fix: resolve conflicts for PR #373 against latest master
This commit is contained in:
@@ -1052,6 +1052,15 @@ def _prs_from_list_response(list_prs_response: list | dict | None) -> list | Non
|
||||
return None
|
||||
|
||||
|
||||
# ── Linked-issue consistency (Issue #314) ────────────────────────────────────
|
||||
#
|
||||
# Stale linked-issue text from a previous PR must not leak into a final
|
||||
# report: the "Linked issue status" field must match the issue(s) the
|
||||
# selected PR actually links, verified live this session, and no other
|
||||
# "Issue #N" mention may appear unless it is a verified linked issue.
|
||||
|
||||
_ISSUE_MENTION_RE = re.compile(r"\bissue\s+#(\d+)", re.IGNORECASE)
|
||||
|
||||
# ── Workspace-vs-worktree mutation consistency (Issue #313) ──────────────────
|
||||
#
|
||||
# A worktree reset/checkout/clean is a workspace mutation even when the
|
||||
@@ -1092,6 +1101,68 @@ def _report_labeled_fields(report_text):
|
||||
return fields
|
||||
|
||||
|
||||
def _issue_numbers_mentioned(text):
|
||||
"""Return the set of ints referenced as 'Issue #N' in *text*."""
|
||||
return {int(n) for n in _ISSUE_MENTION_RE.findall(text or "")}
|
||||
|
||||
|
||||
def assess_linked_issue_consistency(report_text, *, selected_pr=None,
|
||||
linked_issues=None):
|
||||
"""#314: linked-issue status must match the selected PR, live-verified.
|
||||
|
||||
*linked_issues* is the list of issue numbers the selected PR was
|
||||
live-verified to link this session, or None when no live verification
|
||||
happened. Without live proof the report may only say the status was
|
||||
not verified; with proof, the ``Linked issue status`` field must name
|
||||
every linked issue and no stale issue number may appear anywhere in
|
||||
the report.
|
||||
|
||||
Returns {'complete', 'downgraded', 'reasons'}; fails closed.
|
||||
"""
|
||||
fields = _report_labeled_fields(report_text)
|
||||
status_value = fields.get("linked issue status")
|
||||
|
||||
reasons = []
|
||||
|
||||
if status_value is None:
|
||||
reasons.append(
|
||||
"final report missing 'Linked issue status' field for the "
|
||||
"selected PR"
|
||||
)
|
||||
elif linked_issues is None:
|
||||
if not status_value.strip().lower().startswith("not verified"):
|
||||
reasons.append(
|
||||
"linked issue status claimed without live proof; report "
|
||||
"'Linked issue status: not verified in this session' or "
|
||||
"verify the linked issue live"
|
||||
)
|
||||
else:
|
||||
allowed = set(linked_issues)
|
||||
status_mentions = _issue_numbers_mentioned(status_value)
|
||||
for missing in sorted(allowed - status_mentions):
|
||||
reasons.append(
|
||||
f"linked issue #{missing} of selected PR "
|
||||
f"#{selected_pr} not reported in 'Linked issue status'"
|
||||
)
|
||||
for stale in sorted(status_mentions - allowed):
|
||||
reasons.append(
|
||||
f"'Linked issue status' names issue #{stale}, which is "
|
||||
f"not a live-verified linked issue of selected PR "
|
||||
f"#{selected_pr}"
|
||||
)
|
||||
for stale in sorted(_issue_numbers_mentioned(report_text) - allowed):
|
||||
reasons.append(
|
||||
f"stale issue #{stale} mentioned in final report but not "
|
||||
f"live-verified as linked to selected PR #{selected_pr}"
|
||||
)
|
||||
|
||||
return {
|
||||
"complete": not reasons,
|
||||
"downgraded": bool(reasons),
|
||||
"reasons": reasons,
|
||||
}
|
||||
|
||||
|
||||
def _field_claims_none(fields, label):
|
||||
"""True when *label* is present and its value is empty or 'none...'."""
|
||||
value = fields.get(label)
|
||||
@@ -1286,6 +1357,102 @@ def assess_reconciliation_handoff(report_text, observed_commands=None):
|
||||
}
|
||||
|
||||
|
||||
# ── Already-landed report wording (Issue #298) ───────────────────────────────
|
||||
#
|
||||
# An already-landed PR is reconciliation-only: it must never be called
|
||||
# eligible, its head SHA must never be called reviewed, and the legacy
|
||||
# eligible/reviewed/scratch-worktree handoff fields must not appear.
|
||||
# Reviewed-head claims in any report require validation + diff review to
|
||||
# have actually passed.
|
||||
|
||||
ALREADY_LANDED_FORBIDDEN_PHRASES = (
|
||||
"oldest eligible pr",
|
||||
"next eligible pr",
|
||||
"pinned reviewed head",
|
||||
"scratch worktree used",
|
||||
)
|
||||
|
||||
ALREADY_LANDED_ELIGIBILITY_CLASS = "ALREADY_LANDED_RECONCILE_REQUIRED"
|
||||
|
||||
|
||||
def assess_already_landed_report_wording(report_text, *, already_landed,
|
||||
review_validated=False):
|
||||
"""#298: reject eligible/reviewed wording for already-landed PRs.
|
||||
|
||||
*already_landed* states whether the already-landed gate fired for the
|
||||
selected PR. *review_validated* states whether validation and diff
|
||||
review actually passed this session; only then may a reviewed head
|
||||
SHA be populated in a non-already-landed report.
|
||||
|
||||
Returns {'complete', 'downgraded', 'reasons'}; fails closed.
|
||||
"""
|
||||
text_lower = (report_text or "").lower()
|
||||
fields = _report_labeled_fields(report_text)
|
||||
reasons = []
|
||||
|
||||
reviewed_head = fields.get("reviewed head sha")
|
||||
reviewed_head_populated = bool(
|
||||
reviewed_head and not reviewed_head.strip().lower().startswith("none")
|
||||
)
|
||||
pinned_head_present = "pinned reviewed head" in fields
|
||||
|
||||
if already_landed:
|
||||
for phrase in ALREADY_LANDED_FORBIDDEN_PHRASES:
|
||||
if phrase in text_lower:
|
||||
reasons.append(
|
||||
f"already-landed report must not use '{phrase}'; the PR "
|
||||
"is reconciliation-only, not review/merge eligible"
|
||||
)
|
||||
|
||||
eligibility = fields.get("eligibility class", "")
|
||||
if ALREADY_LANDED_ELIGIBILITY_CLASS not in eligibility.upper():
|
||||
reasons.append(
|
||||
"already-landed report missing 'Eligibility class: "
|
||||
f"{ALREADY_LANDED_ELIGIBILITY_CLASS}'"
|
||||
)
|
||||
|
||||
for required in ("oldest open pr requiring action",
|
||||
"candidate head sha"):
|
||||
if required not in fields:
|
||||
reasons.append(
|
||||
f"already-landed report missing '{required}' field"
|
||||
)
|
||||
|
||||
if "reviewed head sha" not in fields:
|
||||
reasons.append(
|
||||
"already-landed report must state 'Reviewed head SHA: none'"
|
||||
)
|
||||
elif reviewed_head_populated:
|
||||
reasons.append(
|
||||
"already-landed report must not claim a reviewed head SHA; "
|
||||
"no validation or diff review passed for this PR"
|
||||
)
|
||||
|
||||
worktree_used = fields.get("review worktree used", "")
|
||||
if worktree_used.strip().lower() not in ("false", "no"):
|
||||
reasons.append(
|
||||
"already-landed report must state 'Review worktree used: "
|
||||
"false'"
|
||||
)
|
||||
elif not review_validated:
|
||||
if pinned_head_present:
|
||||
reasons.append(
|
||||
"'Pinned reviewed head' populated before validation and "
|
||||
"diff review passed"
|
||||
)
|
||||
if reviewed_head_populated:
|
||||
reasons.append(
|
||||
"reviewed head SHA populated before validation and diff "
|
||||
"review passed"
|
||||
)
|
||||
|
||||
return {
|
||||
"complete": not reasons,
|
||||
"downgraded": bool(reasons),
|
||||
"reasons": reasons,
|
||||
}
|
||||
|
||||
|
||||
def assess_role_boundary(proof=None, *, task_role=None, namespaces_used=None,
|
||||
justification=None):
|
||||
"""Assess reviewer/author role separation for blind queue workflows.
|
||||
@@ -1466,6 +1633,7 @@ def build_final_report(checkout_proof, inventory, validation, contamination,
|
||||
report_text=None, review_decision_lock=None,
|
||||
controller_handoff=None, capability_proof=None,
|
||||
sweep_proof=None, worktree_proof=None,
|
||||
validation_environment=None,
|
||||
queue_ordering=None,
|
||||
baseline_validation=None, project_root=None):
|
||||
"""Required behavior 6 + acceptance criteria: one report, distinct proofs.
|
||||
@@ -1494,6 +1662,22 @@ def build_final_report(checkout_proof, inventory, validation, contamination,
|
||||
)
|
||||
|
||||
empty_queue_report = assess_empty_queue_report(report_text)
|
||||
if validation_environment is None and report_text:
|
||||
validation_env_proof = assess_validation_environment_proof(
|
||||
report_text=report_text,
|
||||
)
|
||||
elif validation_environment is not None:
|
||||
validation_env_proof = assess_validation_environment_proof(
|
||||
report_text=report_text,
|
||||
validation_environment=validation_environment,
|
||||
)
|
||||
else:
|
||||
validation_env_proof = {
|
||||
"proven": True,
|
||||
"block": False,
|
||||
"reasons": [],
|
||||
"violations": [],
|
||||
}
|
||||
if queue_ordering is None and report_text:
|
||||
queue_ordering_proof = assess_queue_ordering_proof(
|
||||
report_text=report_text,
|
||||
@@ -1661,6 +1845,11 @@ def build_final_report(checkout_proof, inventory, validation, contamination,
|
||||
"empty-queue report missing or failed trust-gate proof (#198)"
|
||||
)
|
||||
downgrade_reasons.extend(empty_queue_report.get("reasons", []))
|
||||
if not validation_env_proof.get("proven"):
|
||||
downgrade_reasons.append(
|
||||
"validation environment proof missing or failed (#311)"
|
||||
)
|
||||
downgrade_reasons.extend(validation_env_proof.get("reasons", []))
|
||||
if not queue_ordering_proof.get("proven"):
|
||||
downgrade_reasons.append(
|
||||
"queue ordering proof missing or failed (#321)"
|
||||
@@ -1692,11 +1881,13 @@ def build_final_report(checkout_proof, inventory, validation, contamination,
|
||||
# #179: no merge without a proven final live-state recheck.
|
||||
and live_state_proven
|
||||
and worktree_proven
|
||||
and validation_env_proof.get("proven")
|
||||
and queue_ordering_proof.get("proven")
|
||||
and baseline_validation.get("proven")
|
||||
)
|
||||
|
||||
violations = []
|
||||
violations.extend(validation_env_proof.get("violations", []))
|
||||
violations.extend(queue_ordering_proof.get("violations", []))
|
||||
violations.extend(baseline_validation.get("violations", []))
|
||||
if merge_performed and not merge_allowed:
|
||||
@@ -1750,6 +1941,12 @@ def build_final_report(checkout_proof, inventory, validation, contamination,
|
||||
else True
|
||||
),
|
||||
"empty_queue_trust_gate_status": empty_queue_report.get("status"),
|
||||
"validation_environment_proven": bool(
|
||||
validation_env_proof.get("proven")
|
||||
),
|
||||
"validation_environment_violations": list(
|
||||
validation_env_proof.get("violations") or []
|
||||
),
|
||||
"queue_ordering_proven": bool(queue_ordering_proof.get("proven")),
|
||||
"queue_ordering_policy": queue_ordering_proof.get("policy"),
|
||||
"queue_ordering_violations": list(
|
||||
@@ -3366,6 +3563,192 @@ def build_review_mutation_proof(run_log: list[dict]) -> dict:
|
||||
}
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Validation environment proof (#311)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
_VALIDATION_CLAIM_RE = re.compile(
|
||||
r"(?:validation\s+command|pytest\s+(?:executed|passed|failed)|"
|
||||
r"\d+\s+passed|\d+\s+failed|tests?\s+passed)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
_VALIDATION_CMD_LINE_RE = re.compile(
|
||||
r"validation\s+command\s*:\s*(.+)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
_VALIDATION_CWD_LINE_RE = re.compile(
|
||||
r"working\s+directory\s*:\s*(\S+)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
_WHICH_PYTEST_LINE_RE = re.compile(
|
||||
r"which\s+pytest\s*:\s*(.+)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
_PYTEST_VERSION_LINE_RE = re.compile(
|
||||
r"pytest\s+--version\s*:\s*(.+)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
_BARE_PYTEST_CMD_RE = re.compile(
|
||||
r"^(?:python\s+-m\s+)?pytest(?:\s|$)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
_VAGUE_PYTEST_CLAIM_RE = re.compile(
|
||||
r"pytest\s+(?:executed|passed|failed)\b",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
|
||||
def _parse_validation_command(report_text: str) -> str:
|
||||
for line in (report_text or "").splitlines():
|
||||
match = _VALIDATION_CMD_LINE_RE.search(line)
|
||||
if match:
|
||||
return match.group(1).strip().rstrip(".")
|
||||
return ""
|
||||
|
||||
|
||||
def _parse_validation_cwd(report_text: str) -> str:
|
||||
for line in (report_text or "").splitlines():
|
||||
match = _VALIDATION_CWD_LINE_RE.search(line)
|
||||
if match:
|
||||
return match.group(1).strip().rstrip(",.;")
|
||||
return ""
|
||||
|
||||
|
||||
def _is_bare_pytest_command(command: str) -> bool:
|
||||
text = (command or "").strip()
|
||||
if not text:
|
||||
return False
|
||||
if "/" in text or "\\" in text:
|
||||
return False
|
||||
return bool(_BARE_PYTEST_CMD_RE.match(text))
|
||||
|
||||
|
||||
def assess_validation_environment_proof(
|
||||
*,
|
||||
report_text: str | None = None,
|
||||
validation_environment: dict | None = None,
|
||||
) -> dict:
|
||||
"""#311: reviewer reports must include exact validation command/environment."""
|
||||
text = report_text or ""
|
||||
lower = text.lower()
|
||||
env = validation_environment or {}
|
||||
reasons: list[str] = []
|
||||
violations: list[str] = []
|
||||
|
||||
claims_validation = bool(_VALIDATION_CLAIM_RE.search(text))
|
||||
if not claims_validation and not env.get("command"):
|
||||
return {
|
||||
"proven": True,
|
||||
"block": False,
|
||||
"claims_validation": False,
|
||||
"reasons": [],
|
||||
"violations": [],
|
||||
"safe_next_action": "proceed",
|
||||
}
|
||||
|
||||
command = (env.get("command") or _parse_validation_command(text)).strip()
|
||||
working_directory = (
|
||||
env.get("working_directory") or env.get("cwd")
|
||||
or _parse_validation_cwd(text)
|
||||
).strip()
|
||||
|
||||
if not command:
|
||||
reasons.append(
|
||||
"validation result claimed without exact validation command (#311)"
|
||||
)
|
||||
elif _VAGUE_PYTEST_CLAIM_RE.search(text) and command == "":
|
||||
violations.append(
|
||||
"vague pytest summary without exact validation command (#311)"
|
||||
)
|
||||
|
||||
if not working_directory:
|
||||
reasons.append(
|
||||
"validation result claimed without working directory (#311)"
|
||||
)
|
||||
|
||||
has_result = any(
|
||||
token in lower
|
||||
for token in ("passed", "failed", "skipped", "error")
|
||||
) or any(
|
||||
env.get(key) is not None
|
||||
for key in ("passed", "failed", "skipped", "result")
|
||||
)
|
||||
if not has_result:
|
||||
reasons.append(
|
||||
"validation result claimed without pass/fail result evidence (#311)"
|
||||
)
|
||||
|
||||
if command and _is_bare_pytest_command(command):
|
||||
which_pytest = (
|
||||
(env.get("which_pytest") or env.get("executable_path") or "")
|
||||
.strip()
|
||||
)
|
||||
if not which_pytest:
|
||||
for line in text.splitlines():
|
||||
match = _WHICH_PYTEST_LINE_RE.search(line)
|
||||
if match:
|
||||
which_pytest = match.group(1).strip()
|
||||
break
|
||||
if not which_pytest:
|
||||
reasons.append(
|
||||
"bare pytest command requires which-pytest/executable proof (#311)"
|
||||
)
|
||||
|
||||
pytest_version = (env.get("pytest_version") or "").strip()
|
||||
if not pytest_version:
|
||||
for line in text.splitlines():
|
||||
match = _PYTEST_VERSION_LINE_RE.search(line)
|
||||
if match:
|
||||
pytest_version = match.group(1).strip()
|
||||
break
|
||||
if not pytest_version:
|
||||
reasons.append(
|
||||
"bare pytest command requires pytest --version proof (#311)"
|
||||
)
|
||||
|
||||
venv_resolved = env.get("venv_resolved")
|
||||
if venv_resolved is None:
|
||||
venv_resolved = any(
|
||||
marker in lower
|
||||
for marker in (
|
||||
"project venv",
|
||||
"venv/bin/pytest",
|
||||
"resolves to the project venv",
|
||||
"venv resolved: yes",
|
||||
)
|
||||
)
|
||||
if not venv_resolved and which_pytest and "venv" not in which_pytest:
|
||||
reasons.append(
|
||||
"bare pytest command requires proof whether executable "
|
||||
"resolves to the project venv (#311)"
|
||||
)
|
||||
|
||||
proven = not reasons and not violations
|
||||
return {
|
||||
"proven": proven,
|
||||
"block": bool(violations),
|
||||
"claims_validation": True,
|
||||
"command": command or None,
|
||||
"working_directory": working_directory or None,
|
||||
"reasons": reasons,
|
||||
"violations": violations,
|
||||
"safe_next_action": (
|
||||
"report exact validation command, working directory, result, and "
|
||||
"for bare pytest also which-pytest, pytest --version, and venv proof"
|
||||
if not proven
|
||||
else "proceed"
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Reviewer queue ordering proof (#321)
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -3696,6 +4079,279 @@ def assess_reviewer_baseline_validation_proof(
|
||||
}
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Already-landed review gate (#292)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
ALREADY_LANDED_STATE = "ALREADY_LANDED_RECONCILE_REQUIRED"
|
||||
|
||||
ALREADY_LANDED_HANDOFF_FIELDS = (
|
||||
"PR number/title",
|
||||
"candidate head SHA",
|
||||
"target branch",
|
||||
"target branch SHA",
|
||||
"ancestor proof",
|
||||
"linked issue status",
|
||||
"recommended reconciliation action",
|
||||
"capability proof for close/comment mutations",
|
||||
)
|
||||
|
||||
_FORBIDDEN_LANDED_STATES_RE = re.compile(
|
||||
r"review decision\s*:\s*approved?\b|"
|
||||
r"merge result\s*:\s*merged\b|"
|
||||
r"\bready[_ ]to[_ ]merge\b|"
|
||||
r"\bmerge[d]?\s*:\s*success\b",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
|
||||
def assess_already_landed_review_gate(
|
||||
*,
|
||||
pr_number: int | None,
|
||||
candidate_head_sha: str | None,
|
||||
target_branch: str | None,
|
||||
target_branch_sha: str | None,
|
||||
head_is_ancestor_of_target: bool | None,
|
||||
live_head_sha: str | None = None,
|
||||
real_blocker: bool = False,
|
||||
mergeable: bool | None = None,
|
||||
) -> dict:
|
||||
"""#292: hard gate before any review mutation on an already-landed PR.
