||||
- Official validation integrity status: not applicable
|
||||
- Terminal review mutation: none
|
||||
- Review decision: none
|
||||
- Merge preflight: not run
|
||||
- Merge result: none
|
||||
- Linked issue status: open (live fetch proof: gitea_view_issue)
|
||||
- Main checkout branch: master
|
||||
- Main checkout dirty state: clean
|
||||
- Main checkout updated: false
|
||||
- File edits by reviewer: none
|
||||
- Worktree/index mutations: none
|
||||
- Git ref mutations: none
|
||||
- MCP/Gitea mutations: none
|
||||
- Review mutations: none
|
||||
- Merge mutations: none
|
||||
- Cleanup mutations: none
|
||||
- External-state mutations: none
|
||||
- Read-only diagnostics: gitea_view_pr, gitea_get_runtime_context
|
||||
- Blockers: runtime bound to a foreign task worktree; mutation prohibited
|
||||
- Current status: stopped before validation began
|
||||
- Next actor: operator
|
||||
- Next action: repair the runtime workspace binding, then rerun the full
|
||||
review workflow in a fresh reviewer session
|
||||
- Next prompt: Act as REVIEWER for PR 701 after the operator repairs the
|
||||
runtime binding; acquire the lease before any validation.
|
||||
- Safe next action: operator repairs runtime binding, then a fresh reviewer
|
||||
reruns the full workflow
|
||||
- Safety statement: no lease acquired; no verdict recorded; no source edits
|
||||
- Workflow-load helper result: workflow_hash=da045d1e1f1f boundary_status=clean
|
||||
"""
|
||||
|
||||
|
||||
class TestActionLogRobustness(unittest.TestCase):
|
||||
"""#698 original lead: non-dict action_log must not crash validation."""
|
||||
|
||||
MALFORMED = [
|
||||
"git fetch prgs",
|
||||
42,
|
||||
None,
|
||||
{"action": "edit", "path": "x.py", "performed": True, "tracked": True},
|
||||
]
|
||||
|
||||
def test_assess_final_report_validator_survives_malformed_entries(self):
|
||||
result = frv.assess_final_report_validator(
|
||||
_pr703_style_report(),
|
||||
"review_pr",
|
||||
action_log=self.MALFORMED,
|
||||
)
|
||||
self.assertIsInstance(result, dict)
|
||||
rule_ids = {f["rule_id"] for f in result["findings"]}
|
||||
self.assertIn("shared.action_log_malformed", rule_ids)
|
||||
|
||||
def test_malformed_entry_errors_are_sanitized(self):
|
||||
_entries, findings = frv.sanitize_action_log(["secret-token-abc123"])
|
||||
self.assertEqual(len(findings), 1)
|
||||
reason = findings[0]["reason"]
|
||||
self.assertNotIn("secret-token-abc123", reason)
|
||||
self.assertIn("str", reason)
|
||||
self.assertIn("entry 0", reason)
|
||||
|
||||
def test_non_list_action_log_is_reported_not_raised(self):
|
||||
entries, findings = frv.sanitize_action_log("not-a-list")
|
||||
self.assertEqual(entries, [])
|
||||
self.assertEqual(len(findings), 1)
|
||||
self.assertIn("not a list", findings[0]["reason"])
|
||||
|
||||
def test_performed_file_mutations_skips_non_dict_entries(self):
|
||||
performed = rp._performed_file_mutations(
|
||||
["oops", {"action": "edited", "path": "a.py"}]
|
||||
)
|
||||
self.assertEqual(len(performed), 1)
|
||||
self.assertEqual(performed[0]["path"], "a.py")
|
||||
|
||||
def test_schema_entrypoint_survives_string_only_log(self):
|
||||
result = assess_review_final_report_schema(
|
||||
_pr703_style_report(),
|
||||
action_log=["just a string", "another string"],
|
||||
)
|
||||
self.assertIsInstance(result, dict)
|
||||
|
||||
|
||||
class TestLegacyFieldRequirementsRemoved(unittest.TestCase):
|
||||
"""#698: prohibited legacy fields must not be REQUIRED of reports."""
