diff --git a/gitea_mcp_server.py b/gitea_mcp_server.py index b7aee01..b5415eb 100644 --- a/gitea_mcp_server.py +++ b/gitea_mcp_server.py @@ -1764,6 +1764,51 @@ def record_live_review_mutation(pr_number: int, action: str, review_id: int | No _save_review_decision_lock(lock) +def terminal_review_hard_stop_reasons(pr_number: int, operation: str) -> list[str]: + """Session hard-stop after a terminal live review mutation (#332). + + After a terminal verdict is consumed in this run, the only permitted + continuation is the merge sequence for the same PR that was approved. + A REQUEST_CHANGES (or an approval of a different PR) blocks every + further review/mark-ready/merge mutation. An operator-approved + correction (#211) re-opens the review path only — never a cross-PR + merge. + + *operation* is one of 'merge', 'mark_ready', or 'review'. + Returns [] when the operation may proceed. + """ + lock = _load_review_decision_lock() + if lock is None: + return [] + terminals = [ + m for m in (lock.get("live_mutations") or []) + if m.get("action") in _TERMINAL_REVIEW_ACTIONS + ] + if not terminals: + return [] + last = terminals[-1] + if ( + operation == "merge" + and last.get("action") == "approve" + and last.get("pr_number") == pr_number + ): + return [] + if operation in ("mark_ready", "review") and lock.get("correction_authorized"): + return [] + if last.get("action") == "approve": + guidance = ( + f"only the merge sequence for approved PR " + f"#{last.get('pr_number')} may continue" + ) + else: + guidance = "the session must stop and produce a final report" + return [ + "terminal review mutation already consumed in this run " + f"({last.get('action')} on PR #{last.get('pr_number')}); {guidance} " + "(fail closed, #332)" + ] + + # Patterns scrubbed from any surfaced error text so a credential can never leak. _SECRET_PREFIXES = ("token ", "Basic ") @@ -2179,6 +2224,9 @@ def gitea_mark_final_review_decision( } org = resolved_org repo = resolved_repo + hard_stop = terminal_review_hard_stop_reasons(pr_number, "mark_ready") + if hard_stop: + return {"marked_ready": False, "reasons": hard_stop} if lock.get("live_mutations") and not lock.get("correction_authorized"): return { "marked_ready": False, @@ -2196,6 +2244,33 @@ def gitea_mark_final_review_decision( f"{sorted(_REVIEW_ACTIONS)}" ], } + if action == "request_changes": + # Duplicate request-changes suppression (#332): an unresolved + # REQUEST_CHANGES at the current head must not be duplicated. + feedback = gitea_get_pr_review_feedback( + pr_number, remote=remote, org=org, repo=repo) + if not feedback.get("success"): + return { + "marked_ready": False, + "reasons": [ + "could not verify existing request-changes state for " + f"PR #{pr_number}; refusing to submit a possibly " + "duplicate REQUEST_CHANGES (fail closed, #332)" + ], + } + if ( + feedback.get("has_blocking_change_requests") + and not feedback.get("review_feedback_stale") + ): + return { + "marked_ready": False, + "reasons": [ + f"PR #{pr_number} already has an unresolved " + "REQUEST_CHANGES at the current head SHA; do not " + "duplicate the request-changes review (fail closed, " + "#332)" + ], + } lock["final_review_decision_ready"] = True lock["ready_pr_number"] = pr_number lock["ready_action"] = action @@ -2765,6 +2840,14 @@ def gitea_merge_pr( ) return result + # Gate 2b — session hard-stop after a terminal review mutation (#332): + # merge may only continue for the same PR that was just approved. + # Local in-process check; zero API calls. + hard_stop = terminal_review_hard_stop_reasons(pr_number, "merge") + if hard_stop: + reasons.extend(hard_stop) + return result + # Gate 3 — reuse #14 eligibility (identity + profile + merge-allowed + # author + self-merge block + open + mergeable/unknown fail-closed). # Read-only GETs only. diff --git a/review_proofs.py b/review_proofs.py index 15b9846..745b7a1 100644 --- a/review_proofs.py +++ b/review_proofs.py @@ -1231,7 +1231,8 @@ def build_final_report(checkout_proof, inventory, validation, contamination, role_boundary=None, review_mutation=None, report_text=None, review_decision_lock=None, controller_handoff=None, capability_proof=None, - sweep_proof=None, worktree_proof=None): + sweep_proof=None, worktree_proof=None, + baseline_validation=None, project_root=None): """Required behavior 6 + acceptance criteria: one report, distinct proofs. Combines the individual proof verdicts into the final-report fields the @@ -1258,6 +1259,18 @@ def build_final_report(checkout_proof, inventory, validation, contamination, ) empty_queue_report = assess_empty_queue_report(report_text) + if baseline_validation is None and report_text: + baseline_validation = assess_reviewer_baseline_validation_proof( + report_text=report_text, + project_root=project_root, + ) + elif baseline_validation is None: + baseline_validation = { + "proven": True, + "block": False, + "reasons": [], + "violations": [], + } contamination_status = contamination.get("status", "unknown") checkout_proven = bool(checkout_proof.get("proven")) @@ -1387,6 +1400,11 @@ 