|
||||
|
||||
Runs after PR selection and head pinning, before approval, request-
|
||||
changes, or the merge API. *head_is_ancestor_of_target* is the result
|
||||
of an ancestry check of *candidate_head_sha* against the freshly
|
||||
fetched target branch at *target_branch_sha* (e.g. ``git merge-base
|
||||
--is-ancestor``). ``None`` means the check was not run — the gate then
|
||||
fails closed.
|
||||
|
||||
*live_head_sha*, when provided, must equal *candidate_head_sha*; a
|
||||
changed head invalidates the pinned ancestry result until re-checked.
|
||||
|
||||
*mergeable* is accepted for caller convenience but never consulted:
|
||||
conflict/mergeability handling is a separate gate.
|
||||
"""
|
||||
del mergeable # ancestry gate only; mergeability is a separate gate
|
||||
reasons: list[str] = []
|
||||
|
||||
if not isinstance(pr_number, int) or pr_number <= 0:
|
||||
reasons.append("PR number missing or invalid (#292)")
|
||||
if not _FULL_SHA.match((candidate_head_sha or "").strip()):
|
||||
reasons.append(
|
||||
"candidate head SHA is not a full 40-hex commit SHA (#292)"
|
||||
)
|
||||
if not (target_branch or "").strip():
|
||||
reasons.append("target branch missing (#292)")
|
||||
if not _FULL_SHA.match((target_branch_sha or "").strip()):
|
||||
reasons.append(
|
||||
"target branch SHA is not a full 40-hex commit SHA; fetch the "
|
||||
"target branch and record its SHA before the ancestry check "
|
||||
"(#292)"
|
||||
)
|
||||
if live_head_sha is not None and candidate_head_sha and (
|
||||
live_head_sha.strip() != candidate_head_sha.strip()
|
||||
):
|
||||
reasons.append(
|
||||
"PR head changed since the ancestry check was pinned; re-fetch "
|
||||
"and re-run the already-landed gate (#292)"
|
||||
)
|
||||
if head_is_ancestor_of_target is None:
|
||||
reasons.append(
|
||||
"ancestry of the PR head against the target branch was not "
|
||||
"checked; the already-landed gate must run before any review "
|
||||
"mutation (#292)"
|
||||
)
|
||||
|
||||
if reasons:
|
||||
return {
|
||||
"state": "GATE_NOT_PROVEN",
|
||||
"approve_allowed": False,
|
||||
"request_changes_allowed": False,
|
||||
"merge_api_allowed": False,
|
||||
"reconciliation_handoff_required": False,
|
||||
"required_handoff_fields": (),
|
||||
"reasons": reasons,
|
||||
"safe_next_action": (
|
||||
"fetch the target branch, pin the live PR head, run the "
|
||||
"ancestry check, then re-run this gate"
|
||||
),
|
||||
}
|
||||
|
||||
if head_is_ancestor_of_target:
|
||||
return {
|
||||
"state": ALREADY_LANDED_STATE,
|
||||
"approve_allowed": False,
|
||||
"request_changes_allowed": bool(real_blocker),
|
||||
"merge_api_allowed": False,
|
||||
"reconciliation_handoff_required": True,
|
||||
"required_handoff_fields": ALREADY_LANDED_HANDOFF_FIELDS,
|
||||
"reasons": [
|
||||
f"PR #{pr_number} head {candidate_head_sha} is already an "
|
||||
f"ancestor of {target_branch} @ {target_branch_sha}; the PR "
|
||||
"is reconciliation-only (#292)"
|
||||
],
|
||||
"safe_next_action": (
|
||||
"stop before review mutation and emit an "
|
||||
f"{ALREADY_LANDED_STATE} reconciliation handoff; any PR/issue "
|
||||
"close or comment requires exact capability proof"
|
||||
),
|
||||
}
|
||||
|
||||
return {
|
||||
"state": "NORMAL_REVIEW_CANDIDATE",
|
||||
"approve_allowed": True,
|
||||
"request_changes_allowed": True,
|
||||
"merge_api_allowed": True,
|
||||
"reconciliation_handoff_required": False,
|
||||
"required_handoff_fields": (),
|
||||
"reasons": [],
|
||||
"safe_next_action": "proceed with the normal review workflow gates",
|
||||
}
|
||||
|
||||
|
||||
def assess_already_landed_report_state(
|
||||
report_text: str | None,
|
||||
*,
|
||||
gate_fired: bool,
|
||||
) -> dict:
|
||||
"""#292: reject APPROVED/MERGED/READY_TO_MERGE after the gate fired.
|
||||
|
||||
*gate_fired* comes from the session's own gate result, so a report
|
||||
that omits the already-landed markers entirely still fails closed —
|
||||
unlike the text-only #327 wording rules this does not depend on the
|
||||
report admitting the PR was already landed.
|
||||
"""
|
||||
if not gate_fired:
|
||||
return {"complete": True, "block": False, "reasons": []}
|
||||
|
||||
text = report_text or ""
|
||||
reasons: list[str] = []
|
||||
|
||||
if _FORBIDDEN_LANDED_STATES_RE.search(text):
|
||||
reasons.append(
|
||||
"report claims APPROVED/MERGED/READY_TO_MERGE although the "
|
||||
"already-landed gate fired (#292)"
|
||||
)
|
||||
if ALREADY_LANDED_STATE.lower() not in text.lower():
|
||||
reasons.append(
|
||||
f"report must state {ALREADY_LANDED_STATE} when the "
|
||||
"already-landed gate fired (#292)"
|
||||
)
|
||||
|
||||
return {
|
||||
"complete": not reasons,
|
||||
"block": bool(reasons),
|
||||
"reasons": reasons,
|
||||
}
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Full-suite failure approval gate (#323)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def assess_full_suite_failure_approval_gate(
|
||||
*,
|
||||
review_decision: str,
|
||||
full_suite_passed: bool | None,
|
||||
baseline_validation: dict | None = None,
|
||||
baseline_proof: dict | None = None,
|
||||
report_text: str | None = None,
|
||||
project_root: str | None = None,
|
||||
) -> dict:
|
||||
"""#323: approving a PR whose full suite fails requires baseline proof.
|
||||
|
||||
Default action on a full-suite failure is REQUEST_CHANGES. Approval is
|
||||
allowed only when the #325 baseline proof passes in full (branches/
|
||||
worktree, pinned SHAs, matching failure signatures) and the extra #323
|
||||
fields prove the failures are pre-existing: ``pr_suite_command``,
|
||||
``baseline_suite_command``, ``new_tests_passed``, and a non-empty
|
||||
``unrelated_explanation``.
|
||||
|
||||
*review_decision* is the decision the workflow intends to submit; only
|
||||
``approve`` can be blocked. ``block`` is True when an approval was
|
||||
requested that the proofs do not allow.
|
||||
"""
|
||||
decision = (review_decision or "").strip().lower().replace("-", "_")
|
||||
wants_approval = decision == "approve"
|
||||
reasons: list[str] = []
|
||||
|
||||
if full_suite_passed is True:
|
||||
return {
|
||||
"approve_allowed": True,
|
||||
"block": False,
|
||||
"default_action": "proceed",
|
||||
"reasons": [],
|
||||
}
|
||||
|
||||
default_action = "request_changes"
|
||||
|
||||
if full_suite_passed is None:
|
||||
reasons.append(
|
||||
"full-suite result not proven; approval requires a recorded "
|
||||
"full-suite command and result (#323)"
|
||||
)
|
||||
else:
|
||||
if baseline_validation is None:
|
||||
baseline_validation = assess_reviewer_baseline_validation_proof(
|
||||
baseline_proof=baseline_proof,
|
||||
report_text=report_text,
|
||||
project_root=project_root,
|
||||
)
|
||||
proof = baseline_proof or {}
|
||||
|
||||
if not proof:
|
||||
reasons.append(
|
||||
"full suite failed but no baseline proof was provided; "
|
||||
"default action is REQUEST_CHANGES (#323)"
|
||||
)
|
||||
if not baseline_validation.get("proven"):
|
||||
reasons.append(
|
||||
"baseline validation proof missing or failed (#323/#325)"
|
||||
)
|
||||
reasons.extend(baseline_validation.get("reasons", []))
|
||||
|
||||
if proof:
|
||||
worktree = (proof.get("worktree_path") or "").strip()
|
||||
if not _path_under_branches(worktree, project_root):
|
||||
reasons.append(
|
||||
"baseline comparison must run in a clean baseline "
|
||||
"worktree under branches/, not the main checkout (#323)"
|
||||
)
|
||||
if not (proof.get("pr_suite_command") or "").strip():
|
||||
reasons.append(
|
||||
"PR full-suite command/result missing from baseline "
|
||||
"proof (#323)"
|
||||
)
|
||||
if not (proof.get("baseline_suite_command") or "").strip():
|
||||
reasons.append(
|
||||
"baseline full-suite command/result missing from "
|
||||
"baseline proof (#323)"
|
||||
)
|
||||
if proof.get("new_tests_passed") is not True:
|
||||
reasons.append(
|
||||
"proof that new/changed tests passed is missing (#323)"
|
||||
)
|
||||
if not (proof.get("unrelated_explanation") or "").strip():
|
||||
reasons.append(
|
||||
"explanation why failures are unrelated to the PR is "
|
||||
"missing (#323)"
|
||||
)
|
||||
if proof.get("failure_signatures_match") is not True:
|
||||
reasons.append(
|
||||
"PR and baseline failure signatures do not match; "
|
||||
"request changes (#323)"
|
||||
)
|
||||
|
||||
approve_allowed = not reasons
|
||||
return {
|
||||
"approve_allowed": approve_allowed,
|
||||
"block": wants_approval and not approve_allowed,
|
||||
"default_action": "proceed" if approve_allowed else default_action,
|
||||
"reasons": reasons,
|
||||
}
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Identity disclosure (#305)
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -4174,8 +4830,52 @@ def assess_git_ref_mutation_report(report_text, *, command_log=None):
|
||||
}
|
||||
|
||||
|
||||
def assess_merge_simulation_report(report_text, **kwargs):
|
||||
"""#317: classify local merge simulation as worktree/index mutations."""
|
||||
from reviewer_merge_simulation import assess_merge_simulation_report as _assess
|
||||
|
||||
return _assess(report_text, **kwargs)
|
||||
|
||||
|
||||
def assess_validation_integrity_report(report_text, **kwargs):
|
||||
"""#316: separate official PR-head validation from diagnostic experiments."""
|
||||
from reviewer_validation_integrity import assess_validation_integrity_report as _assess
|
||||
|
||||
return _assess(report_text, **kwargs)
|
||||
|
||||
|
||||
def assess_prior_blocker_skip_proof(report_text, **kwargs):
|
||||
"""#318: require live blocker proof before skipping earlier open PRs."""
|
||||
from reviewer_blocker_skip import assess_prior_blocker_skip_proof as _assess
|
||||
|
||||
return _assess(report_text, **kwargs)
|
||||
|
||||
|
||||
def assess_non_mergeable_skip_proof(report_text, **kwargs):
|
||||
"""#322: require conflict proof when skipping non-mergeable PRs."""
|
||||
from reviewer_mergeability_skip import assess_non_mergeable_skip_proof as _assess
|
||||
|
||||
return _assess(report_text, **kwargs)
|
||||
|
||||
|
||||
def assess_validation_worktree_edit_report(report_text, **kwargs):
|
||||
"""#315: block edits in PR validation worktrees; require diagnostic separation."""
|
||||
from reviewer_validation_worktree_edits import (
|
||||
assess_validation_worktree_edit_report as _assess,
|
||||
)
|
||||
|
||||
return _assess(report_text, **kwargs)
|
||||
|
||||
|
||||
def assess_mutation_categories_report(report_text, **kwargs):
|
||||
"""#319: require precise mutation categories in reviewer controller handoffs."""
|
||||
from reviewer_mutation_categories import assess_mutation_categories_report as _assess
|
||||
|
||||
return _assess(report_text, **kwargs)
|
||||
|
||||
|
||||
def assess_worktree_ownership_report(report_text, **kwargs):
|
||||
"""#312: prove session-owned or safe-reuse worktree before reset/validation."""
|
||||
from reviewer_worktree_ownership import assess_worktree_ownership_report as _assess
|
||||
|
||||
return _assess(report_text, **kwargs)
|
||||
|
||||
@@ -0,0 +1,164 @@
|
||||
"""Prior-blocker skip proof verifier for reviewer queue reports (#318)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
from typing import Any
|
||||
|
||||
_FULL_SHA = re.compile(r"\b[0-9a-f]{40}\b", re.IGNORECASE)
|
||||
_SHORT_SHA = re.compile(r"\b[0-9a-f]{7,39}\b", re.IGNORECASE)
|
||||
_PR_NUMBER_RE = re.compile(r"(?:\bPR\s*#?|#)(\d+)\b", re.IGNORECASE)
|
||||
_BLOCKING_DECISION_RE = re.compile(
|
||||
r"(?:blocking review decision|review decision|blocking decision)\s*:\s*request[_ ]changes|"
|
||||
r"request[_ ]changes",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_BLOCKING_HEAD_RE = re.compile(
|
||||
r"(?:blocking review head(?:\s+sha)?|blocker head(?:\s+sha)?|review head at blocker)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_HEAD_CHANGED_RE = re.compile(
|
||||
r"(?:head (?:changed|unchanged)|head sha (?:changed|unchanged)|"
|
||||
r"head changed (?:after|since) (?:the )?blocker|head unchanged since blocker)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_BLOCKER_REASON_RE = re.compile(
|
||||
r"(?:reason (?:it )?remains blocked|remains blocked because|blocking category)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_LIVE_BLOCKER_PROOF_RE = re.compile(
|
||||
r"(?:blocker revalidated live|live proof|gitea_get_pr_review_feedback|"
|
||||
r"gitea_view_pr|review feedback fetched|current review state)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_BLOCKER_UNVERIFIED_RE = re.compile(r"\bBLOCKER_STATUS_UNVERIFIED\b")
|
||||
|
||||
|
||||
def _pr_section(text: str, pr_number: int) -> str:
|
||||
lines = (text or "").splitlines()
|
||||
chunks: list[str] = []
|
||||
capture = False
|
||||
token = f"#{pr_number}"
|
||||
for line in lines:
|
||||
lower = line.lower()
|
||||
if token in lower or f"pr {pr_number}" in lower or f"pr#{pr_number}" in lower.replace(" ", ""):
|
||||
capture = True
|
||||
chunks.append(line)
|
||||
continue
|
||||
if capture:
|
||||
if _PR_NUMBER_RE.search(line) and token not in line.lower():
|
||||
break
|
||||
if line.strip() == "" and len(chunks) > 3:
|
||||
break
|
||||
chunks.append(line)
|
||||
if chunks:
|
||||
return "\n".join(chunks)
|
||||
return text or ""
|
||||
|
||||
|
||||
def _has_head_sha(text: str, head_sha: str | None) -> bool:
|
||||
if not head_sha:
|
||||
return bool(_FULL_SHA.search(text) or _SHORT_SHA.search(text))
|
||||
head = head_sha.strip().lower()
|
||||
if head in text.lower():
|
||||
return True
|
||||
if len(head) >= 7 and head[:7] in text.lower():
|
||||
return True
|
||||
return bool(_FULL_SHA.search(text))
|
||||
|
||||
|
||||
def assess_prior_blocker_skip_proof(
|
||||
report_text: str,
|
||||
*,
|
||||
skipped_prs: list[dict] | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""Validate live blocker proof for skipped earlier open PRs (#318)."""