|
||||
|
||||
PROHIBITED = (
|
||||
"Pinned reviewed head",
|
||||
"Scratch worktree used",
|
||||
"Worktree path",
|
||||
"Worktree dirty",
|
||||
"Workspace mutations",
|
||||
"Mutations",
|
||||
"Next",
|
||||
"Issue/PR",
|
||||
"Branch/SHA",
|
||||
"Files changed",
|
||||
)
|
||||
|
||||
def test_review_role_field_table_has_no_prohibited_requirements(self):
|
||||
names = [name for name, _ in rp.HANDOFF_ROLE_FIELDS["review"]]
|
||||
for prohibited in ("Pinned reviewed head", "Scratch worktree used",
|
||||
"Worktree path", "Worktree dirty"):
|
||||
self.assertNotIn(prohibited, names)
|
||||
|
||||
def test_merger_role_field_table_has_no_pinned_reviewed_head(self):
|
||||
names = [name for name, _ in rp.HANDOFF_ROLE_FIELDS["merger"]]
|
||||
self.assertNotIn("Pinned reviewed head", names)
|
||||
|
||||
def test_canonical_report_missing_fields_never_include_prohibited(self):
|
||||
result = rp.assess_controller_handoff(
|
||||
_pr703_style_report(), role="review"
|
||||
)
|
||||
for prohibited in self.PROHIBITED:
|
||||
self.assertNotIn(prohibited, result.get("missing_fields") or [])
|
||||
|
||||
def test_canonical_pr703_report_satisfies_required_fields(self):
|
||||
result = rp.assess_controller_handoff(
|
||||
_pr703_style_report(), role="review"
|
||||
)
|
||||
self.assertEqual(result.get("missing_fields") or [], [])
|
||||
self.assertEqual(result.get("verdict"), "complete")
|
||||
|
||||
|
||||
class TestBlockedReportAccepted(unittest.TestCase):
|
||||
"""#698: blocked run with no reviewed head / verdict is legitimate."""
|
||||
|
||||
def test_stale_head_proof_waived_before_validation(self):
|
||||
result = pwl.assess_reviewer_stale_head_final_report(
|
||||
_blocked_preflight_report()
|
||||
)
|
||||
self.assertTrue(result["proven"])
|
||||
self.assertEqual(result.get("phase"), "blocked_before_validation")
|
||||
|
||||
def test_blocked_report_passes_schema_validation(self):
|
||||
result = assess_review_final_report_schema(_blocked_preflight_report())
|
||||
blocking = [
|
||||
f for f in result["findings"] if f["severity"] == "block"
|
||||
]
|
||||
self.assertEqual(blocking, [], blocking)
|
||||
|
||||
def test_verdict_phase_still_demands_approval_head_proof(self):
|
||||
report = _blocked_preflight_report().replace(
|
||||
"- Review decision: none",
|
||||
"- Review decision: approve",
|
||||
).replace(
|
||||
"- Candidate head SHA: none",
|
||||
f"- Candidate head SHA: {REVIEWED_HEAD}",
|
||||
)
|
||||
result = pwl.assess_reviewer_stale_head_final_report(report)
|
||||
self.assertFalse(result["proven"])
|
||||
joined = " ".join(result["reasons"])
|
||||
self.assertIn("before approval", joined)
|
||||
|
||||
def test_merge_phase_still_demands_merge_head_proof(self):
|
||||
report = _pr703_style_report().replace(
|
||||
"- Merge result: none",
|
||||
"- Merge result: merged",
|
||||
)
|
||||
result = pwl.assess_reviewer_stale_head_final_report(report)
|
||||
self.assertFalse(result["proven"])
|
||||
self.assertIn(
|
||||
"final live head SHA before merge not stated",
|
||||
result["reasons"],
|
||||
)
|
||||
|
||||
def test_validation_phase_demands_push_disclosure(self):
|
||||
report = _pr703_style_report().replace(
|
||||
"- Pushes occurred during validation: no\n", ""
|
||||
)
|
||||
result = pwl.assess_reviewer_stale_head_final_report(report)
|
||||
self.assertFalse(result["proven"])
|
||||
self.assertIn(
|
||||
"whether push occurred during validation not stated",
|
||||
result["reasons"],
|
||||
)
|
||||
|
||||
|
||||
class TestLeaseReleaseVsPostMergeCleanup(unittest.TestCase):
|
||||
"""#698 (PR #703 review reproduction): lease release is not cleanup."""