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 baseline_validation.get("proven"): + downgrade_reasons.append( + "reviewer baseline validation proof missing or failed (#325)" + ) + downgrade_reasons.extend(baseline_validation.get("reasons", [])) merge_allowed = ( identity_eligible @@ -1398,9 +1416,11 @@ 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 baseline_validation.get("proven") ) violations = [] + violations.extend(baseline_validation.get("violations", [])) if merge_performed and not merge_allowed: violations.append( "merge was performed/claimed although the proofs did not allow " @@ -1452,6 +1472,10 @@ def build_final_report(checkout_proof, inventory, validation, contamination, else True ), "empty_queue_trust_gate_status": empty_queue_report.get("status"), + "baseline_validation_proven": bool(baseline_validation.get("proven")), + "baseline_validation_violations": list( + baseline_validation.get("violations") or [] + ), } @@ -3020,6 +3044,180 @@ def build_review_mutation_proof(run_log: list[dict]) -> dict: } +# --------------------------------------------------------------------------- +# Reviewer baseline validation (#325) +# --------------------------------------------------------------------------- + +_TEST_VALIDATION_COMMAND_RE = re.compile( + r"(?:^|\s)(?:venv/)?(?:bin/)?(?:python\s+-m\s+)?" + r"(?:pytest|make\s+test|npm\s+test|cargo\s+test|go\s+test\b)", + re.IGNORECASE, +) + +_PREEXISTING_FAILURE_CLAIM_RE = re.compile( + r"(?:\bsame\s+as\s+master\b|" + r"\bpre-?existing(?:\s+(?:on\s+)?master)?\b|" + r"\bfailures?\s+(?:are|is)\s+pre-?existing\b|" + r"\bmaster\s+also\s+fails?\b|" + r"\bfull-?suite\s+failures?\s+(?:are|is)\s+pre-?existing\b)", + re.IGNORECASE, +) + +_REPORT_VALIDATION_CWD_RE = re.compile( + r"(?:working\s+directory|cwd|directory)\s*:\s*(\S+)", + re.IGNORECASE, +) + + +def _normalize_path(path: str) -> str: + return (path or "").replace("\\", "/").rstrip("/") + + +def _path_under_branches(path: str, project_root: str | None = None) -> bool: + """True when *path* is inside the project's ``branches/`` directory.""" + normalized = _normalize_path(path) + if not normalized: + return False + if "/branches/" in f"{normalized}/": + return True + if normalized.endswith("/branches"): + return True + if project_root: + root = _normalize_path(project_root) + if normalized.startswith(f"{root}/"): + rel = normalized[len(root) + 1 :] + return rel == "branches" or rel.startswith("branches/") + return False + + +def _is_test_validation_command(command: str) -> bool: + return bool(_TEST_VALIDATION_COMMAND_RE.search((command or "").strip())) + + +def _is_full_sha(value: str | None) -> bool: + return bool(value and _FULL_SHA.match((value or "").strip())) + + +def assess_reviewer_baseline_validation_proof( + *, + validation_runs: list[dict] | None = None, + baseline_proof: dict | None = None, + report_text: str | None = None, + project_root: str | None = None, +) -> dict: + """#325: reviewer validation and baseline comparison must use ``branches/``. + + *validation_runs* entries: ``command``, ``working_directory`` (or ``cwd``), + optional ``project_root``. + + *baseline_proof* keys when claiming pre-existing master failures: + ``worktree_path``, ``baseline_target_sha``, ``pr_head_sha``, + ``baseline_failures``, ``pr_failures``, ``failure_signatures_match``, + ``clean_before``, ``clean_after``. + """ + reasons: list[str] = [] + violations: list[str] = [] + text = report_text or "" + + runs = list(validation_runs or []) + pending_command = None + for raw_line in text.splitlines(): + line = raw_line.strip().lstrip("-*").strip() + lower = line.lower() + if lower.startswith("validation command:"): + pending_command = line.split(":", 1)[1].strip() + continue + cwd_match = _REPORT_VALIDATION_CWD_RE.search(line) + if cwd_match: + cwd = cwd_match.group(1).strip().rstrip(",.;") + command = pending_command or line + if _is_test_validation_command(command): + runs.append( + { + "command": command, + "working_directory": cwd, + "project_root": project_root, + } + ) + pending_command = None + + for run in runs: + command = (run.get("command") or "").strip() + if not command or not _is_test_validation_command(command): + continue + cwd = (run.get("working_directory") or run.get("cwd") or "").strip() + root = run.get("project_root") or project_root + if not cwd: + reasons.append( + "test validation command stated without working directory; " + "cannot prove branches-only execution (#325)" + ) + continue + if not _path_under_branches(cwd, root): + violations.append( + f"test validation ran outside branches/ worktree: cwd={cwd!r}" + ) + reasons.append( + "reviewer workflow must not run test suites in the main " + f"checkout; cwd {cwd!r} is not under branches/ (#325)" + ) + + claims_preexisting = bool(_PREEXISTING_FAILURE_CLAIM_RE.search(text)) + if claims_preexisting: + proof = baseline_proof or {} + worktree = (proof.get("worktree_path") or "").strip() + if not worktree or not _path_under_branches(worktree, project_root): + reasons.append( + "pre-existing master failure