|
||||
text = report_text or ""
|
||||
reasons: list[str] = []
|
||||
assessments: list[dict[str, Any]] = []
|
||||
|
||||
for entry in skipped_prs or []:
|
||||
pr_number = entry.get("pr_number")
|
||||
if pr_number is None:
|
||||
reasons.append("skipped PR entry missing pr_number")
|
||||
continue
|
||||
pr_number = int(pr_number)
|
||||
section = _pr_section(text, pr_number)
|
||||
verified = entry.get("blocker_verified")
|
||||
head_changed = entry.get("head_changed_since_blocker")
|
||||
blocking_head = (entry.get("blocking_review_head_sha") or "").strip() or None
|
||||
current_head = (entry.get("head_sha") or "").strip() or None
|
||||
skip_reason = (entry.get("skip_reason") or entry.get("blocking_decision") or "").lower()
|
||||
|
||||
item_reasons: list[str] = []
|
||||
|
||||
if head_changed is True:
|
||||
item_reasons.append(
|
||||
f"PR #{pr_number} head changed after blocker; it cannot be skipped "
|
||||
"based on stale REQUEST_CHANGES"
|
||||
)
|
||||
|
||||
if f"#{pr_number}" not in text.lower() and f"pr {pr_number}" not in text.lower():
|
||||
item_reasons.append(f"skipped PR #{pr_number} not documented in final report")
|
||||
|
||||
if "request_changes" in skip_reason or entry.get("blocking_decision") == "request_changes":
|
||||
if verified is False:
|
||||
if not _BLOCKER_UNVERIFIED_RE.search(section):
|
||||
item_reasons.append(
|
||||
f"PR #{pr_number} blocker proof unavailable; report must classify "
|
||||
"BLOCKER_STATUS_UNVERIFIED"
|
||||
)
|
||||
else:
|
||||
if not _BLOCKING_DECISION_RE.search(section):
|
||||
item_reasons.append(
|
||||
f"PR #{pr_number} skip missing blocking review decision proof"
|
||||
)
|
||||
if not _has_head_sha(section, current_head):
|
||||
item_reasons.append(
|
||||
f"PR #{pr_number} skip missing current head SHA"
|
||||
)
|
||||
if blocking_head and not _BLOCKING_HEAD_RE.search(section):
|
||||
if blocking_head.lower() not in section.lower():
|
||||
item_reasons.append(
|
||||
f"PR #{pr_number} skip missing blocking review head SHA"
|
||||
)
|
||||
if head_changed is False and not _HEAD_CHANGED_RE.search(section):
|
||||
item_reasons.append(
|
||||
f"PR #{pr_number} skip missing head-changed-since-blocker proof"
|
||||
)
|
||||
if not _BLOCKER_REASON_RE.search(section):
|
||||
item_reasons.append(
|
||||
f"PR #{pr_number} skip missing reason-it-remains-blocked"
|
||||
)
|
||||
if not _LIVE_BLOCKER_PROOF_RE.search(section):
|
||||
item_reasons.append(
|
||||
f"PR #{pr_number} skip missing live blocker proof for this session"
|
||||
)
|
||||
|
||||
proven = not item_reasons
|
||||
assessments.append({
|
||||
"pr_number": pr_number,
|
||||
"proven": proven,
|
||||
"classification": (
|
||||
"BLOCKER_STATUS_UNVERIFIED"
|
||||
if verified is False
|
||||
else "BLOCKED_SKIPPED"
|
||||
),
|
||||
"reasons": item_reasons,
|
||||
})
|
||||
reasons.extend(item_reasons)
|
||||
|
||||
proven = not reasons
|
||||
return {
|
||||
"proven": proven,
|
||||
"block": not proven,
|
||||
"downgraded": False,
|
||||
"assessments": assessments,
|
||||
"reasons": reasons,
|
||||
"safe_next_action": (
|
||||
"fetch live review feedback and document blocker proof for each skipped PR, "
|
||||
"or classify BLOCKER_STATUS_UNVERIFIED"
|
||||
if reasons
|
||||
else "proceed"
|
||||
),
|
||||
}
|
||||
@@ -0,0 +1,148 @@
|
||||
"""Merge-simulation worktree mutation verifier for reviewer reports (#317)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
from typing import Any
|
||||
|
||||
_WORKTREE_INDEX_FIELD_RE = re.compile(
|
||||
r"^\s*worktree/index mutations\s*:\s*(.+?)\s*$",
|
||||
re.IGNORECASE | re.MULTILINE,
|
||||
)
|
||||
_READONLY_DIAG_RE = re.compile(
|
||||
r"read[- ]only diagnostics\s*:\s*(.+)$",
|
||||
re.IGNORECASE | re.MULTILINE,
|
||||
)
|
||||
_WORKTREE_PATH_RE = re.compile(
|
||||
r"(?:worktree path|diagnostic worktree|simulation worktree)\s*:",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_PRE_CLEAN_RE = re.compile(
|
||||
r"(?:pre[- ]simulation|before simulation|clean before).*(?:clean|status)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_MERGE_RESULT_RE = re.compile(
|
||||
r"(?:merge result|simulation result|conflict status|merge conflict)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_ABORT_RE = re.compile(
|
||||
r"(?:merge --abort|abort/reset command|abort command|git merge --abort)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_POST_CLEAN_RE = re.compile(
|
||||
r"(?:post[- ]abort|after abort|clean after).*(?:clean|status)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
|
||||
def _command_text(entry: Any) -> str:
|
||||
if isinstance(entry, dict):
|
||||
return str(entry.get("command") or "").strip()
|
||||
return str(entry or "").strip()
|
||||
|
||||
|
||||
def _git_subcommand_line(command: str) -> str | None:
|
||||
tokens = command.split()
|
||||
if not tokens or tokens[0] != "git":
|
||||
return None
|
||||
return " ".join(tokens[1:])
|
||||
|
||||
|
||||
def merge_simulation_commands(command_log: list | None) -> list[str]:
|
||||
"""Return logged commands that perform local merge simulation (#317)."""
|
||||
out: list[str] = []
|
||||
for entry in command_log or []:
|
||||
command = _command_text(entry)
|
||||
rest = _git_subcommand_line(command)
|
||||
if rest is None:
|
||||
continue
|
||||
lower = command.lower()
|
||||
if rest.startswith("merge"):
|
||||
if "--no-commit" in lower or (
|
||||
"--no-ff" in lower and "merge" in lower and "--commit" not in lower
|
||||
):
|
||||
out.append(command)
|
||||
elif "--abort" in lower:
|
||||
out.append(command)
|
||||
return out
|
||||
|
||||
|
||||
def assess_merge_simulation_report(
|
||||
report_text: str,
|
||||
*,
|
||||
command_log: list | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""Reject merge simulation classified as read-only; require worktree proof (#317)."""
|
||||
text = report_text or ""
|
||||
lower = text.lower()
|
||||
reasons: list[str] = []
|
||||
simulation_commands = merge_simulation_commands(command_log)
|
||||
has_abort = any("--abort" in c.lower() for c in simulation_commands)
|
||||
has_simulation = any(
|
||||
"--no-commit" in c.lower() or (
|
||||
"--no-ff" in c.lower() and "--abort" not in c.lower()
|
||||
)
|
||||
for c in simulation_commands
|
||||
)
|
||||
|
||||
if not simulation_commands:
|
||||
return {
|
||||
"proven": True,
|
||||
"block": False,
|
||||
"reasons": [],
|
||||
"simulation_commands": [],
|
||||
"safe_next_action": "proceed",
|
||||
}
|
||||
|
||||
field = _WORKTREE_INDEX_FIELD_RE.search(text)
|
||||
value = (field.group(1).strip().lower() if field else "") or ""
|
||||
if not value or value in {"none", "n/a", "no"}:
|
||||
reasons.append(
|
||||
"merge simulation commands ran but report lacks "
|
||||
"'Worktree/index mutations' entry"
|
||||
)
|
||||
elif "merge" not in value and "simulation" not in value:
|
||||
if not any(cmd.lower() in lower for cmd in simulation_commands):
|
||||
reasons.append(
|
||||
"Worktree/index mutations must document merge simulation commands"
|
||||
)
|
||||
|
||||
readonly = _READONLY_DIAG_RE.search(text)
|
||||
if readonly:
|
||||
readonly_value = readonly.group(1)
|
||||
for command in simulation_commands:
|
||||
if command.lower() in readonly_value.lower():
|
||||
reasons.append(
|
||||
"merge simulation may not be listed under read-only diagnostics"
|
||||
)
|
||||
if has_simulation and "merge simulation" in readonly_value.lower():
|
||||
reasons.append(
|
||||
"merge simulation may not be classified as read-only diagnostics"
|
||||
)
|
||||
|
||||
if has_simulation:
|
||||
if not _WORKTREE_PATH_RE.search(text):
|
||||
reasons.append("merge simulation report missing worktree path")
|
||||
if not _PRE_CLEAN_RE.search(text):
|
||||
reasons.append("merge simulation report missing pre-simulation clean status")
|
||||
if not _MERGE_RESULT_RE.search(text):
|
||||
reasons.append("merge simulation report missing merge result/conflict status")
|
||||
if has_abort or has_simulation:
|
||||
if has_abort and not _ABORT_RE.search(text):
|
||||
reasons.append("merge simulation report missing abort/reset command proof")
|
||||
if has_abort and not _POST_CLEAN_RE.search(text):
|
||||
reasons.append("merge simulation report missing post-abort clean status")
|
||||
|
||||
proven = not reasons
|
||||
return {
|
||||
"proven": proven,
|
||||
"block": not proven,
|
||||
"reasons": reasons,
|
||||
"simulation_commands": simulation_commands,
|
||||
"safe_next_action": (
|
||||
"classify merge simulation under Worktree/index mutations with full "
|
||||
"pre/merge/abort/post-clean proof; never list as read-only diagnostics"
|
||||
if reasons
|
||||
else "proceed"
|
||||
),
|
||||
}
|
||||
@@ -0,0 +1,130 @@
|
||||
"""Precise mutation category verifier for reviewer controller handoffs (#319)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
from typing import Any
|
||||
|
||||
_CONTROLLER_HANDOFF_RE = re.compile(r"controller handoff", re.IGNORECASE)
|
||||
_WORKSPACE_MUTATIONS_RE = re.compile(
|
||||
r"^\s*[-*]?\s*workspace\s+mutations\s*:",
|
||||
re.IGNORECASE | re.MULTILINE,
|
||||
)
|
||||
_VAGUE_MUTATIONS_NONE_RE = re.compile(
|
||||
r"^\s*[-*]?\s*mutations\s*:\s*none\s*$",
|
||||
re.IGNORECASE | re.MULTILINE,
|
||||
)
|
||||
|
||||
_REQUIRED_CATEGORIES = (
|
||||
"file edits by reviewer",
|
||||
"worktree/index mutations",
|
||||
"git ref mutations",
|
||||
)
|
||||
_WORKTREE_FIELD_ALIASES = (
|
||||
"worktree/index mutations",
|
||||
"worktree mutations",
|
||||
)
|
||||
|
||||
|
||||
def _has_category(text: str, category: str) -> bool:
|
||||
pattern = re.compile(
|
||||
rf"^\s*[-*]?\s*{re.escape(category)}\s*:",
|
||||
re.IGNORECASE | re.MULTILINE,
|
||||
)
|
||||
return bool(pattern.search(text))
|
||||
|
||||
|
||||
def _has_worktree_category(text: str) -> bool:
|
||||
return any(_has_category(text, alias) for alias in _WORKTREE_FIELD_ALIASES)
|
||||
|
||||
|
||||
def _normalize_for_consistency_check(text: str) -> str:
|
||||
"""Map #319 precise labels to #313 field names for consistency delegation."""
|
||||
normalized = text
|
||||
if _has_category(text, "worktree/index mutations") and not _has_category(
|
||||
text, "worktree mutations"
|
||||
):
|
||||
normalized = re.sub(
|
||||
r"(worktree/index mutations\s*:)",
|
||||
"Worktree mutations:",
|
||||
normalized,
|
||||
flags=re.IGNORECASE,
|
||||
)
|
||||
return normalized
|
||||
|
||||
|
||||
def assess_mutation_categories_report(
|
||||
report_text: str,
|
||||
*,
|
||||
handoff_session: dict | None = None,
|
||||
observed_commands: list | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""Require precise mutation categories in reviewer controller handoffs (#319)."""
|
||||
text = report_text or ""
|
||||
session = dict(handoff_session or {})
|
||||
reasons: list[str] = []
|
||||
lower = text.lower()
|
||||
|
||||
is_controller = bool(
|
||||
session.get("controller_handoff")
|
||||
or _CONTROLLER_HANDOFF_RE.search(text)
|
||||
)
|
||||
if not is_controller and not session.get("require_categories"):
|
||||
return {
|
||||
"proven": True,
|
||||
"block": False,
|
||||
"reasons": [],
|
||||
"controller_handoff": False,
|
||||
"safe_next_action": "proceed",
|
||||
}
|
||||
|
||||
if _WORKSPACE_MUTATIONS_RE.search(text):
|
||||
reasons.append(
|
||||
"controller handoffs must not use legacy 'Workspace mutations'; "
|
||||
"use precise mutation category fields"
|
||||
)
|
||||
|
||||
if _VAGUE_MUTATIONS_NONE_RE.search(text):
|
||||
reasons.append(
|
||||
"controller handoffs must not use vague 'Mutations: none'; "
|
||||
"report each precise category separately"
|
||||
)
|
||||
|
||||
missing = [
|
||||
category
|
||||
for category in _REQUIRED_CATEGORIES
|
||||
if category != "worktree/index mutations" and not _has_category(text, category)
|
||||
]
|
||||
if not _has_worktree_category(text):
|
||||
missing.append("worktree/index mutations")
|
||||
|
||||
if missing:
|
||||
reasons.append(
|
||||
"controller handoff missing precise mutation categories: "
|
||||
+ ", ".join(missing)
|
||||
)
|
||||
|
||||
commands = observed_commands or session.get("observed_commands")
|
||||
if commands:
|
||||
from review_proofs import assess_workspace_mutation_consistency
|
||||
|
||||
consistency = assess_workspace_mutation_consistency(
|
||||
_normalize_for_consistency_check(text),
|
||||
commands,
|
||||
)
|
||||
if not consistency.get("complete"):
|
||||
reasons.extend(consistency.get("reasons") or [])
|
||||
|
||||
proven = not reasons
|
||||
return {
|
||||
"proven": proven,
|
||||
"block": not proven,
|
||||
"reasons": reasons,
|
||||
"controller_handoff": True,
|
||||
"safe_next_action": (
|
||||
"replace Workspace mutations with file edits, worktree/index, git ref, "
|
||||
"and other precise mutation category fields"
|
||||
if reasons
|
||||
else "proceed"
|
||||
),
|
||||
}
|
||||
@@ -0,0 +1,148 @@
|
||||
"""PR-head vs diagnostic validation integrity verifier (#316)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
from typing import Any
|
||||
|
||||
_DIAGNOSTIC_LABEL_RE = re.compile(
|
||||
r"diagnostic local experiment|not pr-head validation|diagnostic-only validation",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_OFFICIAL_VALIDATION_RE = re.compile(
|
||||
r"(?:official validation|pr-head validation|validation integrity)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_OFFICIAL_COMMAND_RE = re.compile(
|
||||
r"(?:official validation command|pr-head validation command|validation command)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_OFFICIAL_RESULT_RE = re.compile(
|
||||
r"(?:official validation result|pr-head validation result|validation result|validation integrity status)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_DIRTY_AFTER_RE = re.compile(
|
||||
r"(?:worktree dirty after (?:official )?validation|dirty (?:state )?after (?:official )?validation|"
|
||||
r"validation worktree dirty after)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_DIAGNOSTIC_EDIT_RE = re.compile(
|
||||
r"(?:diagnostic edit(?:ed)? path|file edits by reviewer|diagnostic local edit)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_DIAGNOSTIC_COMMAND_RE = re.compile(
|
||||
r"(?:diagnostic (?:validation )?command|diagnostic test run|diagnostic result)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_SUGGESTED_FIX_RE = re.compile(
|
||||
r"(?:diagnostic results? (?:were )?used only for suggested fix|suggested fix only|"
|
||||
r"not used as official validation)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_INTEGRITY_STATUS_RE = re.compile(
|
||||
r"validation integrity status\s*:\s*(passed|failed|not run|contaminated)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_POST_EDIT_AS_OFFICIAL_RE = re.compile(
|
||||
r"(?:official validation(?:\s+result)?\s*:\s*pass|validation passed after (?:local )?edit|"
|
||||
r"full suite passed after diagnostic edit)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
|
||||
def _performed_edits(action_log: list[dict] | None) -> list[str]:
|
||||
paths: list[str] = []
|
||||
for entry in action_log or []:
|
||||
if entry.get("gated_rejected") or entry.get("performed") is False:
|
||||
continue
|
||||
path = entry.get("path")
|
||||
if path and entry.get("kind", "file_edit") in {"file_edit", "edit", "write"}:
|
||||
paths.append(str(path))
|
||||
return paths
|
||||
|
||||
|
||||
def assess_validation_integrity_report(
|
||||
report_text: str,
|
||||
*,
|
||||
validation_session: dict | None = None,
|
||||
action_log: list[dict] | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""Separate official PR-head validation from diagnostic edited-worktree tests (#316)."""
