test_actual_sandbox_control_read_denied (test_runner.RunnerTests.test_actual_sandbox_control_read_denied) ... ok test_actual_sandbox_write_boundary (test_runner.RunnerTests.test_actual_sandbox_write_boundary) ... FAIL test_agy_pty_without_keychain_access (test_runner.RunnerTests.test_agy_pty_without_keychain_access) ... FAIL test_approval_required (test_runner.RunnerTests.test_approval_required) ... ERROR test_claude_broker_expiry_fails_closed (test_runner.RunnerTests.test_claude_broker_expiry_fails_closed) ... ok test_claude_broker_never_returns_refresh_token (test_runner.RunnerTests.test_claude_broker_never_returns_refresh_token) ... ok test_claude_profile_keeps_personal_keychain_denied (test_runner.RunnerTests.test_claude_profile_keeps_personal_keychain_denied) ... ok test_dependency_gate (test_runner.RunnerTests.test_dependency_gate) ... ok test_duplicate_acceptance_denied (test_runner.RunnerTests.test_duplicate_acceptance_denied) ... ok test_failed_test_blocks_review (test_runner.RunnerTests.test_failed_test_blocks_review) ... ok test_fixed_denominator_tamper_denied (test_runner.RunnerTests.test_fixed_denominator_tamper_denied) ... ok test_full_deterministic_flow_with_simulated_review (test_runner.RunnerTests.test_full_deterministic_flow_with_simulated_review) ... ERROR test_git_metadata_write_denied (test_runner.RunnerTests.test_git_metadata_write_denied) ... ok test_integration_environment_retry_requires_existing_review (test_runner.RunnerTests.test_integration_environment_retry_requires_existing_review) ... ERROR test_llm_budget_limit (test_runner.RunnerTests.test_llm_budget_limit) ... ok test_llm_concurrency_limit (test_runner.RunnerTests.test_llm_concurrency_limit) ... ok test_main_change_invalidates_approval (test_runner.RunnerTests.test_main_change_invalidates_approval) ... ERROR test_missing_acceptance_test_denied (test_runner.RunnerTests.test_missing_acceptance_test_denied) ... ok test_no_zero_cost_assumption (test_runner.RunnerTests.test_no_zero_cost_assumption) ... ok test_node_output_drained_to_protected_logs (test_runner.RunnerTests.test_node_output_drained_to_protected_logs) ... FAIL test_out_of_scope_edit_denied (test_runner.RunnerTests.test_out_of_scope_edit_denied) ... ok test_overlapping_file_scope (test_runner.RunnerTests.test_overlapping_file_scope) ... ok test_p13_document_dedup_leaves_existing_code_binary_and_other_paths (test_runner.RunnerTests.test_p13_document_dedup_leaves_existing_code_binary_and_other_paths) ... ok test_p13_document_dedup_preserves_raw_source_and_other_diffs (test_runner.RunnerTests.test_p13_document_dedup_preserves_raw_source_and_other_diffs) ... ok test_p13_document_dedup_rejects_missing_inconsistent_snapshots (test_runner.RunnerTests.test_p13_document_dedup_rejects_missing_inconsistent_snapshots) ... ok test_p13_recovery_accepts_matching_forward_hashes (test_runner.RunnerTests.test_p13_recovery_accepts_matching_forward_hashes) ... ok test_p13_recovery_rejects_bad_records_and_states (test_runner.RunnerTests.test_p13_recovery_rejects_bad_records_and_states) ... ok test_p13_recovery_rejects_other_p13_tasks (test_runner.RunnerTests.test_p13_recovery_rejects_other_p13_tasks) ... test_p13_recovery_rejects_other_p13_tasks (test_runner.RunnerTests.test_p13_recovery_rejects_other_p13_tasks) (task_id='P13-01') ... ERROR test_p13_recovery_rejects_other_p13_tasks (test_runner.RunnerTests.test_p13_recovery_rejects_other_p13_tasks) (task_id='P13-02') ... ERROR test_p13_recovery_rejects_source_pin_failure (test_runner.RunnerTests.test_p13_recovery_rejects_source_pin_failure) ... ok test_p13_recovery_uses_normal_submission_and_downstream_gates (test_runner.RunnerTests.test_p13_recovery_uses_normal_submission_and_downstream_gates) ... ok test_packet_capacity_guard_remains (test_runner.RunnerTests.test_packet_capacity_guard_remains) ... ok test_path_traversal_denied (test_runner.RunnerTests.test_path_traversal_denied) ... ok test_policy_tamper_denied (test_runner.RunnerTests.test_policy_tamper_denied) ... ok test_provider_credentials_are_not_inherited (test_runner.RunnerTests.test_provider_credentials_are_not_inherited) ... ok test_recover_releases_operation_not_task_locks (test_runner.RunnerTests.test_recover_releases_operation_not_task_locks) ... ok test_repair_cannot_bypass_counter (test_runner.RunnerTests.test_repair_cannot_bypass_counter) ... ok test_repair_limit (test_runner.RunnerTests.test_repair_limit) ... ok test_resource_lock (test_runner.RunnerTests.test_resource_lock) ... ok test_review_changes_blocks_candidate (test_runner.RunnerTests.test_review_changes_blocks_candidate) ... ERROR test_review_refresh_requires_new_candidate (test_runner.RunnerTests.test_review_refresh_requires_new_candidate) ... ERROR test_reviewer_packet_deduplicates_only_p13_03 (test_runner.RunnerTests.test_reviewer_packet_deduplicates_only_p13_03) ... ok test_reviewer_sees_committed_tests_outside_worker_scope (test_runner.RunnerTests.test_reviewer_sees_committed_tests_outside_worker_scope) ... ERROR test_runtime_isolation (test_runner.RunnerTests.test_runtime_isolation) ... ok test_schema_rejects_false_success (test_runner.RunnerTests.test_schema_rejects_false_success) ... ok test_secret_file_read_denied (test_runner.RunnerTests.test_secret_file_read_denied) ... ok test_secret_scope_denied (test_runner.RunnerTests.test_secret_scope_denied) ... ok test_spec_writes_denied (test_runner.RunnerTests.test_spec_writes_denied) ... ok test_symlink_denied (test_runner.RunnerTests.test_symlink_denied) ... ok test_timeout_is_not_pass (test_runner.RunnerTests.test_timeout_is_not_pass) ... FAIL test_untracked_out_of_scope_denied (test_runner.RunnerTests.test_untracked_out_of_scope_denied) ... ok test_validation_before_submission_denied (test_runner.RunnerTests.test_validation_before_submission_denied) ... ok test_validation_python_does_not_depend_on_shell_path (test_runner.RunnerTests.test_validation_python_does_not_depend_on_shell_path) ... ERROR test_worker_commit_denied (test_runner.RunnerTests.test_worker_commit_denied) ... ok