claimed without a baseline " + "worktree path under branches/ (#325)" + ) + if not _is_full_sha(proof.get("baseline_target_sha")): + reasons.append( + "pre-existing master failure claimed without " + "baseline_target_sha proof (#325)" + ) + if not _is_full_sha(proof.get("pr_head_sha")): + reasons.append( + "pre-existing master failure claimed without pr_head_sha " + "proof (#325)" + ) + baseline_failures = proof.get("baseline_failures") + pr_failures = proof.get("pr_failures") + if baseline_failures is None or pr_failures is None: + reasons.append( + "pre-existing master failure claimed without baseline and " + "PR failure listings (#325)" + ) + if proof.get("failure_signatures_match") is not True: + reasons.append( + "pre-existing master failure claimed without proven matching " + "failure signatures (#325)" + ) + if proof.get("clean_before") is not True: + reasons.append( + "baseline worktree clean-before validation not proven (#325)" + ) + if proof.get("clean_after") is not True: + reasons.append( + "baseline worktree clean-after validation not proven (#325)" + ) + + proven = not reasons and not violations + return { + "proven": proven, + "block": bool(violations), + "claims_preexisting": claims_preexisting, + "reasons": reasons, + "violations": violations, + "safe_next_action": ( + "create a clean baseline worktree under branches/, e.g. " + "branches/baseline-master-pr, and rerun validation there" + if not proven + else "proceed" + ), + } + + # --------------------------------------------------------------------------- # Identity disclosure (#305) # --------------------------------------------------------------------------- @@ -3106,3 +3304,126 @@ def assess_reviewer_fallback_report(report_text, **kwargs): from reviewer_fallback import assess_reviewer_fallback_report as _assess return _assess(report_text, **kwargs) + + +# --------------------------------------------------------------------------- +# Git ref mutations (#297) +# --------------------------------------------------------------------------- + +_GIT_REF_MUTATIONS_FIELD_RE = re.compile( + r"^\s*git ref mutations\s*:\s*(.+?)\s*$", re.I | re.M) +_GIT_WORKTREE_MUTATIONS_NONE_RE = re.compile( + r"^\s*git/worktree mutations\s*:\s*none\b", re.I | re.M) + +_GIT_REF_MUTATING_FIRST_WORDS = frozenset( + {"fetch", "pull", "push", "merge", "update-ref"}) +_GIT_REF_MUTATING_PREFIXES = ("remote update", "branch -d", "branch -D", + "reset --hard") + + +def _command_text(entry): + if isinstance(entry, dict): + return str(entry.get("command") or "").strip() + return str(entry or "").strip() + + +def _git_subcommand_line(command): + tokens = command.split() + if not tokens or tokens[0] != "git": + return None + return " ".join(tokens[1:]) + + +def git_ref_mutating_commands(command_log): + """Return logged commands that update git refs (#297). + + ``git fetch`` and friends edit no files but move refs; they are never + read-only diagnostics. + """ + out = [] + for entry in command_log or []: + command = _command_text(entry) + rest = _git_subcommand_line(command) + if rest is None: + continue + first = rest.split()[0] if rest.split() else "" + if first in _GIT_REF_MUTATING_FIRST_WORDS: + out.append(command) + continue + if any(rest.startswith(prefix) for prefix in _GIT_REF_MUTATING_PREFIXES): + out.append(command) + return out + + +def _fetch_targets(ref_commands): + """Extract ``/`` targets from git fetch commands.""" + targets = [] + for command in ref_commands: + rest = _git_subcommand_line(command) or "" + tokens = rest.split() + if not tokens or tokens[0] != "fetch": + continue + args = [t for t in tokens[1:] if not t.startswith("-")] + if len(args) >= 2: + targets.append(f"{args[0]}/{args[1]}") + return targets + + +def assess_git_ref_mutation_report(report_text, *, command_log=None): + """#297: ref updates are Git ref mutations, not read-only diagnostics. + + When the command log holds ref-updating commands, the report must carry + a non-none ``Git ref mutations`` entry (naming ``fetched + /`` for targeted fetches), may not claim ``Git/worktree + mutations: None``, and may not list the command as read-only. + """ + text = report_text or "" + lower = text.lower() + reasons = [] + ref_commands = git_ref_mutating_commands(command_log) + fetch_targets = _fetch_targets(ref_commands) + + if ref_commands: + field = _GIT_REF_MUTATIONS_FIELD_RE.search(text) + value = field.group(1).strip().lower() if field else None + if not value or value == "none": + reasons.append( + "ref-updating commands ran but the report has no " + "'Git ref mutations' entry" + ) + for target in fetch_targets: + if "fetched" not in lower or target.lower() not in lower: + reasons.append( + "git fetch ran; report must state " + f"'Git ref mutations: fetched {target}'" + ) + if _GIT_WORKTREE_MUTATIONS_NONE_RE.search(text): + reasons.append( + "'Git/worktree mutations: None' rejected: ref-updating " + "commands ran" + ) + for line in text.splitlines(): + if "read-only" not in line.lower(): + continue + for command in ref_commands: + if command.lower() in