|
||||
text = report_text or ""
|
||||
session = dict(validation_session or {})
|
||||
reasons: list[str] = []
|
||||
|
||||
diagnostic_edits = list(session.get("diagnostic_edits") or [])
|
||||
if not diagnostic_edits:
|
||||
diagnostic_edits = _performed_edits(action_log)
|
||||
diagnostic_ran = bool(
|
||||
session.get("diagnostic_validation_ran")
|
||||
or session.get("diagnostic_runs")
|
||||
)
|
||||
official_ran = bool(session.get("official_validation_ran", True))
|
||||
official_result = (session.get("official_result") or "").strip().lower()
|
||||
diagnostic_result = (session.get("diagnostic_result") or "").strip().lower()
|
||||
dirty_after = session.get("worktree_dirty_after_official")
|
||||
contaminated = bool(session.get("contaminated"))
|
||||
|
||||
if official_ran:
|
||||
if not _OFFICIAL_VALIDATION_RE.search(text) and not _OFFICIAL_COMMAND_RE.search(text):
|
||||
reasons.append("report missing official PR-head validation section")
|
||||
if not _OFFICIAL_COMMAND_RE.search(text) and "validation:" not in text.lower():
|
||||
reasons.append("report missing official validation command")
|
||||
if not _OFFICIAL_RESULT_RE.search(text):
|
||||
reasons.append("report missing official validation result or integrity status")
|
||||
if dirty_after is not None and not _DIRTY_AFTER_RE.search(text):
|
||||
reasons.append(
|
||||
"report missing worktree dirty state after official validation"
|
||||
)
|
||||
elif dirty_after is None and official_ran and not _DIRTY_AFTER_RE.search(text):
|
||||
reasons.append(
|
||||
"report missing worktree dirty state after official validation"
|
||||
)
|
||||
|
||||
if diagnostic_edits or diagnostic_ran:
|
||||
if not _DIAGNOSTIC_LABEL_RE.search(text):
|
||||
reasons.append(
|
||||
"post-edit diagnostic runs must be labeled "
|
||||
"'Diagnostic local experiment — not PR-head validation'"
|
||||
)
|
||||
if diagnostic_edits and not _DIAGNOSTIC_EDIT_RE.search(text):
|
||||
reasons.append("report missing diagnostic edit path")
|
||||
if diagnostic_ran and not _DIAGNOSTIC_COMMAND_RE.search(text):
|
||||
reasons.append("report missing diagnostic command/result")
|
||||
if not _SUGGESTED_FIX_RE.search(text):
|
||||
reasons.append(
|
||||
"report must state diagnostic results were used only for suggested fix"
|
||||
)
|
||||
if _POST_EDIT_AS_OFFICIAL_RE.search(text):
|
||||
reasons.append(
|
||||
"post-edit diagnostic results cannot be reported as official PR-head validation"
|
||||
)
|
||||
if diagnostic_result == "pass" and official_result == "fail":
|
||||
if "request_changes" not in text.lower() and "failed" not in text.lower():
|
||||
reasons.append(
|
||||
"request-changes must cite unmodified PR-head failure, not diagnostic pass"
|
||||
)
|
||||
|
||||
if contaminated:
|
||||
status = _INTEGRITY_STATUS_RE.search(text)
|
||||
if not status or "contaminated" not in status.group(1).lower():
|
||||
reasons.append(
|
||||
"contaminated validation must report integrity status "
|
||||
"'contaminated — recovery required'"
|
||||
)
|
||||
|
||||
proven = not reasons
|
||||
return {
|
||||
"proven": proven,
|
||||
"block": not proven,
|
||||
"reasons": reasons,
|
||||
"diagnostic_edits": diagnostic_edits,
|
||||
"safe_next_action": (
|
||||
"separate official PR-head validation from diagnostic experiments; "
|
||||
"report dirty-after-validation state"
|
||||
if reasons
|
||||
else "proceed"
|
||||
),
|
||||
}
|
||||
@@ -0,0 +1,184 @@
|
||||
"""PR validation worktree read-only edit verifier (#315)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
from typing import Any
|
||||
|
||||
_VALIDATION_WORKTREE_RE = re.compile(
|
||||
r"branches/(?:review-pr\d+[\w/-]*|review-[\w-]+)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_DIAGNOSTIC_WORKTREE_RE = re.compile(
|
||||
r"branches/(?:diagnostic[\w/-]*|scratch[\w/-]*)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_FILE_EDITS_NONE_RE = re.compile(
|
||||
r"file edits by reviewer\s*:\s*none\b",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_FILE_EDITS_FIELD_RE = re.compile(
|
||||
r"file edits by reviewer\s*:\s*(.+)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_VALIDATION_WORKTREE_PATH_RE = re.compile(
|
||||
r"(?:validation worktree path|review worktree path)\s*:\s*(\S+)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_DIAGNOSTIC_WORKTREE_PATH_RE = re.compile(
|
||||
r"(?:diagnostic (?:scratch )?worktree path|diagnostic worktree)\s*:\s*(\S+)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_DIAGNOSTIC_LABEL_RE = re.compile(
|
||||
r"diagnostic local experiment|not pr-head validation|diagnostic-only",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_OFFICIAL_VALIDATION_RE = re.compile(
|
||||
r"(?:official (?:pr-head )?validation|pr-head validation result)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_POST_EDIT_OFFICIAL_RE = re.compile(
|
||||
r"(?:official validation(?:\s+result)?\s*:\s*pass|validation passed after (?:local )?edit)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
_PERFORMED_EDIT_KINDS = frozenset({"file_edit", "edit", "write", "edited", "created", "wrote"})
|
||||
|
||||
|
||||
def _normalize_path(path: str) -> str:
|
||||
return (path or "").replace("\\", "/").strip()
|
||||
|
||||
|
||||
def _is_validation_worktree(path: str) -> bool:
|
||||
return bool(_VALIDATION_WORKTREE_RE.search(_normalize_path(path)))
|
||||
|
||||
|
||||
def _is_diagnostic_worktree(path: str) -> bool:
|
||||
normalized = _normalize_path(path)
|
||||
return bool(
|
||||
_DIAGNOSTIC_WORKTREE_RE.search(normalized)
|
||||
or "diagnostic" in normalized.lower()
|
||||
)
|
||||
|
||||
|
||||
def _performed_edits(action_log: list[dict] | None) -> list[dict[str, str]]:
|
||||
edits: list[dict[str, str]] = []
|
||||
for entry in action_log or []:
|
||||
if entry.get("gated_rejected") or entry.get("performed") is False:
|
||||
continue
|
||||
kind = (entry.get("kind") or entry.get("action") or "file_edit").strip().lower()
|
||||
if kind not in _PERFORMED_EDIT_KINDS:
|
||||
continue
|
||||
path = (entry.get("path") or "").strip()
|
||||
if not path:
|
||||
continue
|
||||
worktree = _normalize_path(str(entry.get("worktree_path") or entry.get("cwd") or ""))
|
||||
edits.append({"path": path, "worktree_path": worktree})
|
||||
return edits
|
||||
|
||||
|
||||
def _extract_validation_path(text: str, session: dict) -> str:
|
||||
path = _normalize_path(str(session.get("validation_worktree_path") or ""))
|
||||
if path:
|
||||
return path
|
||||
match = _VALIDATION_WORKTREE_PATH_RE.search(text or "")
|
||||
return _normalize_path(match.group(1)) if match else ""
|
||||
|
||||
|
||||
def _extract_diagnostic_path(text: str, session: dict) -> str:
|
||||
path = _normalize_path(str(session.get("diagnostic_worktree_path") or ""))
|
||||
if path:
|
||||
return path
|
||||
match = _DIAGNOSTIC_WORKTREE_PATH_RE.search(text or "")
|
||||
return _normalize_path(match.group(1)) if match else ""
|
||||
|
||||
|
||||
def assess_validation_worktree_edit_report(
|
||||
report_text: str,
|
||||
*,
|
||||
validation_session: dict | None = None,
|
||||
action_log: list[dict] | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""Block edits in PR validation worktrees; require diagnostic separation (#315)."""
|
||||
text = report_text or ""
|
||||
session = dict(validation_session or {})
|
||||
reasons: list[str] = []
|
||||
|
||||
validation_path = _extract_validation_path(text, session)
|
||||
diagnostic_path = _extract_diagnostic_path(text, session)
|
||||
validation_edits = list(session.get("validation_worktree_edits") or [])
|
||||
diagnostic_edits = list(session.get("diagnostic_edits") or [])
|
||||
edits = _performed_edits(action_log)
|
||||
|
||||
if not validation_edits:
|
||||
for entry in edits:
|
||||
wt = entry.get("worktree_path") or validation_path
|
||||
if wt and _is_validation_worktree(wt) and not _is_diagnostic_worktree(wt):
|
||||
validation_edits.append(entry["path"])
|
||||
|
||||
if not diagnostic_edits:
|
||||
for entry in edits:
|
||||
wt = entry.get("worktree_path") or ""
|
||||
if wt and _is_diagnostic_worktree(wt):
|
||||
diagnostic_edits.append(entry["path"])
|
||||
elif entry["path"] and diagnostic_path and not validation_edits:
|
||||
if _is_diagnostic_worktree(diagnostic_path):
|
||||
diagnostic_edits.append(entry["path"])
|
||||
|
||||
claimed_none = bool(_FILE_EDITS_NONE_RE.search(text))
|
||||
any_edits = bool(validation_edits or diagnostic_edits or edits)
|
||||
|
||||
if validation_edits:
|
||||
reasons.append(
|
||||
"reviewer must not edit files in the PR validation worktree; "
|
||||
f"observed edits: {', '.join(validation_edits)}"
|
||||
)
|
||||
|
||||
if diagnostic_edits or session.get("diagnostic_experiment"):
|
||||
if not diagnostic_path and not _DIAGNOSTIC_WORKTREE_PATH_RE.search(text):
|
||||
reasons.append(
|
||||
"diagnostic experiments require a separate diagnostic scratch worktree path"
|
||||
)
|
||||
if not _DIAGNOSTIC_LABEL_RE.search(text):
|
||||
reasons.append(
|
||||
"diagnostic experiments must be labeled "
|
||||
"'Diagnostic local experiment — not PR-head validation'"
|
||||
)
|
||||
if not _FILE_EDITS_FIELD_RE.search(text) or claimed_none:
|
||||
reasons.append(
|
||||
"diagnostic edits must be reported under 'File edits by reviewer'"
|
||||
)
|
||||
|
||||
if any_edits and claimed_none:
|
||||
reasons.append(
|
||||
"report claims 'File edits by reviewer: none' but reviewer file edits occurred"
|
||||
)
|
||||
|
||||
if session.get("official_validation_after_edit") or _POST_EDIT_OFFICIAL_RE.search(text):
|
||||
if validation_edits or (validation_path and diagnostic_edits):
|
||||
reasons.append(
|
||||
"post-edit test results cannot be reported as official PR-head validation"
|
||||
)
|
||||
|
||||
if validation_edits and _OFFICIAL_VALIDATION_RE.search(text):
|
||||
if not _DIAGNOSTIC_LABEL_RE.search(text):
|
||||
reasons.append(
|
||||
"validation worktree was edited; official PR-head validation is no longer valid"
|
||||
)
|
||||
|
||||
proven = not reasons
|
||||
return {
|
||||
"proven": proven,
|
||||
"block": not proven,
|
||||
"reasons": reasons,
|
||||
"validation_worktree_path": validation_path or None,
|
||||
"diagnostic_worktree_path": diagnostic_path or None,
|
||||
"validation_worktree_edits": validation_edits,
|
||||
"diagnostic_edits": diagnostic_edits,
|
||||
"safe_next_action": (
|
||||
"keep PR validation worktrees read-only; use a separate diagnostic "
|
||||
"scratch worktree and report all reviewer file edits"
|
||||
if reasons
|
||||
else "proceed"
|
||||
),
|
||||
}
|
||||
@@ -0,0 +1,207 @@
|
||||
"""Reviewer worktree ownership and safe-reuse proof verifier (#312)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
from typing import Any
|
||||
|
||||
_SESSION_OWNED_RE = re.compile(
|
||||
r"branches/(?:review-pr\d+[\w/-]*|review-[\w-]+)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_WORKTREE_PATH_RE = re.compile(
|
||||
r"(?:review worktree path|worktree path|session-owned worktree)\s*:\s*(\S+)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_BRANCHES_PATH_RE = re.compile(r"/branches/|\bbranches/", re.IGNORECASE)
|
||||
_MAIN_CHECKOUT_RE = re.compile(
|
||||
r"main checkout|not (?:the )?main checkout|outside branches/",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_SAFE_REUSE_RE = re.compile(r"safe[- ]reuse proof", re.IGNORECASE)
|
||||
_REUSE_POLICY_RE = re.compile(
|
||||
r"(?:project policy|policy) (?:allows|allowing) (?:reuse|reset)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_CLEAN_TRACKED_RE = re.compile(
|
||||
r"(?:clean tracked state|tracked state\s*:\s*clean|no uncommitted tracked)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_CLEAN_UNTRACKED_RE = re.compile(
|
||||
r"(?:clean untracked state|untracked state\s*:\s*clean|no untracked files)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_NOT_OTHER_SESSION_RE = re.compile(
|
||||
r"not owned by (?:another|other) (?:active )?(?:task|session)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_BRANCH_BEFORE_RESET_RE = re.compile(
|
||||
r"(?:branch/head before reset|head before reset|branch before reset)\s*:\s*(\S+)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_RESET_TARGET_RE = re.compile(
|
||||
r"(?:reset target sha|reset target)\s*:\s*([0-9a-f]{7,40})",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_DESTRUCTIVE_CMD_RE = re.compile(
|
||||
r"\bgit\b(?:\s+(?:-C\s+\S+\s+)?)?"
|
||||
r"(?:reset\s+--hard|clean(?:\s+-[A-Za-z]+)*|checkout\s+(?!HEAD\s+--)|switch\s+)",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_WORKSPACE_NONE_RE = re.compile(r"workspace mutations\s*:\s*none", re.IGNORECASE)
|
||||
_WORKTREE_MUTATION_RE = re.compile(
|
||||
r"(?:worktree(?:/index)? mutations|destructive reset)\s*:\s*(?!none\b).+",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_RESET_IN_REPORT_RE = re.compile(r"reset\s+--hard", re.IGNORECASE)
|
||||
|
||||
|
||||
def _command_text(entry) -> str:
|
||||
if isinstance(entry, dict):
|
||||
return str(entry.get("command") or "").strip()
|
||||
return str(entry or "").strip()
|
||||
|
||||
|
||||
def _destructive_commands(command_log: list | None) -> list[str]:
|
||||
return [
|
||||
cmd
|
||||
for cmd in (_command_text(entry) for entry in (command_log or []))
|
||||
if cmd and _DESTRUCTIVE_CMD_RE.search(cmd)
|
||||
]
|
||||
|
||||
|
||||
def _extract_worktree_path(text: str, session: dict) -> str:
|
||||
path = (session.get("worktree_path") or "").strip()
|
||||
if path:
|
||||
return path
|
||||
match = _WORKTREE_PATH_RE.search(text or "")
|
||||
return match.group(1).strip() if match else ""
|
||||
|
||||
|
||||
def _is_session_owned_path(path: str) -> bool:
|
||||
normalized = (path or "").replace("\\", "/")
|
||||
return bool(_SESSION_OWNED_RE.search(normalized))
|
||||
|
||||
|
||||
def _safe_reuse_fields_present(text: str) -> list[str]:
|
||||
missing: list[str] = []
|
||||
if not _WORKTREE_PATH_RE.search(text):
|
||||
missing.append("exact worktree path")
|
||||
if not _BRANCHES_PATH_RE.search(text):
|
||||
missing.append("worktree inside branches/")
|
||||
if not _MAIN_CHECKOUT_RE.search(text):
|
||||
missing.append("worktree is not the main checkout")
|
||||
if not _NOT_OTHER_SESSION_RE.search(text):
|
||||
missing.append("worktree not owned by another active session")
|
||||
if not _CLEAN_TRACKED_RE.search(text):
|
||||
missing.append("clean tracked state")
|
||||
if not _CLEAN_UNTRACKED_RE.search(text):
|
||||
missing.append("clean untracked state")
|
||||
if not _BRANCH_BEFORE_RESET_RE.search(text):
|
||||
missing.append("branch/head before reset")
|
||||
if not _RESET_TARGET_RE.search(text):
|
||||
missing.append("reset target SHA")
|
||||
if not _REUSE_POLICY_RE.search(text):
|
||||
missing.append("explicit project policy allowing reuse/reset")
|
||||
return missing
|
||||
|
||||
|
||||
def assess_worktree_ownership_report(
|
||||
report_text: str,
|
||||
*,
|
||||
ownership_session: dict | None = None,
|
||||
command_log: list | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""Prove reviewer worktree ownership before reset or validation (#312)."""