|
||||
|
||||
def test_lease_release_cleanup_mutations_do_not_demand_checklist(self):
|
||||
result = pmcp.assess_post_merge_cleanup_proof(_pr703_style_report())
|
||||
self.assertFalse(result["block"], result["reasons"])
|
||||
|
||||
def test_release_tool_name_alone_is_recognized(self):
|
||||
report = _pr703_style_report(
|
||||
cleanup_mutations="gitea_release_reviewer_pr_lease comment 11244"
|
||||
)
|
||||
result = pmcp.assess_post_merge_cleanup_proof(report)
|
||||
self.assertFalse(result["block"], result["reasons"])
|
||||
|
||||
def test_substantive_non_lease_cleanup_still_demands_checklist(self):
|
||||
report = _pr703_style_report(
|
||||
cleanup_mutations="deleted stale scratch directory manually"
|
||||
)
|
||||
result = pmcp.assess_post_merge_cleanup_proof(report)
|
||||
self.assertTrue(result["block"])
|
||||
|
||||
def test_remote_branch_delete_claims_still_demand_full_proof(self):
|
||||
report = _pr703_style_report(
|
||||
cleanup_mutations="gitea_delete_branch removed the remote branch"
|
||||
)
|
||||
result = pmcp.assess_post_merge_cleanup_proof(report)
|
||||
self.assertTrue(result["block"])
|
||||
self.assertTrue(
|
||||
any("remote branch deletion missing" in r for r in result["reasons"])
|
||||
)
|
||||
|
||||
def test_full_schema_run_accepts_lease_release_report(self):
|
||||
result = assess_review_final_report_schema(_pr703_style_report())
|
||||
lease_cleanup_blocks = [
|
||||
f for f in result["findings"]
|
||||
if f["rule_id"] == "reviewer.post_merge_cleanup_proof"
|
||||
]
|
||||
self.assertEqual(lease_cleanup_blocks, [], lease_cleanup_blocks)
|
||||
|
||||
|
||||
class TestStructuredProofRecognition(unittest.TestCase):
|
||||
"""#698: structured workflow-load and validation proof must be accepted."""
|
||||
|
||||
def test_key_value_workflow_proof_recognized(self):
|
||||
findings = frv._rule_reviewer_workflow_load_boundary(
|
||||
_pr703_style_report()
|
||||
)
|
||||
self.assertEqual(findings, [], findings)
|
||||
|
||||
def test_colon_form_workflow_proof_still_recognized(self):
|
||||
report = _pr703_style_report().replace(
|
||||
"- Workflow-load helper result: workflow_hash=da045d1e1f1f "
|
||||
"boundary_status=clean",
|
||||
"- Workflow-load helper result: workflow_hash: da045d1e1f1f, "
|
||||
"boundary_status: clean",
|
||||
)
|
||||
findings = frv._rule_reviewer_workflow_load_boundary(report)
|
||||
self.assertEqual(findings, [], findings)
|
||||
|
||||
def test_incomplete_structured_proof_still_blocks(self):
|
||||
report = _pr703_style_report().replace(
|
||||
"workflow_hash=da045d1e1f1f boundary_status=clean",
|
||||
"workflow_hash=da045d1e1f1f",
|
||||
)
|
||||
findings = frv._rule_reviewer_workflow_load_boundary(report)
|
||||
self.assertTrue(findings)
|
||||
self.assertIn("boundary_status", findings[0]["reason"])
|
||||
|
||||
def test_validation_counts_accepted_as_pass_proof(self):