line.lower(): + reasons.append( + "read-only diagnostics may not include ref-updating " + f"command '{command}'" + ) + + proven = not reasons + return { + "proven": proven, + "block": not proven, + "reasons": reasons, + "ref_mutating_commands": ref_commands, + "fetch_targets": fetch_targets, + } + + +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) diff --git a/reviewer_mergeability_skip.py b/reviewer_mergeability_skip.py new file mode 100644 index 0000000..565de40 --- /dev/null +++ b/reviewer_mergeability_skip.py @@ -0,0 +1,159 @@ +"""Non-mergeable PR skip conflict-proof verifier for reviewer reports (#322).""" + +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) +_MERGEABILITY_FALSE_RE = re.compile( + r"(?:mergeable\s*:\s*false|not mergeable|non[- ]mergeable|mergeability\s*:\s*false|" + r"mergeability result\s*:\s*false)", + re.IGNORECASE, +) +_CONFLICT_PROOF_RE = re.compile( + r"(?:merge-tree|git merge-tree|gitea_view_pr|gitea_check_pr_eligibility|" + r"conflict proof|mergeability tool|merge simulation|conflicting files?)", + re.IGNORECASE, +) +_CONFLICTING_FILES_RE = re.compile( + r"(?:conflicting files?|conflict files?)\s*:\s*(.+)$", + re.IGNORECASE | re.MULTILINE, +) +_HEAD_CHANGED_RE = re.compile( + r"(?:head (?:changed|unchanged)|head sha (?:changed|unchanged)|" + r"head changed since|head unchanged since)", + re.IGNORECASE, +) +_MERGEABILITY_UNVERIFIED_RE = re.compile( + r"\bMERGEABILITY_UNVERIFIED\b", +) + + +def _pr_section(text: str, pr_number: int) -> str: + """Return report lines likely describing one skipped PR.""" + 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_non_mergeable_skip_proof( + report_text: str, + *, + skipped_prs: list[dict] | None = None, +) -> dict[str, Any]: + """Validate skipped non-mergeable PR documentation in reviewer reports (#322).""" + 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) + mergeable = entry.get("mergeable") + verified = entry.get("mergeability_verified") + classification = (entry.get("classification") or "").strip().upper() + head_sha = (entry.get("head_sha") or "").strip() or None + + item_reasons: list[str] = [] + + 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 mergeable is False or verified is False: + if not _MERGEABILITY_UNVERIFIED_RE.search(section) and verified is False: + if "MERGEABILITY_UNVERIFIED" not in classification: + item_reasons.append( + f"PR #{pr_number} conflict proof unavailable; report must classify " + "MERGEABILITY_UNVERIFIED" + ) + elif verified is not False: + if not _MERGEABILITY_FALSE_RE.search(section): + item_reasons.append( + f"PR #{pr_number} skip missing mergeability:false proof" + ) + if not _has_head_sha(section, head_sha): + item_reasons.append( + f"PR #{pr_number} skip missing current head SHA" + ) + if not _CONFLICT_PROOF_RE.search(section): + item_reasons.append( + f"PR #{pr_number} skip missing conflict proof command/tool" + ) + if entry.get("head_changed_since_prior_blocker") is not None: + if not _HEAD_CHANGED_RE.search(section): + item_reasons.append( + f"PR #{pr_number} skip missing head-changed-since-blocker proof" + ) + + if ( + entry.get("conflicting_files") + and not _CONFLICTING_FILES_RE.search(section) + and not any( + path.lower() in section.lower() + for path in (entry.get("conflicting_files") or []) + ) + ): + item_reasons.append( + f"PR #{pr_number} has conflicting files in session proof but " + "report omits file-level conflict proof" + ) + + proven = not item_reasons + assessments.append({ + "pr_number": pr_number, + "proven": proven, + "classification": classification or ( + "MERGEABILITY_UNVERIFIED" if verified is False else "NON_MERGEABLE_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": ( + "document each skipped non-mergeable PR with head SHA, mergeability result, " + "conflict proof command, conflicting files, and head-change status" + if reasons + else "proceed" + ), + } \ No newline at end of file diff --git a/tests/test_git_ref_mutation_report.py b/tests/test_git_ref_mutation_report.py new file mode 100644 index 0000000..c8ce29c --- /dev/null +++ b/tests/test_git_ref_mutation_report.py @@ -0,0 +1,101 @@ +"""Git ref mutations must be reported, never hidden as diagnostics (#297). + +``git fetch`` updates remote-tracking refs even though it edits no files. +Reports that ran fetch (or any ref-updating command) must carry a +``Git ref mutations`` entry and may not claim ``Git/worktree mutations: +None`` or classify the fetch as read-only diagnostics. +""" +import sys +import unittest + +sys.path.insert(0, str(__import__("pathlib").Path(__file__).resolve().parent.parent)) + +import review_proofs + + +def _assess(report, commands): + return review_proofs.assess_git_ref_mutation_report( + report, command_log=commands) + + +class TestGitRefMutationDetection(unittest.TestCase): + def test_fetch_only_review_with_proper_ledger_passes(self): + report = "\n".join([ + "Git ref mutations: fetched prgs/master", + "Review decision: APPROVE", + ]) + res = _assess(report, ["git fetch prgs