|
||||
text = report_text or ""
|
||||
session = dict(ownership_session or {})
|
||||
reasons: list[str] = []
|
||||
|
||||
worktree_path = _extract_worktree_path(text, session)
|
||||
destructive = _destructive_commands(command_log or session.get("command_log"))
|
||||
if not destructive and session.get("destructive_reset"):
|
||||
destructive = ["git reset --hard (session)"]
|
||||
|
||||
session_owned = bool(
|
||||
session.get("session_owned")
|
||||
or (worktree_path and _is_session_owned_path(worktree_path))
|
||||
)
|
||||
safe_reuse = bool(session.get("safe_reuse") or _SAFE_REUSE_RE.search(text))
|
||||
main_checkout = bool(session.get("main_checkout"))
|
||||
dirty_tracked = session.get("dirty_tracked")
|
||||
dirty_untracked = session.get("dirty_untracked")
|
||||
other_session_owned = bool(session.get("other_session_owned"))
|
||||
|
||||
if worktree_path or destructive or session.get("validation_ran"):
|
||||
if not worktree_path:
|
||||
reasons.append("report missing exact review worktree path")
|
||||
elif main_checkout or "branches/" not in worktree_path.replace("\\", "/"):
|
||||
reasons.append("review worktree must be inside branches/, not the main checkout")
|
||||
elif not _BRANCHES_PATH_RE.search(worktree_path.replace("\\", "/")):
|
||||
reasons.append("review worktree path must be under branches/")
|
||||
|
||||
if other_session_owned and not safe_reuse:
|
||||
reasons.append(
|
||||
"reused worktree appears owned by another active task/session; "
|
||||
"safe-reuse proof required"
|
||||
)
|
||||
|
||||
if dirty_tracked:
|
||||
reasons.append(
|
||||
"worktree has uncommitted tracked changes before reset or validation"
|
||||
)
|
||||
if dirty_untracked and safe_reuse:
|
||||
reasons.append("safe-reuse proof requires clean untracked state")
|
||||
|
||||
if safe_reuse and not session_owned:
|
||||
reasons.extend(
|
||||
f"safe-reuse proof missing {field}"
|
||||
for field in _safe_reuse_fields_present(text)
|
||||
)
|
||||
|
||||
if destructive:
|
||||
if not session_owned and not safe_reuse:
|
||||
reasons.append(
|
||||
"destructive worktree commands forbidden without session-owned "
|
||||
"worktree or safe-reuse proof"
|
||||
)
|
||||
if _WORKSPACE_NONE_RE.search(text) and (
|
||||
_RESET_IN_REPORT_RE.search(text) or any("reset" in c.lower() for c in destructive)
|
||||
):
|
||||
reasons.append(
|
||||
"final report must not claim 'Workspace mutations: none' when "
|
||||
"git reset --hard occurred"
|
||||
)
|
||||
if not _WORKTREE_MUTATION_RE.search(text) and not _RESET_IN_REPORT_RE.search(text):
|
||||
reasons.append(
|
||||
"destructive reset must be reported under Worktree/index mutations "
|
||||
"or destructive reset operations"
|
||||
)
|
||||
|
||||
if (
|
||||
worktree_path
|
||||
and not session_owned
|
||||
and not safe_reuse
|
||||
and (destructive or session.get("validation_ran"))
|
||||
and not _is_session_owned_path(worktree_path)
|
||||
):
|
||||
reasons.append(
|
||||
"reused branch-named worktree requires safe-reuse proof before reset or validation"
|
||||
)
|
||||
|
||||
proven = not reasons
|
||||
return {
|
||||
"proven": proven,
|
||||
"block": not proven,
|
||||
"reasons": reasons,
|
||||
"worktree_path": worktree_path or None,
|
||||
"session_owned": session_owned,
|
||||
"safe_reuse": safe_reuse,
|
||||
"destructive_commands": destructive,
|
||||
"safe_next_action": (
|
||||
"use a fresh session-owned review worktree under branches/review-pr<N>-* "
|
||||
"or document full safe-reuse proof before destructive reset"
|
||||
if reasons
|
||||
else "proceed"
|
||||
),
|
||||
}
|
||||
@@ -62,7 +62,24 @@ class TestPreflightWarnings(unittest.TestCase):
|
||||
self.assertIn("_encode_commit_payload.py", status["preflight_warnings"][0])
|
||||
|
||||
|
||||
# Issue-write tools are profile-gated (#69); gitea_lock_issue requires
|
||||
# gitea.issue.comment (see task_capability_map), so the gate must be
|
||||
# seeded exactly like tests/test_mcp_server.py::TestIssueLocking (#359).
|
||||
ISSUE_WRITE_ENV = {
|
||||
"GITEA_ALLOWED_OPERATIONS": (
|
||||
"gitea.issue.create,gitea.issue.close,gitea.issue.comment"
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
class TestIssueLockArtifactWarning(unittest.TestCase):
|
||||
def setUp(self):
|
||||
self._env_patcher = patch.dict(os.environ, ISSUE_WRITE_ENV, clear=True)
|
||||
self._env_patcher.start()
|
||||
|
||||
def tearDown(self):
|
||||
self._env_patcher.stop()
|
||||
|
||||
@patch("mcp_server.api_get_all", return_value=[])
|
||||
@patch("mcp_server._auth", return_value="token x")
|
||||
@patch("mcp_server._resolve", return_value=("h", "o", "r"))
|
||||
@@ -72,6 +89,9 @@ class TestIssueLockArtifactWarning(unittest.TestCase):
|
||||
mock_state.return_value = {
|
||||
"current_branch": "master",
|
||||
"porcelain_status": "?? _emit_payload.py\n",
|
||||
"base_equivalent": True,
|
||||
"inspected_git_root": "/scratch/wt",
|
||||
"base_branch": "origin/master",
|
||||
}
|
||||
result = mcp_server.gitea_lock_issue(
|
||||
issue_number=261,
|
||||
|
||||
@@ -0,0 +1,151 @@
|
||||
"""Tests for already-landed final-report wording validator (#298).
|
||||
|
||||
An already-landed PR is reconciliation-only, never review/merge
|
||||
eligible, and a head SHA may not be called reviewed unless validation
|
||||
and diff review actually passed. Final reports and controller handoffs
|
||||
must use the reconciliation wording, not the legacy eligible/reviewed
|
||||
fields.
|
||||
"""
|
||||
import sys
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
|
||||
|
||||
from review_proofs import assess_already_landed_report_wording # noqa: E402
|
||||
|
||||
|
||||
GOOD_ALREADY_LANDED = (
|
||||
"Controller Handoff\n"
|
||||
"- Oldest open PR requiring action: PR #278\n"
|
||||
"- Eligibility class: ALREADY_LANDED_RECONCILE_REQUIRED\n"
|
||||
"- Candidate head SHA: 2a544b7\n"
|
||||
"- Reviewed head SHA: none\n"
|
||||
"- Review worktree used: false\n"
|
||||
)
|
||||
|
||||
|
||||
class TestAlreadyLandedWording(unittest.TestCase):
|
||||
def test_correct_reconciliation_wording_passes(self):
|
||||
result = assess_already_landed_report_wording(
|
||||
GOOD_ALREADY_LANDED, already_landed=True
|
||||
)
|
||||
self.assertTrue(result["complete"])
|
||||
self.assertFalse(result["downgraded"])
|
||||
self.assertEqual(result["reasons"], [])
|
||||
|
||||
def test_oldest_eligible_wording_fails(self):
|
||||
report = GOOD_ALREADY_LANDED + "- oldest eligible PR: PR #278\n"
|
||||
result = assess_already_landed_report_wording(
|
||||
report, already_landed=True
|
||||
)
|
||||
self.assertFalse(result["complete"])
|
||||
self.assertTrue(
|
||||
any("oldest eligible pr" in r.lower() for r in result["reasons"])
|
||||
)
|
||||
|
||||
def test_next_eligible_wording_fails(self):
|
||||
report = GOOD_ALREADY_LANDED + "- next eligible PR: PR #278\n"
|
||||
result = assess_already_landed_report_wording(
|
||||
report, already_landed=True
|
||||
)
|
||||
self.assertFalse(result["complete"])
|
||||
|
||||
def test_pinned_reviewed_head_fails(self):
|
||||
report = GOOD_ALREADY_LANDED + "- Pinned reviewed head: 2a544b7\n"
|
||||
result = assess_already_landed_report_wording(
|
||||
report, already_landed=True
|
||||
)
|
||||
self.assertFalse(result["complete"])
|
||||
self.assertTrue(
|
||||
any("pinned reviewed head" in r.lower() for r in result["reasons"])
|
||||
)
|
||||
|
||||
def test_scratch_worktree_field_fails(self):
|
||||
report = GOOD_ALREADY_LANDED + "- Scratch worktree used: False\n"
|
||||
result = assess_already_landed_report_wording(
|
||||
report, already_landed=True
|
||||
)
|
||||
self.assertFalse(result["complete"])
|
||||
|
||||
def test_missing_eligibility_class_fails(self):
|
||||
report = (
|
||||
"Controller Handoff\n"
|
||||
"- Oldest open PR requiring action: PR #278\n"
|
||||
"- Candidate head SHA: 2a544b7\n"
|
||||
"- Reviewed head SHA: none\n"
|
||||
"- Review worktree used: false\n"
|
||||
)
|
||||
result = assess_already_landed_report_wording(
|
||||
report, already_landed=True
|
||||
)
|
||||
self.assertFalse(result["complete"])
|
||||
self.assertTrue(
|
||||
any("eligibility class" in r.lower() for r in result["reasons"])
|
||||
)
|
||||
|
||||
def test_populated_reviewed_head_sha_fails(self):
|
||||
report = GOOD_ALREADY_LANDED.replace(
|
||||
"- Reviewed head SHA: none\n",
|
||||
"- Reviewed head SHA: 2a544b7\n",
|
||||
)
|
||||
result = assess_already_landed_report_wording(
|
||||
report, already_landed=True
|
||||
)
|
||||
self.assertFalse(result["complete"])
|
||||
self.assertTrue(
|
||||
any("reviewed head" in r.lower() for r in result["reasons"])
|
||||
)
|
||||
|
||||
|
||||
class TestNonAlreadyLandedReports(unittest.TestCase):
|
||||
def test_normal_reviewed_report_passes(self):
|
||||
report = (
|
||||
"- Selected PR: 281\n"
|
||||
"- Pinned reviewed head: abc1234\n"
|
||||
"- Review decision: approve\n"
|
||||
)
|
||||
result = assess_already_landed_report_wording(
|
||||
report, already_landed=False, review_validated=True
|
||||
)
|
||||
self.assertTrue(result["complete"])
|
||||
|
||||
def test_blocked_infra_report_with_pinned_head_fails(self):
|
||||
report = (
|
||||
"- Selected PR: 281\n"
|
||||
"- Pinned reviewed head: abc1234\n"
|
||||
"- Current status: blocked on infra_stop\n"
|
||||
)
|
||||
result = assess_already_landed_report_wording(
|
||||
report, already_landed=False, review_validated=False
|
||||
)
|
||||
self.assertFalse(result["complete"])
|
||||
self.assertTrue(
|
||||
any("before validation" in r.lower() for r in result["reasons"])
|
||||
)
|
||||
|
||||
def test_validation_failed_report_with_reviewed_sha_fails(self):
|
||||
report = (
|
||||
"- Selected PR: 281\n"
|
||||
"- Reviewed head SHA: abc1234\n"
|
||||
"- Validation: full suite failed\n"
|
||||
)
|
||||
result = assess_already_landed_report_wording(
|
||||
report, already_landed=False, review_validated=False
|
||||
)
|
||||
self.assertFalse(result["complete"])
|
||||
|
||||
def test_validation_failed_report_with_reviewed_none_passes(self):
|
||||
report = (
|
||||
"- Selected PR: 281\n"
|
||||
"- Reviewed head SHA: none\n"
|
||||
"- Validation: full suite failed\n"
|
||||
)
|
||||
result = assess_already_landed_report_wording(
|
||||
report, already_landed=False, review_validated=False
|
||||
)
|
||||
self.assertTrue(result["complete"])
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,118 @@
|
||||
"""Tests for linked-issue consistency verifier (#314).
|
||||
|
||||
Reviewer reports must verify the linked issue live for the selected PR;
|
||||
stale issue numbers from a previous PR must not leak into the final
|
||||
report, and linked-issue status must never be claimed without live proof.
|
||||
"""
|
||||
import sys
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
|
||||
|
||||
from review_proofs import assess_linked_issue_consistency # noqa: E402
|
||||
|
||||
|
||||
class TestCorrectLinkedIssue(unittest.TestCase):
|
||||
def test_matching_linked_issue_passes(self):
|
||||
report = (
|
||||
"Selected PR: 280\n"
|
||||
"Linked issue status: Issue #275 open, closes on merge\n"
|
||||
)
|
||||
result = assess_linked_issue_consistency(
|
||||
report, selected_pr=280, linked_issues=[275]
|
||||
)
|
||||
self.assertTrue(result["complete"])
|
||||
self.assertFalse(result["downgraded"])
|
||||
self.assertEqual(result["reasons"], [])
|
||||
|
||||
def test_multiple_linked_issues_all_reported_passes(self):
|
||||
report = (
|
||||
"Linked issue status: Issue #275 and Issue #276 both open\n"
|
||||
)
|
||||
result = assess_linked_issue_consistency(
|
||||
report, selected_pr=280, linked_issues=[275, 276]
|
||||
)
|
||||
self.assertTrue(result["complete"])
|
||||
|
||||
def test_multiple_linked_issues_one_missing_fails(self):
|
||||
report = "Linked issue status: Issue #275 open\n"
|
||||
result = assess_linked_issue_consistency(
|
||||
report, selected_pr=280, linked_issues=[275, 276]
|
||||
)
|
||||
self.assertFalse(result["complete"])
|
||||
self.assertTrue(
|
||||
any("276" in r for r in result["reasons"])
|
||||
)
|
||||
|
||||
|
||||
class TestStaleIssueLeak(unittest.TestCase):
|
||||
def test_stale_issue_in_status_field_fails(self):
|
||||
# #314 observed behavior: PR #280 links Issue #275 but the report
|
||||
# carries Issue #260 from the previous PR.
|
||||
report = "Linked issue status: Issue #260 open\n"
|
||||
result = assess_linked_issue_consistency(
|
||||
report, selected_pr=280, linked_issues=[275]
|
||||
)
|
||||
self.assertFalse(result["complete"])
|
||||
self.assertTrue(any("260" in r for r in result["reasons"]))
|
||||
|
||||
def test_stale_issue_in_diagnostics_fails(self):
|
||||
report = (
|
||||
"Linked issue status: Issue #275 open\n"
|
||||
"Read-only diagnostics: viewed Issue #260 status\n"
|
||||
)
|
||||
result = assess_linked_issue_consistency(
|
||||
report, selected_pr=280, linked_issues=[275]
|
||||
)
|
||||
self.assertFalse(result["complete"])
|
||||
self.assertTrue(
|
||||
any("stale" in r.lower() and "260" in r for r in result["reasons"])
|
||||
)
|
||||
|
||||
def test_selected_pr_number_mention_is_not_stale(self):