|
||||
# "Validation: focused 50 passed; ..." must satisfy the reviewed-head
|
||||
# validation-proof rule (PR #703 reproduction).
|
||||
result = assess_review_final_report_schema(_pr703_style_report())
|
||||
head_blocks = [
|
||||
f for f in result["findings"]
|
||||
if f["rule_id"] == "reviewer.reviewed_head_without_validation"
|
||||
]
|
||||
self.assertEqual(head_blocks, [], head_blocks)
|
||||
|
||||
|
||||
class TestAuthoritativeMutationInference(unittest.TestCase):
|
||||
"""#698: review mutations inferred only from authoritative evidence."""
|
||||
|
||||
def test_read_only_entries_do_not_imply_mutations(self):
|
||||
report = "## Controller Handoff\n- Mutations: none\n"
|
||||
findings = frv._rule_reviewer_vague_mutations_none(
|
||||
report,
|
||||
action_log=[
|
||||
{"action": "gitea_view_pr"},
|
||||
{"action": "gitea_get_pr_review_feedback", "performed": False},
|
||||
],
|
||||
)
|
||||
self.assertEqual(findings, [], findings)
|
||||
|
||||
def test_performed_mutation_still_blocks_vague_none(self):
|
||||
report = "## Controller Handoff\n- Mutations: none\n"
|
||||
findings = frv._rule_reviewer_vague_mutations_none(
|
||||
report,
|
||||
action_log=[{"action": "edit", "path": "a.py", "performed": True}],
|
||||
)
|
||||
self.assertTrue(findings)
|
||||
|
||||
def test_gated_rejection_is_not_a_mutation(self):
|
||||
report = "## Controller Handoff\n- Mutations: none\n"
|
||||
findings = frv._rule_reviewer_vague_mutations_none(
|
||||
report,
|
||||
action_log=[
|
||||
{"action": "edit", "path": "a.py", "performed": True,
|
||||
"gated_rejected": True},
|
||||
],
|
||||
)
|
||||
self.assertEqual(findings, [], findings)
|
||||
|
||||
|
||||
class TestValidatorRuleErrorContainment(unittest.TestCase):
|
||||
"""#698: a defective rule fails closed with a sanitized error."""
|
||||
|
||||
def test_rule_exception_becomes_sanitized_block_finding(self):
|
||||
def _boom(report_text):
|
||||
raise ValueError("raw secret detail that must not leak")
|
||||
|
||||
original = frv._RULES_BY_TASK["review_pr"]
|
||||
frv._RULES_BY_TASK["review_pr"] = [_boom]
|
||||
try:
|
||||
result = frv.assess_final_report_validator(
|
||||
"report body", "review_pr"
|
||||
)
|
||||
finally:
|
||||
frv._RULES_BY_TASK["review_pr"] = original
|
||||
self.assertTrue(result["blocked"])
|
||||
finding = next(
|
||||
f for f in result["findings"]
|
||||
if f["rule_id"] == "shared.validator_rule_error"
|
||||
)
|
||||
self.assertNotIn("raw secret detail", finding["reason"])
|
||||
self.assertIn("ValueError", finding["reason"])
|
||||
self.assertIn("_boom", finding["reason"])
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
File diff suppressed because it is too large
Load Diff
@@ -30,17 +30,11 @@ class TestMcpDaemonGuard(unittest.TestCase):
|
||||
# Running under pytest already sets PYTEST_CURRENT_TEST.
|
||||
mcp_daemon_guard.assert_sanctioned_mutation_runtime("pytest")
|
||||
|
||||
def test_test_native_runtime_install_under_pytest(self):
|
||||
def test_mark_sanctioned_bootstrap_allows(self):
|
||||
mcp_daemon_guard.clear_native_runtime_for_tests()
|
||||
mcp_daemon_guard.install_test_native_runtime()
|
||||
self.assertTrue(mcp_daemon_guard.is_native_mcp_transport())
|
||||
self.assertFalse(mcp_daemon_guard.is_production_native_mcp_transport())