master"]) + self.assertTrue(res["proven"], res["reasons"]) + self.assertEqual(res["ref_mutating_commands"], ["git fetch prgs master"]) + + def test_fetch_without_ref_mutation_line_is_blocked(self): + report = "Review decision: APPROVE\nMutations: None\n" + res = _assess(report, ["git fetch prgs master"]) + self.assertFalse(res["proven"]) + self.assertTrue( + any("git ref mutations" in r.lower() for r in res["reasons"])) + + def test_fetch_with_remote_branch_requires_fetched_target_in_report(self): + report = "Git ref mutations: some refs updated\n" + res = _assess(report, ["git fetch prgs master"]) + self.assertFalse(res["proven"]) + self.assertTrue( + any("prgs/master" in r for r in res["reasons"])) + + def test_git_worktree_mutations_none_rejected_when_fetch_occurred(self): + report = "\n".join([ + "Git ref mutations: fetched prgs/master", + "Git/worktree mutations: None", + ]) + res = _assess(report, ["git fetch prgs master"]) + self.assertFalse(res["proven"]) + self.assertTrue( + any("git/worktree mutations" in r.lower() for r in res["reasons"])) + + def test_fetch_classified_as_read_only_diagnostics_rejected(self): + report = "\n".join([ + "Git ref mutations: fetched prgs/master", + "Read-only diagnostics: git fetch prgs master, git status", + ]) + res = _assess(report, ["git fetch prgs master"]) + self.assertFalse(res["proven"]) + self.assertTrue( + any("read-only" in r.lower() for r in res["reasons"])) + + def test_worktree_creation_is_not_a_ref_mutation(self): + report = "Worktree mutations: created branches/review-pr9\n" + res = _assess(report, ["git worktree add branches/review-pr9 prgs/master"]) + self.assertTrue(res["proven"], res["reasons"]) + self.assertEqual(res["ref_mutating_commands"], []) + + def test_merge_command_counts_as_ref_mutation(self): + report = "Review decision: APPROVE\n" + res = _assess(report, ["git merge --no-ff feat/x"]) + self.assertFalse(res["proven"]) + self.assertIn("git merge --no-ff feat/x", res["ref_mutating_commands"]) + + def test_cleanup_branch_delete_counts_as_ref_mutation(self): + report = "Cleanup mutations: deleted branch feat/x\n" + res = _assess(report, ["git branch -d feat/x"]) + self.assertFalse(res["proven"]) + self.assertIn("git branch -d feat/x", res["ref_mutating_commands"]) + + def test_no_mutation_blocked_handoff_passes(self): + report = "\n".join([ + "Git/worktree mutations: None", + "Current status: blocked handoff, no mutations performed", + ]) + res = _assess(report, ["git status --porcelain", "git log --oneline -1"]) + self.assertTrue(res["proven"], res["reasons"]) + self.assertEqual(res["ref_mutating_commands"], []) + + def test_command_log_dict_entries_supported(self): + report = "Git ref mutations: fetched prgs/master\n" + res = _assess(report, [{"command": "git fetch prgs master"}]) + self.assertTrue(res["proven"], res["reasons"]) + self.assertEqual( + res["ref_mutating_commands"], ["git fetch prgs master"]) + + +if __name__ == "__main__": + unittest.main() diff --git a/tests/test_llm_workflow_split.py b/tests/test_llm_workflow_split.py index ea7bfce..0481ed5 100644 --- a/tests/test_llm_workflow_split.py +++ b/tests/test_llm_workflow_split.py @@ -127,4 +127,10 @@ def test_reviewer_fallback_verifier_exported(): def test_create_issue_final_report_verifier_exported(): from review_proofs import assess_create_issue_final_report - assert callable(assess_create_issue_final_report) \ No newline at end of file + assert callable(assess_create_issue_final_report) + + +def test_non_mergeable_skip_verifier_exported(): + from review_proofs import assess_non_mergeable_skip_proof + + assert callable(assess_non_mergeable_skip_proof) \ No newline at end of file diff --git a/tests/test_mcp_server.py b/tests/test_mcp_server.py index 45928bb..394ab03 100644 --- a/tests/test_mcp_server.py +++ b/tests/test_mcp_server.py @@ -48,6 +48,21 @@ import mcp_server FAKE_AUTH = "Basic dGVzdDp0ZXN0" +_NO_BLOCKER_FEEDBACK = { + "success": True, + "has_blocking_change_requests": False, + "review_feedback_stale": False, +} + + +def _mark_request_changes_ready(pr_number=8, **kwargs): + """Mark a request_changes decision ready with the #332 duplicate- + suppression feedback fetch stubbed to 'no existing blocker'.""" + with patch("mcp_server.gitea_get_pr_review_feedback", + return_value=dict(_NO_BLOCKER_FEEDBACK)): + return gitea_mark_final_review_decision( + pr_number, "request_changes", **kwargs) + def _formal_review(reviewer, verdict, sha="abc123", review_id=1): return { @@ -1839,7 +1854,7 @@ class TestSubmitPrReview(unittest.TestCase): @patch("mcp_server.api_request") @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH) def test_request_changes_succeeds_when_eligible(self, _auth, mock_api): - gitea_mark_final_review_decision(8, "request_changes", remote="prgs") + _mark_request_changes_ready(remote="prgs") mock_api.side_effect = [ {"login": "reviewer-bot"}, self._pr("author-bot"), {"id": 9, "state": "REQUEST_CHANGES"}, @@ -1862,7 +1877,7 @@ class TestSubmitPrReview(unittest.TestCase): self.assertEqual(post_calls[0].args[3]["event"], "REQUEST_CHANGES") def