|
||||
# "PR #280" mentions must not be confused with issue mentions.
|
||||
report = (
|
||||
"Selected PR: 280\n"
|
||||
"Validation: ran tests at PR #280 head\n"
|
||||
"Linked issue status: Issue #275 open\n"
|
||||
)
|
||||
result = assess_linked_issue_consistency(
|
||||
report, selected_pr=280, linked_issues=[275]
|
||||
)
|
||||
self.assertTrue(result["complete"])
|
||||
|
||||
|
||||
class TestMissingProof(unittest.TestCase):
|
||||
def test_status_claim_without_live_proof_fails(self):
|
||||
report = "Linked issue status: Issue #275 open\n"
|
||||
result = assess_linked_issue_consistency(
|
||||
report, selected_pr=280, linked_issues=None
|
||||
)
|
||||
self.assertFalse(result["complete"])
|
||||
self.assertTrue(
|
||||
any("live proof" in r.lower() for r in result["reasons"])
|
||||
)
|
||||
|
||||
def test_unverified_wording_without_proof_passes(self):
|
||||
report = (
|
||||
"Linked issue status: not verified in this session\n"
|
||||
)
|
||||
result = assess_linked_issue_consistency(
|
||||
report, selected_pr=280, linked_issues=None
|
||||
)
|
||||
self.assertTrue(result["complete"])
|
||||
|
||||
def test_missing_field_fails(self):
|
||||
report = "Selected PR: 280\n"
|
||||
result = assess_linked_issue_consistency(
|
||||
report, selected_pr=280, linked_issues=[275]
|
||||
)
|
||||
self.assertFalse(result["complete"])
|
||||
self.assertTrue(
|
||||
any("linked issue status" in r.lower() for r in result["reasons"])
|
||||
)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -136,7 +136,43 @@ def test_create_issue_final_report_verifier_exported():
|
||||
assert callable(assess_create_issue_final_report)
|
||||
|
||||
|
||||
def test_merge_simulation_verifier_exported():
|
||||
from review_proofs import assess_merge_simulation_report
|
||||
|
||||
assert callable(assess_merge_simulation_report)
|
||||
|
||||
|
||||
def test_validation_integrity_verifier_exported():
|
||||
from review_proofs import assess_validation_integrity_report
|
||||
|
||||
assert callable(assess_validation_integrity_report)
|
||||
|
||||
|
||||
def test_prior_blocker_skip_verifier_exported():
|
||||
from review_proofs import assess_prior_blocker_skip_proof
|
||||
|
||||
assert callable(assess_prior_blocker_skip_proof)
|
||||
|
||||
|
||||
def test_non_mergeable_skip_verifier_exported():
|
||||
from review_proofs import assess_non_mergeable_skip_proof
|
||||
|
||||
assert callable(assess_non_mergeable_skip_proof)
|
||||
|
||||
|
||||
def test_validation_worktree_edit_verifier_exported():
|
||||
from review_proofs import assess_validation_worktree_edit_report
|
||||
|
||||
assert callable(assess_validation_worktree_edit_report)
|
||||
|
||||
|
||||
def test_mutation_categories_verifier_exported():
|
||||
from review_proofs import assess_mutation_categories_report
|
||||
|
||||
assert callable(assess_mutation_categories_report)
|
||||
|
||||
|
||||
def test_worktree_ownership_verifier_exported():
|
||||
from review_proofs import assess_worktree_ownership_report
|
||||
|
||||
assert callable(assess_worktree_ownership_report)
|
||||
+406
-3
@@ -23,7 +23,11 @@ sys.path.insert(0, str(__import__("pathlib").Path(__file__).resolve().parent.par
|
||||
from review_proofs import ( # noqa: E402
|
||||
ISSUE_SELECTION_CONTINUATION_EXPLICIT,
|
||||
ISSUE_SELECTION_REPRESENTED_BY_OPEN_PR,
|
||||
assess_already_landed_report_state,
|
||||
assess_already_landed_review_gate,
|
||||
assess_author_pr_report,
|
||||
assess_validation_environment_proof,
|
||||
assess_full_suite_failure_approval_gate,
|
||||
assess_queue_ordering_proof,
|
||||
assess_reviewer_baseline_validation_proof,
|
||||
assess_capability_evidence,
|
||||
@@ -2314,10 +2318,108 @@ class TestCreateIssueFinalReport(unittest.TestCase):
|
||||
self.assertTrue(result["downgraded"])
|
||||
|
||||
|
||||
class TestQueueOrderingProof(unittest.TestCase):
|
||||
"""Issue #321: reviewer queue selection must prove ordering."""
|
||||
class TestValidationEnvironmentProof(unittest.TestCase):
|
||||
"""Issue #311: exact validation command and execution environment."""
|
||||
|
||||
ROOT = "/repo/Gitea-Tools/branches/review-pr-280"
|
||||
|
||||
def test_venv_pytest_with_full_report_passes(self):
|
||||
result = assess_validation_environment_proof(
|
||||
report_text=(
|
||||
"Validation command: venv/bin/pytest tests/ --ignore=branches\n"
|
||||
f"Working directory: {self.ROOT}\n"
|
||||
"Result: 1014 passed, 6 skipped"
|
||||
),
|
||||
)
|
||||
self.assertTrue(result["proven"])
|
||||
|
||||
def test_bare_pytest_without_path_proof_fails(self):
|
||||
result = assess_validation_environment_proof(
|
||||
report_text=(
|
||||
"Validation command: pytest\n"
|
||||
f"Working directory: {self.ROOT}\n"
|
||||
"1014 passed, 6 skipped"
|
||||
),
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
|
||||
def test_bare_pytest_with_path_and_version_proof_passes(self):
|
||||
result = assess_validation_environment_proof(
|
||||
report_text=(
|
||||
"Validation command: pytest tests/\n"
|
||||
f"Working directory: {self.ROOT}\n"
|
||||
"which pytest: /repo/Gitea-Tools/venv/bin/pytest\n"
|
||||
"pytest --version: pytest 8.3.4\n"
|
||||
"Resolves to the project venv: yes\n"
|
||||
"1014 passed, 6 skipped"
|
||||
),
|
||||
)
|
||||
self.assertTrue(result["proven"])
|
||||
|
||||
def test_vague_pytest_summary_without_command_fails(self):
|
||||
result = assess_validation_environment_proof(
|
||||
report_text=(
|
||||
f"Working directory: {self.ROOT}\n"
|
||||
"pytest executed inside the worktree: 1014 passed, 6 skipped"
|
||||
),
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
|
||||
def test_structured_environment_proof_passes(self):
|
||||
result = assess_validation_environment_proof(
|
||||
validation_environment={
|
||||
"command": "pytest tests/",
|
||||
"working_directory": self.ROOT,
|
||||
"which_pytest": "/repo/Gitea-Tools/venv/bin/pytest",
|
||||
"pytest_version": "pytest 8.3.4",
|
||||
"venv_resolved": True,
|
||||
"passed": 1014,
|
||||
"skipped": 6,
|
||||
},
|
||||
)
|
||||
self.assertTrue(result["proven"])
|
||||
|
||||
def test_missing_working_directory_fails(self):
|
||||
result = assess_validation_environment_proof(
|
||||
report_text=(
|
||||
"Validation command: venv/bin/pytest tests/\n"
|
||||
"1014 passed, 6 skipped"
|
||||
),
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
|
||||
def test_build_final_report_downgrades_missing_environment_proof(self):
|
||||
report = build_final_report(
|
||||
checkout_proof=_good_checkout(),
|
||||
inventory=_good_inventory(),
|
||||
validation=_good_validation(),
|
||||
contamination=_good_contamination(),
|
||||
identity_eligible=True,
|
||||
merge_performed=False,
|
||||
issue_status_verified=True,
|
||||
capability_evidence=_good_capability_evidence(),
|
||||
sweep=_good_sweep(),
|
||||
live_state=_good_live_state(),
|
||||
role_boundary=_good_role_boundary(),
|
||||
review_mutation=_good_review_mutation(),
|
||||
controller_handoff=_good_handoff(),
|
||||
capability_proof=_good_capability_proof(),
|
||||
sweep_proof=_good_secret_sweep(),
|
||||
worktree_proof={
|
||||
"worktree_path": "/repo/branches/review-feat-issue-224",
|
||||
"porcelain_status": "",
|
||||
"pr_scope_files": ["docs/wiki/Repositories.md"],
|
||||
"scratch_used": True,
|
||||
},
|
||||
report_text=(
|
||||
f"Working directory: {self.ROOT}\n"
|
||||
"pytest executed: 1014 passed, 6 skipped"
|
||||
),
|
||||
)
|
||||
self.assertNotEqual(report["grade"], "A")
|
||||
self.assertFalse(report["validation_environment_proven"])
|
||||
|
||||
|
||||
def test_next_eligible_claim_without_policy_fails(self):
|
||||
result = assess_queue_ordering_proof(
|
||||
report_text="Selected the next eligible PR: PR #286.",
|
||||
)
|
||||
@@ -2539,5 +2641,306 @@ class TestReviewerBaselineValidationProof(unittest.TestCase):
|
||||
self.assertFalse(report["baseline_validation_proven"])
|
||||
|
||||
|
||||
class TestAlreadyLandedReviewGate(unittest.TestCase):
|
||||
"""Issue #292: PR head already on target blocks approval and merge."""
|
||||
|
||||
def _gate(self, **overrides):
|
||||
kwargs = {
|
||||
"pr_number": 278,
|
||||
"candidate_head_sha": PINNED,
|
||||
"target_branch": "master",
|
||||
"target_branch_sha": OTHER,
|
||||
"head_is_ancestor_of_target": True,
|
||||
"live_head_sha": PINNED,
|
||||
}
|
||||
kwargs.update(overrides)
|
||||
return assess_already_landed_review_gate(**kwargs)
|
||||
|
||||
def test_already_landed_blocks_approval_and_merge(self):
|
||||
result = self._gate()
|
||||
self.assertEqual(result["state"], "ALREADY_LANDED_RECONCILE_REQUIRED")
|
||||
self.assertFalse(result["approve_allowed"])
|
||||
self.assertFalse(result["merge_api_allowed"])
|
||||
self.assertFalse(result["request_changes_allowed"])
|
||||
self.assertTrue(result["reconciliation_handoff_required"])
|
||||
|
||||
def test_already_landed_with_real_blocker_allows_request_changes(self):
|
||||
result = self._gate(real_blocker=True)
|
||||
self.assertEqual(result["state"], "ALREADY_LANDED_RECONCILE_REQUIRED")
|
||||
self.assertFalse(result["approve_allowed"])
|
||||
self.assertFalse(result["merge_api_allowed"])
|
||||
self.assertTrue(result["request_changes_allowed"])
|
||||
|
||||
def test_normal_candidate_passes_gate(self):
|
||||
result = self._gate(head_is_ancestor_of_target=False)
|
||||
self.assertEqual(result["state"], "NORMAL_REVIEW_CANDIDATE")
|
||||
self.assertTrue(result["approve_allowed"])
|
||||
self.assertTrue(result["merge_api_allowed"])
|
||||
self.assertFalse(result["reconciliation_handoff_required"])
|
||||
|
||||
def test_non_mergeable_normal_pr_still_passes_this_gate(self):
|
||||
# Mergeability/conflicts are separate gates; ancestry gate only
|
||||
# decides already-landed vs normal candidate.
|
||||
result = self._gate(
|
||||
head_is_ancestor_of_target=False, mergeable=False)
|
||||
self.assertEqual(result["state"], "NORMAL_REVIEW_CANDIDATE")
|
||||
self.assertTrue(result["request_changes_allowed"])
|
||||
|
||||
def test_unchecked_ancestry_blocks_review_mutations(self):
|
||||
result = self._gate(head_is_ancestor_of_target=None)
|
||||
self.assertEqual(result["state"], "GATE_NOT_PROVEN")
|
||||
self.assertFalse(result["approve_allowed"])
|
||||
self.assertFalse(result["merge_api_allowed"])
|
||||
|
||||
def test_changed_head_since_pin_blocks_until_recheck(self):
|
||||
result = self._gate(
|
||||
head_is_ancestor_of_target=False, live_head_sha=OTHER)
|
||||
self.assertEqual(result["state"], "GATE_NOT_PROVEN")
|
||||
self.assertFalse(result["approve_allowed"])
|
||||
self.assertTrue(any(
|
||||
"head" in reason.lower() for reason in result["reasons"]
|
||||
))
|
||||
|
||||
def test_invalid_shas_block_gate(self):
|
||||
result = self._gate(candidate_head_sha="deadbeef")
|
||||
self.assertEqual(result["state"], "GATE_NOT_PROVEN")
|
||||
self.assertFalse(result["approve_allowed"])
|
||||
|
||||
result = self._gate(target_branch_sha=None)
|
||||
self.assertEqual(result["state"], "GATE_NOT_PROVEN")
|
||||
|
||||
def test_already_landed_handoff_lists_required_fields(self):
|
||||
result = self._gate()
|
||||
for field in (
|
||||
"PR number/title",
|
||||
"candidate head SHA",
|
||||
"target branch",
|
||||
"target branch SHA",
|
||||
"ancestor proof",
|
||||
"linked issue status",
|
||||
"recommended reconciliation action",
|
||||
"capability proof for close/comment mutations",
|
||||
):
|
||||
self.assertIn(field, result["required_handoff_fields"])
|
||||
|
||||
|
||||
class TestAlreadyLandedReportState(unittest.TestCase):
|
||||
"""Issue #292: reports cannot say APPROVED after the gate fired."""
|
||||
|
||||
GOOD_REPORT = (
|
||||
"Eligibility class: ALREADY_LANDED_RECONCILE_REQUIRED\n"
|
||||
"Candidate head SHA: " + PINNED + "\n"
|
||||
"Review decision: none\n"
|
||||
"Merge result: none\n"
|
||||
)
|
||||
|
||||
def test_gate_fired_with_reconcile_state_passes(self):
|
||||
result = assess_already_landed_report_state(
|
||||
self.GOOD_REPORT, gate_fired=True)
|
||||
self.assertTrue(result["complete"])
|
||||
self.assertFalse(result["block"])
|
||||
|
||||
def test_gate_fired_with_approved_state_blocks(self):
|
||||
report = self.GOOD_REPORT.replace(
|
||||
"Review decision: none", "Review decision: APPROVED")
|
||||
result = assess_already_landed_report_state(report, gate_fired=True)
|
||||
self.assertTrue(result["block"])
|
||||
|
||||
def test_gate_fired_with_merged_state_blocks(self):
|
||||
report = self.GOOD_REPORT.replace(
|
||||
"Merge result: none", "Merge result: MERGED")
|
||||
result = assess_already_landed_report_state(report, gate_fired=True)
|
||||
self.assertTrue(result["block"])
|
||||
|
||||
def test_gate_fired_with_ready_to_merge_blocks(self):
|
||||
result = assess_already_landed_report_state(
|
||||
self.GOOD_REPORT + "Current status: READY_TO_MERGE\n",
|
||||
gate_fired=True)
|
||||
self.assertTrue(result["block"])
|
||||
|
||||
def test_gate_fired_without_reconcile_state_blocks(self):
|
||||
result = assess_already_landed_report_state(
|
||||
"Current status: review complete.\n", gate_fired=True)
|
||||
self.assertTrue(result["block"])
|
||||
self.assertTrue(any(
|
||||
"already_landed_reconcile_required" in reason.lower()
|
||||
for reason in result["reasons"]
|
||||
))
|
||||
|
||||
def test_gate_not_fired_reports_pass_untouched(self):
|
||||
result = assess_already_landed_report_state(
|
||||
"Review decision: APPROVED\nMerge result: MERGED\n",
|
||||
gate_fired=False)
|
||||
self.assertTrue(result["complete"])
|
||||
|
||||
|
||||
class TestFullSuiteFailureApprovalGate(unittest.TestCase):
|
||||
"""Issue #323: full-suite failure blocks approval without baseline proof."""