|
||||
# Hermetic unit path still passes under pytest.
|
||||
mcp_daemon_guard.mark_sanctioned_daemon(allow_test_bootstrap=True)
|
||||
mcp_daemon_guard.assert_sanctioned_mutation_runtime("daemon")
|
||||
# Production mutation gate rejects test-mode records.
|
||||
with self.assertRaises(mcp_daemon_guard.UnsanctionedRuntimeError) as ctx:
|
||||
mcp_daemon_guard.assert_production_mutation_runtime("gitea_mutation")
|
||||
self.assertIn("Test-mode", str(ctx.exception))
|
||||
self.assertTrue(mcp_daemon_guard.is_native_mcp_transport())
|
||||
|
||||
def test_env_alone_insufficient_when_force_unsanctioned(self):
|
||||
mcp_daemon_guard.clear_native_runtime_for_tests()
|
||||
@@ -93,11 +87,6 @@ class TestMcpDaemonGuard(unittest.TestCase):
|
||||
with self.assertRaises(mcp_daemon_guard.UnsanctionedRuntimeError):
|
||||
gitea_auth.get_auth_header("gitea.prgs.cc")
|
||||
|
||||
def test_no_allow_test_bootstrap_public_parameter(self):
|
||||
"""Production mark must not accept allow_test_bootstrap (#695)."""
|
||||
sig = __import__("inspect").signature(mcp_daemon_guard.mark_sanctioned_daemon)
|
||||
self.assertNotIn("allow_test_bootstrap", sig.parameters)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
|
||||
@@ -957,20 +957,17 @@ class TestControllerHandoff(unittest.TestCase):
|
||||
if not line.startswith("- Workspace mutations:"))
|
||||
result = assess_controller_handoff(review_base, role="review")
|
||||
self.assertEqual(result["verdict"], "incomplete")
|
||||
# #698: the canonical schema forbids the legacy fields, so the
|
||||
# validator must demand the canonical names instead.
|
||||
self.assertIn("Reviewed head SHA", result["missing_fields"])
|
||||
self.assertIn("Review worktree path", result["missing_fields"])
|
||||
self.assertIn("Pinned reviewed head", result["missing_fields"])
|
||||
self.assertIn("Worktree path", result["missing_fields"])
|
||||
self.assertIn("Merge result", result["missing_fields"])
|
||||
for legacy in ("Pinned reviewed head", "Scratch worktree used"):
|
||||
self.assertNotIn(legacy, result["missing_fields"])
|
||||
|
||||
complete = review_base + "\n" + "\n".join([
|
||||
"- Selected PR: #999",
|
||||
"- Reviewer eligibility: passed",
|
||||
"- Reviewed head SHA: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
|
||||
"- Review worktree path: /repo/branches/review-pr-999",
|
||||
"- Review worktree dirty before validation: no",
|
||||
"- Pinned reviewed head: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
|
||||
"- Worktree path: /repo/branches/review-pr-999",
|
||||
"- Worktree dirty: no",
|
||||
"- Scratch worktree used: yes (/repo/branches/review-pr-999)",
|
||||
"- Unrelated local mutations: none",
|
||||
"- Review decision: approve",
|
||||
"- Merge result: merged",
|
||||
@@ -1128,9 +1125,10 @@ class TestReviewHandoffPreciseMutationCategories(unittest.TestCase):
|
||||
"- Safety: no self-review; no self-merge; no secrets",
|
||||
"- Selected PR: #999",
|
||||
"- Reviewer eligibility: passed",
|
||||
"- Reviewed head SHA: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
|
||||
"- Pinned reviewed head: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
|
||||
"- Worktree path: /repo/branches/review-pr-999",
|
||||
"- Worktree dirty: no",
|
||||
"- Scratch worktree used: yes (/repo/branches/review-pr-999)",
|
||||
"- Unrelated local mutations: none",
|
||||
"- Review decision: approve",
|
||||
"- Merge result: none",
|
||||
|
||||
Reference in New Issue
Block a user