test_request_changes_blocked_without_eligibility(self): - gitea_mark_final_review_decision(8, "request_changes", remote="prgs") + _mark_request_changes_ready(remote="prgs") with patch("mcp_server.get_auth_header", return_value=FAKE_AUTH) as _a, \ patch("mcp_server.api_request") as mock_api: mock_api.side_effect = [{"login": "reviewer-bot"}, self._pr("author-bot")] @@ -2144,7 +2159,7 @@ class TestSubmitPrReview(unittest.TestCase): reason="operator approved correcting mistaken approve", operator_authorized=True, ) - gitea_mark_final_review_decision(8, "request_changes", remote="prgs") + _mark_request_changes_ready(remote="prgs") second = gitea_submit_pr_review( pr_number=8, action="request_changes", remote="prgs", final_review_decision_ready=True, diff --git a/tests/test_review_proofs.py b/tests/test_review_proofs.py index b4683dc..ec411d2 100644 --- a/tests/test_review_proofs.py +++ b/tests/test_review_proofs.py @@ -24,6 +24,7 @@ from review_proofs import ( # noqa: E402 ISSUE_SELECTION_CONTINUATION_EXPLICIT, ISSUE_SELECTION_REPRESENTED_BY_OPEN_PR, assess_author_pr_report, + assess_reviewer_baseline_validation_proof, assess_capability_evidence, assess_capability_proof, assess_contradictory_no_pr_claim, @@ -2160,5 +2161,125 @@ class TestCreateIssueFinalReport(unittest.TestCase): self.assertTrue(result["downgraded"]) +class TestReviewerBaselineValidationProof(unittest.TestCase): + """Issue #325: baseline validation must use branches/ worktrees.""" + + ROOT = "/repo/Gitea-Tools" + + def _good_baseline_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, + } + proof.update(overrides) + return proof + + def test_main_checkout_test_run_blocks(self): + result = assess_reviewer_baseline_validation_proof( + validation_runs=[ + { + "command": "venv/bin/pytest tests/", + "working_directory": self.ROOT, + "project_root": self.ROOT, + } + ], + project_root=self.ROOT, + ) + self.assertFalse(result["proven"]) + self.assertTrue(result["block"]) + self.assertTrue(result["violations"]) + + def test_branches_worktree_test_run_passes(self): + result = assess_reviewer_baseline_validation_proof( + validation_runs=[ + { + "command": "venv/bin/pytest tests/", + "working_directory": f"{self.ROOT}/branches/review-pr-280", + "project_root": self.ROOT, + } + ], + project_root=self.ROOT, + ) + self.assertTrue(result["proven"]) + + def test_preexisting_claim_without_baseline_proof_fails(self): + result = assess_reviewer_baseline_validation_proof( + report_text=( + "Validation: full-suite failures are pre-existing on master." + ), + project_root=self.ROOT, + ) + self.assertFalse(result["proven"]) + self.assertTrue(result["claims_preexisting"]) + + def test_preexisting_claim_with_complete_baseline_proof_passes(self): + result = assess_reviewer_baseline_validation_proof( + report_text="Failures are pre-existing on master.", + baseline_proof=self._good_baseline_proof(), + project_root=self.ROOT, + ) + self.assertTrue(result["proven"]) + + def test_mismatched_failures_block_preexisting_claim(self): + result = assess_reviewer_baseline_validation_proof( + report_text="Same as master.", + baseline_proof=self._good_baseline_proof( + failure_signatures_match=False, + pr_failures=["tests/test_other.py::test_other"], + ), + project_root=self.ROOT, + ) + self.assertFalse(result["proven"]) + + def test_report_parsed_main_checkout_cwd_blocks(self): + result = assess_reviewer_baseline_validation_proof( + report_text=( + "- Validation command: venv/bin/pytest tests/\n" + f"- Working directory: {self.ROOT}\n" + ), + project_root=self.ROOT, + ) + self.assertFalse(result["proven"]) + self.assertTrue(result["block"]) + + def test_build_final_report_downgrades_main_checkout_validation(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=( + "- Validation command: venv/bin/pytest tests/\n" + f"- Working directory: {self.ROOT}\n" + ), + project_root=self.ROOT, + ) + self.assertNotEqual(report["grade"], "A") + self.assertFalse(report["baseline_validation_proven"]) + + if __name__ == "__main__": unittest.main() diff --git a/tests/test_reviewer_mergeability_skip.py b/tests/test_reviewer_mergeability_skip.py new file mode 100644 index 0000000..98fcc2d --- /dev/null +++ b/tests/test_reviewer_mergeability_skip.py @@ -0,0 +1,150 @@ +"""Tests for non-mergeable skip conflict-proof verifier (#322).""" +import sys +import unittest +from pathlib import Path + +sys.path.insert(0, str(Path(__file__).resolve().parent.parent)) + +from reviewer_mergeability_skip import assess_non_mergeable_skip_proof # noqa: E402 + +HEAD_A = "0fdc8f582026b72a229d59a172c0a63ac4aaeaf9" +HEAD_B = "1111111111111111111111111111111111111111" + + +def _good_skip_report(pr_number: int, head: str, files: str = "review_proofs.py") -> str: + return "\n".join([ + f"Skipped PR #{pr_number} (non-mergeable).", + f"- PR number: #{pr_number}", + f"- Current head SHA: {head}", + "- Mergeability result: false", + "- Conflict proof command: git merge-tree $(git merge-base prgs/master prgs/feat) prgs/master prgs/feat", + f"- Conflicting files: {files}", + "- Head unchanged since prior