|
||||
|
||||
ROOT = "/repo/Gitea-Tools"
|
||||
|
||||
def _good_proof(self, **overrides):
|
||||
proof = {
|
||||
"worktree_path": f"{self.ROOT}/branches/baseline-master-pr280",
|
||||
"baseline_target_sha": PINNED,
|
||||
"pr_head_sha": OTHER,
|
||||
"baseline_failures": ["tests/test_foo.py::test_bar"],
|
||||
"pr_failures": ["tests/test_foo.py::test_bar"],
|
||||
"failure_signatures_match": True,
|
||||
"clean_before": True,
|
||||
"clean_after": True,
|
||||
"pr_suite_command": "venv/bin/pytest tests/",
|
||||
"baseline_suite_command": "venv/bin/pytest tests/",
|
||||
"new_tests_passed": True,
|
||||
"unrelated_explanation": (
|
||||
"failures touch agent_temp_artifacts only; PR changes "
|
||||
"review_proofs handoff fields"
|
||||
),
|
||||
}
|
||||
proof.update(overrides)
|
||||
return proof
|
||||
|
||||
def _good_report(self):
|
||||
return (
|
||||
"Full suite failed on PR worktree and on baseline.\n"
|
||||
"- Validation command: venv/bin/pytest tests/\n"
|
||||
f"- Working directory: {self.ROOT}/branches/review-pr-280\n"
|
||||
"Failures are pre-existing on master.\n"
|
||||
)
|
||||
|
||||
def test_full_suite_pass_allows_approval_without_baseline(self):
|
||||
result = assess_full_suite_failure_approval_gate(
|
||||
review_decision="approve",
|
||||
full_suite_passed=True,
|
||||
project_root=self.ROOT,
|
||||
)
|
||||
self.assertTrue(result["approve_allowed"])
|
||||
self.assertFalse(result["block"])
|
||||
self.assertEqual(result["default_action"], "proceed")
|
||||
|
||||
def test_full_suite_failure_defaults_to_request_changes(self):
|
||||
result = assess_full_suite_failure_approval_gate(
|
||||
review_decision="request_changes",
|
||||
full_suite_passed=False,
|
||||
project_root=self.ROOT,
|
||||
)
|
||||
self.assertFalse(result["block"])
|
||||
self.assertEqual(result["default_action"], "request_changes")
|
||||
|
||||
def test_approval_with_failure_and_no_proof_blocks(self):
|
||||
result = assess_full_suite_failure_approval_gate(
|
||||
review_decision="approve",
|
||||
full_suite_passed=False,
|
||||
project_root=self.ROOT,
|
||||
)
|
||||
self.assertFalse(result["approve_allowed"])
|
||||
self.assertTrue(result["block"])
|
||||
self.assertEqual(result["default_action"], "request_changes")
|
||||
|
||||
def test_approval_with_matching_baseline_proof_allowed(self):
|
||||
result = assess_full_suite_failure_approval_gate(
|
||||
review_decision="approve",
|
||||
full_suite_passed=False,
|
||||
baseline_proof=self._good_proof(),
|
||||
report_text=self._good_report(),
|
||||
project_root=self.ROOT,
|
||||
)
|
||||
self.assertTrue(result["approve_allowed"])
|
||||
self.assertFalse(result["block"])
|
||||
|
||||
def test_mismatched_failure_signatures_block_approval(self):
|
||||
result = assess_full_suite_failure_approval_gate(
|
||||
review_decision="approve",
|
||||
full_suite_passed=False,
|
||||
baseline_proof=self._good_proof(
|
||||
failure_signatures_match=False,
|
||||
pr_failures=["tests/test_other.py::test_other"],
|
||||
),
|
||||
report_text=self._good_report(),
|
||||
project_root=self.ROOT,
|
||||
)
|
||||
self.assertFalse(result["approve_allowed"])
|
||||
self.assertTrue(result["block"])
|
||||
|
||||
def test_main_checkout_baseline_blocks_approval(self):
|
||||
result = assess_full_suite_failure_approval_gate(
|
||||
review_decision="approve",
|
||||
full_suite_passed=False,
|
||||
baseline_proof=self._good_proof(worktree_path=self.ROOT),
|
||||
report_text=self._good_report(),
|
||||
project_root=self.ROOT,
|
||||
)
|
||||
self.assertFalse(result["approve_allowed"])
|
||||
self.assertTrue(result["block"])
|
||||
|
||||
def test_missing_new_tests_proof_blocks_approval(self):
|
||||
result = assess_full_suite_failure_approval_gate(
|
||||
review_decision="approve",
|
||||
full_suite_passed=False,
|
||||
baseline_proof=self._good_proof(new_tests_passed=None),
|
||||
report_text=self._good_report(),
|
||||
project_root=self.ROOT,
|
||||
)
|
||||
self.assertFalse(result["approve_allowed"])
|
||||
self.assertTrue(any(
|
||||
"new" in reason.lower() and "test" in reason.lower()
|
||||
for reason in result["reasons"]
|
||||
))
|
||||
|
||||
def test_missing_unrelated_explanation_blocks_approval(self):
|
||||
result = assess_full_suite_failure_approval_gate(
|
||||
review_decision="approve",
|
||||
full_suite_passed=False,
|
||||
baseline_proof=self._good_proof(unrelated_explanation=""),
|
||||
report_text=self._good_report(),
|
||||
project_root=self.ROOT,
|
||||
)
|
||||
self.assertFalse(result["approve_allowed"])
|
||||
|
||||
def test_missing_suite_commands_block_approval(self):
|
||||
result = assess_full_suite_failure_approval_gate(
|
||||
review_decision="approve",
|
||||
full_suite_passed=False,
|
||||
baseline_proof=self._good_proof(
|
||||
pr_suite_command="", baseline_suite_command=""),
|
||||
report_text=self._good_report(),
|
||||
project_root=self.ROOT,
|
||||
)
|
||||
self.assertFalse(result["approve_allowed"])
|
||||
self.assertTrue(any(
|
||||
"command" in reason.lower() for reason in result["reasons"]
|
||||
))
|
||||
|
||||
def test_unknown_suite_result_blocks_approval(self):
|
||||
result = assess_full_suite_failure_approval_gate(
|
||||
review_decision="approve",
|
||||
full_suite_passed=None,
|
||||
project_root=self.ROOT,
|
||||
)
|
||||
self.assertFalse(result["approve_allowed"])
|
||||
self.assertTrue(result["block"])
|
||||
|
||||
def test_vague_same_as_master_claim_without_proof_blocks(self):
|
||||
result = assess_full_suite_failure_approval_gate(
|
||||
review_decision="approve",
|
||||
full_suite_passed=False,
|
||||
report_text="Validation: failures same as master; approving.",
|
||||
project_root=self.ROOT,
|
||||
)
|
||||
self.assertFalse(result["approve_allowed"])
|
||||
self.assertTrue(result["block"])
|
||||
|
||||
def test_non_approve_decision_never_blocks(self):
|
||||
result = assess_full_suite_failure_approval_gate(
|
||||
review_decision="comment",
|
||||
full_suite_passed=None,
|
||||
project_root=self.ROOT,
|
||||
)
|
||||
self.assertFalse(result["block"])
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
|
||||
@@ -0,0 +1,139 @@
|
||||
"""Tests for prior-blocker skip proof verifier (#318)."""
|
||||
import sys
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
|
||||
|
||||
from reviewer_blocker_skip import assess_prior_blocker_skip_proof # noqa: E402
|
||||
|
||||
HEAD_CURRENT = "0fdc8f582026b72a229d59a172c0a63ac4aaeaf9"
|
||||
HEAD_BLOCKER = "1111111111111111111111111111111111111111"
|
||||
|
||||
|
||||
def _good_blocker_skip_report(pr_number: int) -> str:
|
||||
return "\n".join([
|
||||
f"Skipped PR #{pr_number} due to prior REQUEST_CHANGES.",
|
||||
f"- PR number: #{pr_number}",
|
||||
f"- Current head SHA: {HEAD_CURRENT}",
|
||||
"- Blocking review decision: request_changes",
|
||||
f"- Blocking review head SHA: {HEAD_CURRENT}",
|
||||
"- Head unchanged since blocker",
|
||||
"- Reason remains blocked: unresolved review feedback at same head",
|
||||
"- Blocker revalidated live in this session via gitea_get_pr_review_feedback",
|
||||
])
|
||||
|
||||
|
||||
class TestPriorBlockerSkipProof(unittest.TestCase):
|
||||
def test_no_skips_passes(self):
|
||||
result = assess_prior_blocker_skip_proof(
|
||||
"Selected PR #281 for review.",
|
||||
skipped_prs=[],
|
||||
)
|
||||
self.assertTrue(result["proven"])
|
||||
|
||||
def test_blocked_unchanged_with_live_proof_passes(self):
|
||||
report = _good_blocker_skip_report(280)
|
||||
result = assess_prior_blocker_skip_proof(
|
||||
report,
|
||||
skipped_prs=[{
|
||||
"pr_number": 280,
|
||||
"head_sha": HEAD_CURRENT,
|
||||
"blocking_decision": "request_changes",
|
||||
"blocking_review_head_sha": HEAD_CURRENT,
|
||||
"head_changed_since_blocker": False,
|
||||
"blocker_verified": True,
|
||||
}],
|
||||
)
|
||||
self.assertTrue(result["proven"])
|
||||
|
||||
def test_head_changed_after_blocker_blocks_skip(self):
|
||||
result = assess_prior_blocker_skip_proof(
|
||||
_good_blocker_skip_report(280),
|
||||
skipped_prs=[{
|
||||
"pr_number": 280,
|
||||
"head_sha": HEAD_CURRENT,
|
||||
"blocking_decision": "request_changes",
|
||||
"blocking_review_head_sha": HEAD_BLOCKER,
|
||||
"head_changed_since_blocker": True,
|
||||
"blocker_verified": True,
|
||||
}],
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
self.assertTrue(any("head changed" in r for r in result["reasons"]))
|
||||
|
||||
def test_missing_live_proof_blocks(self):
|
||||
report = _good_blocker_skip_report(280).replace(
|
||||
"- Blocker revalidated live in this session via gitea_get_pr_review_feedback",
|
||||
"",
|
||||
)
|
||||
result = assess_prior_blocker_skip_proof(
|
||||
report,
|
||||
skipped_prs=[{
|
||||
"pr_number": 280,
|
||||
"head_sha": HEAD_CURRENT,
|
||||
"blocking_decision": "request_changes",
|
||||
"blocking_review_head_sha": HEAD_CURRENT,
|
||||
"head_changed_since_blocker": False,
|
||||
"blocker_verified": True,
|
||||
}],
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
self.assertTrue(any("live blocker proof" in r for r in result["reasons"]))
|
||||
|
||||
def test_blocker_unverified_classification_passes(self):
|
||||
report = "\n".join([
|
||||
"Skipped PR #280.",
|
||||
"Classification: BLOCKER_STATUS_UNVERIFIED",
|
||||
"Review feedback could not be fetched live in this session.",
|
||||
])
|
||||
result = assess_prior_blocker_skip_proof(
|
||||
report,
|
||||
skipped_prs=[{
|
||||
"pr_number": 280,
|
||||
"blocking_decision": "request_changes",
|
||||
"blocker_verified": False,
|
||||
}],
|
||||
)
|
||||
self.assertTrue(result["proven"])
|
||||
|
||||
def test_unverified_without_classification_blocks(self):
|
||||
result = assess_prior_blocker_skip_proof(
|
||||
"Skipped PR #280 based on memory from last session.",
|
||||
skipped_prs=[{
|
||||
"pr_number": 280,
|
||||
"blocking_decision": "request_changes",
|
||||
"blocker_verified": False,
|
||||
}],
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
self.assertTrue(any("BLOCKER_STATUS_UNVERIFIED" in r for r in result["reasons"]))
|
||||
|
||||
def test_missing_blocking_head_sha_blocks(self):
|
||||
report = _good_blocker_skip_report(280).replace(
|
||||
f"- Blocking review head SHA: {HEAD_CURRENT}",
|
||||
"",
|
||||
)
|
||||
result = assess_prior_blocker_skip_proof(
|
||||
report,
|
||||
skipped_prs=[{
|
||||
"pr_number": 280,
|
||||
"head_sha": HEAD_CURRENT,
|
||||
"blocking_decision": "request_changes",
|
||||
"blocking_review_head_sha": HEAD_CURRENT,
|
||||
"head_changed_since_blocker": False,
|
||||
"blocker_verified": True,
|
||||
}],
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
|
||||
|
||||
class TestExport(unittest.TestCase):
|
||||
def test_review_proofs_reexport(self):
|
||||
from review_proofs import assess_prior_blocker_skip_proof as exported
|
||||
|
||||
self.assertTrue(callable(exported))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,135 @@
|
||||
"""Tests for merge-simulation worktree mutation verifier (#317)."""
|
||||
import sys
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
|
||||
|
||||
from reviewer_merge_simulation import ( # noqa: E402
|
||||
assess_merge_simulation_report,
|
||||
merge_simulation_commands,
|
||||
)
|
||||
|
||||
|
||||
def _good_simulation_report(**overrides) -> str:
|
||||
lines = [
|
||||
"Worktree/index mutations: merge simulation in branches/review-pr281",
|
||||
"Worktree path: branches/review-pr281",
|
||||
"Pre-simulation clean status: clean (git status --porcelain empty)",
|
||||
"Merge result: conflicts in review_proofs.py",
|
||||
"Abort command: git merge --abort",
|
||||
"Post-abort clean status: clean after abort (git status --porcelain empty)",
|
||||
]
|
||||
text = "\n".join(lines)
|
||||
for key, value in overrides.items():
|
||||
text = text.replace(f"{key}:", f"{key}: {value}")
|
||||
return text
|
||||
|
||||
|
||||
class TestMergeSimulationDetection(unittest.TestCase):
|
||||
def test_detects_no_commit_merge(self):
|
||||
commands = merge_simulation_commands([
|
||||
"git merge prgs/master --no-commit --no-ff",
|
||||
"git status",
|
||||
])
|
||||
self.assertEqual(commands, ["git merge prgs/master --no-commit --no-ff"])
|
||||
|
||||
def test_detects_merge_abort(self):
|
||||
commands = merge_simulation_commands([
|
||||
"git merge prgs/master --no-commit --no-ff",
|
||||
"git merge --abort",
|
||||
])
|
||||
self.assertIn("git merge --abort", commands)
|
||||
|
||||
|
||||
class TestMergeSimulationReport(unittest.TestCase):
|
||||
def test_no_simulation_passes(self):
|
||||
result = assess_merge_simulation_report(
|
||||
"Review complete. Worktree/index mutations: none",
|
||||
command_log=["git status --porcelain", "git diff prgs/master...HEAD"],
|
||||
)
|
||||
self.assertTrue(result["proven"])
|
||||
|
||||
def test_documented_simulation_passes(self):
|
||||
report = _good_simulation_report()
|
||||
result = assess_merge_simulation_report(
|
||||
report,
|
||||
command_log=[
|
||||
"git merge prgs/master --no-commit --no-ff",
|
||||
"git merge --abort",
|
||||
],
|
||||
)
|
||||
self.assertTrue(result["proven"], result["reasons"])
|
||||
|
||||
def test_readonly_classification_blocks(self):
|
||||
report = "\n".join([
|
||||
"Read-only diagnostics: git merge prgs/master --no-commit --no-ff, git status",
|
||||
"Worktree/index mutations: none",
|
||||
])
|
||||
result = assess_merge_simulation_report(
|
||||
report,
|
||||
command_log=["git merge prgs/master --no-commit --no-ff"],
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
self.assertTrue(result["block"])
|
||||
self.assertTrue(any("read-only" in r.lower() for r in result["reasons"]))
|
||||
|
||||
def test_missing_worktree_field_blocks(self):
|
||||
report = "Merge simulation ran but only noted in prose."
|
||||
result = assess_merge_simulation_report(
|
||||
report,
|
||||
command_log=["git merge prgs/master --no-commit --no-ff"],
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
self.assertTrue(any("worktree/index mutations" in r.lower() for r in result["reasons"]))
|
||||
|
||||
def test_conflict_simulation_requires_merge_result(self):
|
||||
report = _good_simulation_report().replace(
|
||||
"Merge result: conflicts in review_proofs.py",
|
||||
"",
|
||||
)
|
||||
result = assess_merge_simulation_report(
|
||||
report,
|
||||
command_log=["git merge prgs/master --no-commit --no-ff"],
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
self.assertTrue(any("merge result" in r.lower() for r in result["reasons"]))
|
||||
|
||||
def test_aborted_simulation_requires_post_clean_proof(self):
|
||||
report = _good_simulation_report().replace(
|
||||
"Post-abort clean status: clean after abort (git status --porcelain empty)",
|
||||
"",
|
||||
)
|
||||
result = assess_merge_simulation_report(
|
||||
report,
|
||||
command_log=[
|
||||
"git merge prgs/master --no-commit --no-ff",
|
||||
"git merge --abort",
|
||||
],
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
self.assertTrue(any("post-abort" in r.lower() for r in result["reasons"]))
|
||||
|
||||
def test_successful_simulation_without_abort_omits_abort_fields(self):
|
||||
report = "\n".join([
|
||||
"Worktree/index mutations: merge simulation completed cleanly",
|
||||
"Worktree path: branches/review-pr281",
|
||||
"Pre-simulation clean status: clean before simulation",
|
||||
"Merge result: clean fast-forward simulation",
|
||||
])
|
||||
result = assess_merge_simulation_report(
|
||||
report,
|
||||
command_log=["git merge prgs/master --no-commit --no-ff"],
|
||||
)
|
||||
self.assertTrue(result["proven"], result["reasons"])
|
||||
|
||||
|
||||
class TestExport(unittest.TestCase):
|
||||
def test_review_proofs_reexport(self):
|
||||
from review_proofs import assess_merge_simulation_report as exported
|
||||
|
||||
self.assertTrue(callable(exported))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,88 @@
|
||||
"""Tests for precise mutation category verifier (#319)."""
|
||||
import sys
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
|
||||
|
||||
from reviewer_mutation_categories import assess_mutation_categories_report # noqa: E402
|
||||
|
||||
|
||||
def _precise_handoff() -> str:
|
||||
return "\n".join([
|
||||
"Controller Handoff",
|
||||
"File edits by reviewer: none",
|
||||
"Worktree/index mutations: git worktree add branches/review-pr1",
|
||||
"Git ref mutations: git fetch prgs master",
|
||||
"MCP/Gitea mutations: gitea_view_pr",
|
||||
"Review mutations: gitea_review_pr request_changes",
|
||||
"Read-only diagnostics: git status, git diff",
|
||||
])
|
||||
|
||||
|
||||
class TestMutationCategories(unittest.TestCase):
|
||||
def test_precise_categories_pass(self):
|
||||
result = assess_mutation_categories_report(_precise_handoff())
|
||||
self.assertTrue(result["proven"], result["reasons"])
|
||||
|
||||
def test_legacy_workspace_mutations_blocks(self):
|
||||
report = "\n".join([
|
||||
"Controller Handoff",
|
||||
"Workspace mutations: none (no local file changes)",
|
||||
"File edits by reviewer: none",
|
||||
"Worktree/index mutations: none",
|
||||
"Git ref mutations: none",
|
||||
])
|
||||
result = assess_mutation_categories_report(report)
|
||||
self.assertFalse(result["proven"])
|
||||
self.assertTrue(any("workspace mutations" in r.lower() for r in result["reasons"]))
|
||||
|
||||
def test_workspace_none_with_worktree_command_blocks(self):
|
||||
report = "\n".join([
|
||||
"Controller Handoff",
|
||||
"Workspace mutations: none (no local file changes)",
|
||||
"File edits by reviewer: none",
|
||||
"Worktree/index mutations: none",
|
||||
"Git ref mutations: none",
|
||||
])
|
||||
result = assess_mutation_categories_report(
|
||||
report,
|
||||
observed_commands=["git reset --hard FETCH_HEAD"],
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
|
||||
def test_file_edits_none_with_worktree_mutation_passes(self):
|
||||
report = "\n".join([
|
||||
"Controller Handoff",
|
||||
"File edits by reviewer: none",
|
||||
"Worktree/index mutations: git reset --hard FETCH_HEAD",
|
||||
"Git ref mutations: git fetch prgs",
|
||||
])
|
||||
result = assess_mutation_categories_report(
|
||||
report,
|
||||
observed_commands=["git reset --hard FETCH_HEAD", "git fetch prgs"],
|
||||
)
|
||||
self.assertTrue(result["proven"], result["reasons"])
|
||||
|
||||
def test_missing_required_categories_blocks(self):
|
||||
report = "Controller Handoff\nFile edits by reviewer: none\n"
|
||||
result = assess_mutation_categories_report(report)
|
||||
self.assertFalse(result["proven"])
|
||||
self.assertTrue(any("missing" in r.lower() for r in result["reasons"]))
|
||||
|
||||
def test_non_controller_handoff_skips(self):
|
||||
result = assess_mutation_categories_report(
|
||||
"Workspace mutations: none\n",
|
||||
)
|
||||
self.assertTrue(result["proven"])
|
||||
|
||||
|
||||
class TestExport(unittest.TestCase):
|
||||
def test_review_proofs_reexport(self):
|
||||
from review_proofs import assess_mutation_categories_report as exported
|
||||
|
||||
self.assertTrue(callable(exported))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,130 @@
|
||||
"""Tests for PR-head vs diagnostic validation integrity verifier (#316)."""