blocker", + "- Blocking category: merge conflict", + ]) + + +class TestNonMergeableSkipProof(unittest.TestCase): + def test_no_skips_passes(self): + report = "Selected PR #203 for review. No earlier PRs skipped." + result = assess_non_mergeable_skip_proof(report, skipped_prs=[]) + self.assertTrue(result["proven"]) + self.assertFalse(result["block"]) + + def test_documented_non_mergeable_skip_passes(self): + report = _good_skip_report(282, HEAD_A) + result = assess_non_mergeable_skip_proof( + report, + skipped_prs=[{ + "pr_number": 282, + "mergeable": False, + "head_sha": HEAD_A, + "mergeability_verified": True, + "conflicting_files": ["review_proofs.py"], + "head_changed_since_prior_blocker": False, + }], + ) + self.assertTrue(result["proven"]) + + def test_skip_without_conflict_proof_blocks(self): + report = "\n".join([ + "Skipped PR #284 because it was not mergeable.", + f"Head SHA: {HEAD_B}", + ]) + result = assess_non_mergeable_skip_proof( + report, + skipped_prs=[{ + "pr_number": 284, + "mergeable": False, + "head_sha": HEAD_B, + "mergeability_verified": True, + }], + ) + self.assertFalse(result["proven"]) + self.assertTrue(result["block"]) + self.assertTrue(any("conflict proof" in r for r in result["reasons"])) + + def test_missing_head_sha_blocks(self): + report = _good_skip_report(282, HEAD_A).replace(HEAD_A, "") + result = assess_non_mergeable_skip_proof( + report, + skipped_prs=[{ + "pr_number": 282, + "mergeable": False, + "head_sha": HEAD_A, + "mergeability_verified": True, + }], + ) + self.assertFalse(result["proven"]) + + def test_mergeability_unverified_classification_passes(self): + report = "\n".join([ + "Skipped PR #282.", + "Classification: MERGEABILITY_UNVERIFIED", + "Conflict proof could not be retrieved in this session.", + ]) + result = assess_non_mergeable_skip_proof( + report, + skipped_prs=[{ + "pr_number": 282, + "mergeable": False, + "mergeability_verified": False, + }], + ) + self.assertTrue(result["proven"]) + + def test_unverified_without_classification_blocks(self): + report = "Skipped PR #282 due to conflicts." + result = assess_non_mergeable_skip_proof( + report, + skipped_prs=[{ + "pr_number": 282, + "mergeable": False, + "mergeability_verified": False, + }], + ) + self.assertFalse(result["proven"]) + self.assertTrue(any("MERGEABILITY_UNVERIFIED" in r for r in result["reasons"])) + + def test_non_mergeable_without_file_details_still_passes_with_command(self): + report = _good_skip_report(284, HEAD_B, files="not available") + result = assess_non_mergeable_skip_proof( + report, + skipped_prs=[{ + "pr_number": 284, + "mergeable": False, + "head_sha": HEAD_B, + "mergeability_verified": True, + "conflicting_files": [], + }], + ) + self.assertTrue(result["proven"]) + + def test_stale_head_requires_head_change_field(self): + report = _good_skip_report(282, HEAD_A).replace( + "- Head unchanged since prior blocker", + "", + ) + result = assess_non_mergeable_skip_proof( + report, + skipped_prs=[{ + "pr_number": 282, + "mergeable": False, + "head_sha": HEAD_A, + "mergeability_verified": True, + "head_changed_since_prior_blocker": True, + }], + ) + self.assertFalse(result["proven"]) + self.assertTrue(any("head-changed" in r for r in result["reasons"])) + + +class TestExport(unittest.TestCase): + def test_review_proofs_reexport(self): + from review_proofs import assess_non_mergeable_skip_proof as exported + + self.assertTrue(callable(exported)) + + +if __name__ == "__main__": + unittest.main() \ No newline at end of file diff --git a/tests/test_terminal_review_hard_stop.py b/tests/test_terminal_review_hard_stop.py new file mode 100644 index 0000000..bd5109b --- /dev/null +++ b/tests/test_terminal_review_hard_stop.py @@ -0,0 +1,187 @@ +"""Tests for the session hard-stop after a terminal review mutation (#332). + +Extends the single-terminal-decision machinery (#211): after a live +REQUEST_CHANGES the run must stop; after an APPROVE only the merge sequence +for that same PR may continue; a different PR can never be reviewed or +merged in the same run; duplicate REQUEST_CHANGES at an unchanged head is +suppressed. +""" +import os +import unittest +from unittest.mock import patch + +import mcp_server + + +def _lock(mutations=None, correction=False): + return { + "task": "review_pr", + "remote": "prgs", + "session_pid": os.getpid(), + "session_profile": "prgs-reviewer", + "session_profile_lock": "", + "final_review_decision_ready": False, + "ready_pr_number": None, + "ready_action": None, + "ready_expected_head_sha": None, + "ready_remote": None, + "ready_org": None, + "ready_repo": None, + "live_mutations": list(mutations or []), + "correction_authorized": correction, + "correction_reason": None, + } + + +def _seed(mutations=None, correction=False): + mcp_server._save_review_decision_lock(_lock(mutations, correction)) + + +APPROVED_A = {"pr_number": 5, "action": "approve", "review_id": 1, + "review_state": "approve"} +RC_A = {"pr_number": 5, "action": "request_changes", "review_id": 2, + "review_state": "request_changes"} + + +class