|
||||
import sys
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
|
||||
|
||||
from reviewer_validation_integrity import assess_validation_integrity_report # noqa: E402
|
||||
|
||||
|
||||
def _official_only_report() -> str:
|
||||
return "\n".join([
|
||||
"Official PR-head validation on unmodified worktree.",
|
||||
"Official validation command: pytest tests/ -q",
|
||||
"Official validation result: failed (3 failed)",
|
||||
"Validation integrity status: failed",
|
||||
"Worktree dirty after official validation: clean",
|
||||
"Review decision: request_changes",
|
||||
])
|
||||
|
||||
|
||||
def _diagnostic_report() -> str:
|
||||
return "\n".join([
|
||||
_official_only_report(),
|
||||
"Diagnostic local experiment — not PR-head validation",
|
||||
"Diagnostic edit path: tests/test_example.py",
|
||||
"File edits by reviewer: tests/test_example.py",
|
||||
"Diagnostic command: pytest tests/test_example.py -q",
|
||||
"Diagnostic result: passed after local fix",
|
||||
"Diagnostic results used only for suggested fix; blocker remains PR-head failure.",
|
||||
])
|
||||
|
||||
|
||||
class TestValidationIntegrity(unittest.TestCase):
|
||||
def test_official_only_passes(self):
|
||||
result = assess_validation_integrity_report(
|
||||
_official_only_report(),
|
||||
validation_session={
|
||||
"official_validation_ran": True,
|
||||
"official_result": "fail",
|
||||
"worktree_dirty_after_official": False,
|
||||
},
|
||||
)
|
||||
self.assertTrue(result["proven"], result["reasons"])
|
||||
|
||||
def test_failing_pr_head_with_diagnostic_pass_passes(self):
|
||||
result = assess_validation_integrity_report(
|
||||
_diagnostic_report(),
|
||||
validation_session={
|
||||
"official_validation_ran": True,
|
||||
"official_result": "fail",
|
||||
"diagnostic_validation_ran": True,
|
||||
"diagnostic_result": "pass",
|
||||
"diagnostic_edits": ["tests/test_example.py"],
|
||||
"worktree_dirty_after_official": False,
|
||||
},
|
||||
)
|
||||
self.assertTrue(result["proven"], result["reasons"])
|
||||
|
||||
def test_post_edit_tests_as_official_blocks(self):
|
||||
report = "\n".join([
|
||||
"Official validation result: passed after diagnostic edit",
|
||||
"pytest passed after local fix in validation worktree",
|
||||
])
|
||||
result = assess_validation_integrity_report(
|
||||
report,
|
||||
validation_session={
|
||||
"official_validation_ran": True,
|
||||
"diagnostic_edits": ["tests/test_example.py"],
|
||||
"diagnostic_validation_ran": True,
|
||||
},
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
self.assertTrue(result["block"])
|
||||
|
||||
def test_missing_dirty_after_validation_blocks(self):
|
||||
report = _official_only_report().replace(
|
||||
"Worktree dirty after official validation: clean",
|
||||
"",
|
||||
)
|
||||
result = assess_validation_integrity_report(
|
||||
report,
|
||||
validation_session={"official_validation_ran": True, "official_result": "fail"},
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
self.assertTrue(any("dirty" in r.lower() for r in result["reasons"]))
|
||||
|
||||
def test_diagnostic_without_label_blocks(self):
|
||||
report = _diagnostic_report().replace(
|
||||
"Diagnostic local experiment — not PR-head validation",
|
||||
"",
|
||||
)
|
||||
result = assess_validation_integrity_report(
|
||||
report,
|
||||
validation_session={
|
||||
"official_validation_ran": True,
|
||||
"diagnostic_edits": ["tests/test_example.py"],
|
||||
"diagnostic_validation_ran": True,
|
||||
},
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
self.assertTrue(any("diagnostic" in r.lower() for r in result["reasons"]))
|
||||
|
||||
def test_contaminated_requires_integrity_status(self):
|
||||
report = "Validation worktree was edited before official validation completed."
|
||||
result = assess_validation_integrity_report(
|
||||
report,
|
||||
validation_session={"contaminated": True, "official_validation_ran": True},
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
self.assertTrue(any("contaminated" in r.lower() for r in result["reasons"]))
|
||||
|
||||
def test_action_log_edits_trigger_diagnostic_rules(self):
|
||||
result = assess_validation_integrity_report(
|
||||
_official_only_report(),
|
||||
validation_session={"official_validation_ran": True, "official_result": "fail"},
|
||||
action_log=[{"path": "tests/test_example.py", "kind": "file_edit", "performed": True}],
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
|
||||
|
||||
class TestExport(unittest.TestCase):
|
||||
def test_review_proofs_reexport(self):
|
||||
from review_proofs import assess_validation_integrity_report as exported
|
||||
|
||||
self.assertTrue(callable(exported))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,134 @@
|
||||
"""Tests for PR validation worktree no-edit verifier (#315)."""
|
||||
import sys
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
|
||||
|
||||
from reviewer_validation_worktree_edits import ( # noqa: E402
|
||||
assess_validation_worktree_edit_report,
|
||||
)
|
||||
|
||||
|
||||
def _read_only_report() -> str:
|
||||
return "\n".join([
|
||||
"Validation worktree path: branches/review-pr280-feat-issue-275-claim",
|
||||
"Official PR-head validation on unmodified worktree.",
|
||||
"Official validation result: failed (1 failed)",
|
||||
"File edits by reviewer: none",
|
||||
"Review decision: request_changes",
|
||||
])
|
||||
|
||||
|
||||
def _diagnostic_report() -> str:
|
||||
return "\n".join([
|
||||
"Validation worktree path: branches/review-pr280-feat-issue-275-claim",
|
||||
"Official PR-head validation on unmodified worktree.",
|
||||
"Official validation result: failed (1 failed)",
|
||||
"Review decision: request_changes",
|
||||
"Diagnostic local experiment — not PR-head validation",
|
||||
"Diagnostic scratch worktree path: branches/diagnostic-pr280-fix-test",
|
||||
"File edits by reviewer: tests/test_agent_temp_artifacts.py (diagnostic only)",
|
||||
"Diagnostic result: passed after local fix",
|
||||
])
|
||||
|
||||
|
||||
class TestValidationWorktreeEdits(unittest.TestCase):
|
||||
def test_read_only_review_passes(self):
|
||||
result = assess_validation_worktree_edit_report(
|
||||
_read_only_report(),
|
||||
validation_session={
|
||||
"validation_worktree_path": (
|
||||
"branches/review-pr280-feat-issue-275-claim"
|
||||
),
|
||||
},
|
||||
)
|
||||
self.assertTrue(result["proven"], result["reasons"])
|
||||
|
||||
def test_validation_worktree_edit_blocks(self):
|
||||
result = assess_validation_worktree_edit_report(
|
||||
_read_only_report(),
|
||||
validation_session={
|
||||
"validation_worktree_path": (
|
||||
"branches/review-pr280-feat-issue-275-claim"
|
||||
),
|
||||
"validation_worktree_edits": ["tests/test_agent_temp_artifacts.py"],
|
||||
},
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
self.assertTrue(result["block"])
|
||||
self.assertTrue(any("validation worktree" in r.lower() for r in result["reasons"]))
|
||||
|
||||
def test_file_edits_none_contradiction_blocks(self):
|
||||
result = assess_validation_worktree_edit_report(
|
||||
_read_only_report(),
|
||||
validation_session={
|
||||
"validation_worktree_path": (
|
||||
"branches/review-pr280-feat-issue-275-claim"
|
||||
),
|
||||
},
|
||||
action_log=[
|
||||
{
|
||||
"path": "tests/test_agent_temp_artifacts.py",
|
||||
"kind": "file_edit",
|
||||
"performed": True,
|
||||
"worktree_path": "branches/review-pr280-feat-issue-275-claim",
|
||||
}
|
||||
],
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
self.assertTrue(any("file edits" in r.lower() for r in result["reasons"]))
|
||||
|
||||
def test_diagnostic_scratch_with_reporting_passes(self):
|
||||
result = assess_validation_worktree_edit_report(
|
||||
_diagnostic_report(),
|
||||
validation_session={
|
||||
"validation_worktree_path": (
|
||||
"branches/review-pr280-feat-issue-275-claim"
|
||||
),
|
||||
"diagnostic_worktree_path": "branches/diagnostic-pr280-fix-test",
|
||||
"diagnostic_edits": ["tests/test_agent_temp_artifacts.py"],
|
||||
"diagnostic_experiment": True,
|
||||
},
|
||||
)
|
||||
self.assertTrue(result["proven"], result["reasons"])
|
||||
|
||||
def test_diagnostic_without_scratch_worktree_blocks(self):
|
||||
result = assess_validation_worktree_edit_report(
|
||||
"File edits by reviewer: tests/test_example.py",
|
||||
validation_session={
|
||||
"diagnostic_edits": ["tests/test_example.py"],
|
||||
"diagnostic_experiment": True,
|
||||
},
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
self.assertTrue(any("diagnostic" in r.lower() for r in result["reasons"]))
|
||||
|
||||
def test_post_edit_official_validation_blocks(self):
|
||||
report = "\n".join([
|
||||
"Validation worktree path: branches/review-pr280-feat-issue-275-claim",
|
||||
"Official validation result: passed after local edit",
|
||||
"File edits by reviewer: tests/test_agent_temp_artifacts.py",
|
||||
])
|
||||
result = assess_validation_worktree_edit_report(
|
||||
report,
|
||||
validation_session={
|
||||
"validation_worktree_path": (
|
||||
"branches/review-pr280-feat-issue-275-claim"
|
||||
),
|
||||
"validation_worktree_edits": ["tests/test_agent_temp_artifacts.py"],
|
||||
"official_validation_after_edit": True,
|
||||
},
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
|
||||
|
||||
class TestExport(unittest.TestCase):
|
||||
def test_review_proofs_reexport(self):
|
||||
from review_proofs import assess_validation_worktree_edit_report as exported
|
||||
|
||||
self.assertTrue(callable(exported))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,137 @@
|
||||
"""Tests for reviewer worktree ownership verifier (#312)."""
|
||||
import sys
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
|
||||
|
||||
from reviewer_worktree_ownership import assess_worktree_ownership_report # noqa: E402
|
||||
|
||||
|
||||
def _fresh_review_report() -> str:
|
||||
return "\n".join([
|
||||
"Review worktree path: branches/review-pr280-feat-issue-275-claim",
|
||||
"Worktree is inside branches/ and not the main checkout.",
|
||||
"Tracked state: clean; untracked state: clean.",
|
||||
"Official PR-head validation on session-owned worktree.",
|
||||
"Worktree mutations: none",
|
||||
])
|
||||
|
||||
|
||||
def _safe_reuse_report() -> str:
|
||||
return "\n".join([
|
||||
"Safe-reuse proof for existing review worktree.",
|
||||
"Review worktree path: branches/docs-issue-260-forbid-commit-fallbacks",
|
||||
"Worktree inside branches/; not the main checkout.",
|
||||
"Not owned by another active task/session.",
|
||||
"Clean tracked state; clean untracked state.",
|
||||
"Branch/head before reset: feat/issue-260-example",
|
||||
"Reset target SHA: abc123def4567890abcdef1234567890abcdef12",
|
||||
"Project policy allows reuse/reset for this clean review worktree.",
|
||||
"Worktree mutations: git reset --hard FETCH_HEAD",
|
||||
"Destructive reset operations: git reset --hard FETCH_HEAD",
|
||||
])
|
||||
|
||||
|
||||
class TestWorktreeOwnership(unittest.TestCase):
|
||||
def test_fresh_session_owned_passes(self):
|
||||
result = assess_worktree_ownership_report(
|
||||
_fresh_review_report(),
|
||||
ownership_session={
|
||||
"validation_ran": True,
|
||||
"worktree_path": "branches/review-pr280-feat-issue-275-claim",
|
||||
},
|
||||
)
|
||||
self.assertTrue(result["proven"], result["reasons"])
|
||||
self.assertTrue(result["session_owned"])
|
||||
|
||||
def test_safe_reuse_with_reset_passes(self):
|
||||
result = assess_worktree_ownership_report(
|
||||
_safe_reuse_report(),
|
||||
ownership_session={
|
||||
"safe_reuse": True,
|
||||
"worktree_path": "branches/docs-issue-260-forbid-commit-fallbacks",
|
||||
},
|
||||
command_log=["git reset --hard FETCH_HEAD"],
|
||||
)
|
||||
self.assertTrue(result["proven"], result["reasons"])
|
||||
|
||||
def test_destructive_reset_without_proof_blocks(self):
|
||||
report = "\n".join([
|
||||
"Review worktree path: branches/docs-issue-260-forbid-commit-fallbacks",
|
||||
"Worktree mutations: git reset --hard FETCH_HEAD",
|
||||
])
|
||||
result = assess_worktree_ownership_report(
|
||||
report,
|
||||
ownership_session={
|
||||
"validation_ran": True,
|
||||
"worktree_path": "branches/docs-issue-260-forbid-commit-fallbacks",
|
||||
},
|
||||
command_log=["git reset --hard FETCH_HEAD"],
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
self.assertTrue(result["block"])
|
||||
|
||||
def test_reused_dirty_tracked_blocks(self):
|
||||
result = assess_worktree_ownership_report(
|
||||
_fresh_review_report(),
|
||||
ownership_session={
|
||||
"validation_ran": True,
|
||||
"worktree_path": "branches/review-pr280-feat-issue-275-claim",
|
||||
"dirty_tracked": True,
|
||||
},
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
self.assertTrue(any("tracked" in r.lower() for r in result["reasons"]))
|
||||
|
||||
def test_safe_reuse_dirty_untracked_blocks(self):
|
||||
result = assess_worktree_ownership_report(
|
||||
_safe_reuse_report(),
|
||||
ownership_session={
|
||||
"safe_reuse": True,
|
||||
"dirty_untracked": True,
|
||||
"worktree_path": "branches/docs-issue-260-forbid-commit-fallbacks",
|
||||
},
|
||||
command_log=["git reset --hard FETCH_HEAD"],
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
self.assertTrue(any("untracked" in r.lower() for r in result["reasons"]))
|
||||
|
||||
def test_workspace_none_with_reset_blocks(self):
|
||||
report = "\n".join([
|
||||
"Review worktree path: branches/review-pr280-feat-issue-275-claim",
|
||||
"Workspace mutations: none",
|
||||
"Worktree mutations: git reset --hard FETCH_HEAD",
|
||||
])
|
||||
result = assess_worktree_ownership_report(
|
||||
report,
|
||||
ownership_session={
|
||||
"session_owned": True,
|
||||
"worktree_path": "branches/review-pr280-feat-issue-275-claim",
|
||||
},
|
||||
command_log=["git reset --hard FETCH_HEAD"],
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
self.assertTrue(any("workspace mutations" in r.lower() for r in result["reasons"]))
|
||||
|
||||
def test_main_checkout_blocks(self):
|
||||
result = assess_worktree_ownership_report(
|
||||
"Review worktree path: /Users/dev/Gitea-Tools",
|
||||
ownership_session={
|
||||
"validation_ran": True,
|
||||
"main_checkout": True,
|
||||
"worktree_path": "/Users/dev/Gitea-Tools",
|
||||
},
|
||||
)
|
||||
self.assertFalse(result["proven"])
|
||||
|
||||
|
||||
class TestExport(unittest.TestCase):
|
||||
def test_review_proofs_reexport(self):
|
||||
from review_proofs import assess_worktree_ownership_report as exported
|
||||
|
||||
self.assertTrue(callable(exported))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
Reference in New Issue
Block a user