TestTerminalHardStopReasons(unittest.TestCase): + def tearDown(self): + mcp_server._save_review_decision_lock(None) + + def test_no_lock_no_reasons(self): + mcp_server._save_review_decision_lock(None) + self.assertEqual( + mcp_server.terminal_review_hard_stop_reasons(5, "merge"), []) + + def test_no_terminal_mutation_no_reasons(self): + _seed() + self.assertEqual( + mcp_server.terminal_review_hard_stop_reasons(5, "merge"), []) + + def test_request_changes_blocks_everything(self): + _seed([RC_A]) + for op in ("merge", "mark_ready", "review"): + for pr in (5, 6): + reasons = mcp_server.terminal_review_hard_stop_reasons(pr, op) + self.assertTrue(reasons, f"{op}/{pr}") + self.assertIn("request_changes on PR #5", reasons[0]) + self.assertIn("#332", reasons[0]) + + def test_approve_allows_same_pr_merge_only(self): + _seed([APPROVED_A]) + self.assertEqual( + mcp_server.terminal_review_hard_stop_reasons(5, "merge"), []) + self.assertTrue( + mcp_server.terminal_review_hard_stop_reasons(6, "merge")) + self.assertTrue( + mcp_server.terminal_review_hard_stop_reasons(6, "mark_ready")) + self.assertTrue( + mcp_server.terminal_review_hard_stop_reasons(6, "review")) + + def test_correction_reopens_review_path_only(self): + _seed([RC_A], correction=True) + self.assertEqual( + mcp_server.terminal_review_hard_stop_reasons(5, "mark_ready"), []) + self.assertEqual( + mcp_server.terminal_review_hard_stop_reasons(5, "review"), []) + # correction never opens a cross-PR merge + self.assertTrue( + mcp_server.terminal_review_hard_stop_reasons(6, "merge")) + + +class TestMergeHardStopWiring(unittest.TestCase): + def tearDown(self): + mcp_server._save_review_decision_lock(None) + + def test_merge_blocked_after_request_changes(self): + _seed([RC_A]) + result = mcp_server.gitea_merge_pr( + pr_number=6, confirmation="MERGE PR 6", remote="prgs") + self.assertFalse(result["performed"]) + self.assertTrue( + any("#332" in r for r in result["reasons"]), result["reasons"]) + + def test_merge_of_other_pr_blocked_after_approve(self): + _seed([APPROVED_A]) + result = mcp_server.gitea_merge_pr( + pr_number=6, confirmation="MERGE PR 6", remote="prgs") + self.assertFalse(result["performed"]) + self.assertTrue( + any("#332" in r for r in result["reasons"]), result["reasons"]) + + +class TestMarkFinalHardStopWiring(unittest.TestCase): + def tearDown(self): + mcp_server._save_review_decision_lock(None) + + def test_mark_ready_blocked_after_terminal_mutation(self): + _seed([RC_A]) + result = mcp_server.gitea_mark_final_review_decision( + pr_number=6, action="approve", remote="prgs") + self.assertFalse(result["marked_ready"]) + self.assertTrue( + any("#332" in r for r in result["reasons"]), result["reasons"]) + + +def _feedback(blocking, stale=False, success=True): + return { + "success": success, + "has_blocking_change_requests": blocking, + "review_feedback_stale": stale, + "current_head_sha": "abc123", + } + + +class TestDuplicateRequestChangesSuppression(unittest.TestCase): + def tearDown(self): + mcp_server._save_review_decision_lock(None) + + def test_duplicate_request_changes_blocked_at_same_head(self): + _seed() + with patch.object(mcp_server, "gitea_get_pr_review_feedback", + return_value=_feedback(blocking=True, stale=False)): + result = mcp_server.gitea_mark_final_review_decision( + pr_number=6, action="request_changes", remote="prgs") + self.assertFalse(result["marked_ready"]) + self.assertTrue( + any("duplicate" in r for r in result["reasons"]), + result["reasons"]) + + def test_request_changes_allowed_when_prior_blocker_stale(self): + _seed() + with patch.object(mcp_server, "gitea_get_pr_review_feedback", + return_value=_feedback(blocking=True, stale=True)): + result = mcp_server.gitea_mark_final_review_decision( + pr_number=6, action="request_changes", remote="prgs") + self.assertTrue(result["marked_ready"], result.get("reasons")) + + def test_request_changes_allowed_when_no_blocker(self): + _seed() + with patch.object(mcp_server, "gitea_get_pr_review_feedback", + return_value=_feedback(blocking=False)): + result = mcp_server.gitea_mark_final_review_decision( + pr_number=6, action="request_changes", remote="prgs") + self.assertTrue(result["marked_ready"], result.get("reasons")) + + def test_request_changes_fails_closed_when_feedback_unavailable(self): + _seed() + with patch.object(mcp_server, "gitea_get_pr_review_feedback", + return_value=_feedback(blocking=False, + success=False)): + result = mcp_server.gitea_mark_final_review_decision( + pr_number=6, action="request_changes", remote="prgs") + self.assertFalse(result["marked_ready"]) + self.assertTrue( + any("could not verify" in r for r in result["reasons"]), + result["reasons"]) + + def test_approve_does_not_fetch_feedback(self): + _seed() + with patch.object(mcp_server, "gitea_get_pr_review_feedback", + side_effect=AssertionError("must not be called")): + result = mcp_server.gitea_mark_final_review_decision( + pr_number=6, action="approve", remote="prgs") + self.assertTrue(result["marked_ready"], result.get("reasons")) + + +if __name__ == "__main__": + unittest.main()