test_worker_has_mandatory_outer_sandbox (test_runner.RunnerTests.test_worker_has_mandatory_outer_sandbox) ... ok test_wrong_candidate_denied (test_runner.RunnerTests.test_wrong_candidate_denied) ... ERROR ====================================================================== ERROR: test_approval_required (test_runner.RunnerTests.test_approval_required) ---------------------------------------------------------------------- Traceback (most recent call last): File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/tests/test_runner.py", line 302, in test_approval_required self.candidate() File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/tests/test_runner.py", line 268, in candidate self.submit(); self.r.validate("T001") ^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 920, in validate self.verify(task_id,wt,task["submitted"],"validation") File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 905, in verify require(passed,f"test_failed: {report}") File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 50, in require raise GateError(message) runner.core.GateError: test_failed: /Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/.runtime/RP13-01/tmp/agent-control-test-7j4lj471/state/test/runs/13abf23717bc46d6af102cd7a7509787-validation.json ====================================================================== ERROR: test_full_deterministic_flow_with_simulated_review (test_runner.RunnerTests.test_full_deterministic_flow_with_simulated_review) ---------------------------------------------------------------------- Traceback (most recent call last): File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/tests/test_runner.py", line 292, in test_full_deterministic_flow_with_simulated_review t=self.candidate() ^^^^^^^^^^^^^^^^ File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/tests/test_runner.py", line 268, in candidate self.submit(); self.r.validate("T001") ^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 920, in validate self.verify(task_id,wt,task["submitted"],"validation") File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 905, in verify require(passed,f"test_failed: {report}") File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 50, in require raise GateError(message) runner.core.GateError: test_failed: /Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/.runtime/RP13-01/tmp/agent-control-test-et0phhsl/state/test/runs/cc9dc8f4ef9a45eba0d3a2b67abdf0df-validation.json ====================================================================== ERROR: test_integration_environment_retry_requires_existing_review (test_runner.RunnerTests.test_integration_environment_retry_requires_existing_review) ---------------------------------------------------------------------- Traceback (most recent call last): File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/tests/test_runner.py", line 306, in test_integration_environment_retry_requires_existing_review self.submit(); self.r.validate("T001") ^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 920, in validate self.verify(task_id,wt,task["submitted"],"validation") File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 905, in verify require(passed,f"test_failed: {report}") File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 50, in require raise GateError(message) runner.core.GateError: test_failed: /Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/.runtime/RP13-01/tmp/agent-control-test-ale6gvtj/state/test/runs/3a0f8b8706ad41889d250bd46152a27d-validation.json ====================================================================== ERROR: test_main_change_invalidates_approval (test_runner.RunnerTests.test_main_change_invalidates_approval) ---------------------------------------------------------------------- Traceback (most recent call last): File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/tests/test_runner.py", line 374, in test_main_change_invalidates_approval t=self.candidate(); self.r.approve("T001",t["candidate"],t["main_base"],"owner") ^^^^^^^^^^^^^^^^ File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/tests/test_runner.py", line 268, in candidate self.submit(); self.r.validate("T001") ^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 920, in validate self.verify(task_id,wt,task["submitted"],"validation") File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 905, in verify require(passed,f"test_failed: {report}") File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 50, in require raise GateError(message) runner.core.GateError: test_failed: /Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/.runtime/RP13-01/tmp/agent-control-test-qp92ql5k/state/test/runs/f2b55e7065dc45bab577059b9b2a0631-validation.json ====================================================================== ERROR: test_p13_recovery_rejects_other_p13_tasks (test_runner.RunnerTests.test_p13_recovery_rejects_other_p13_tasks) (task_id='P13-01') ---------------------------------------------------------------------- Traceback (most recent call last): File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/tests/test_runner.py", line 136, in test_p13_recovery_rejects_other_p13_tasks self.r.add(dict(self.contract, id=task_id)) File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 456, in add require(not any(set(c["acceptance_ids"]) & set(contract["acceptance_ids"]) for c in existing), "同一受入項目の重複タスクは禁止") File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 50, in require raise GateError(message) runner.core.GateError: 同一受入項目の重複タスクは禁止 ====================================================================== ERROR: test_p13_recovery_rejects_other_p13_tasks (test_runner.RunnerTests.test_p13_recovery_rejects_other_p13_tasks) (task_id='P13-02') ---------------------------------------------------------------------- Traceback (most recent call last): File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/tests/test_runner.py", line 136, in test_p13_recovery_rejects_other_p13_tasks self.r.add(dict(self.contract, id=task_id)) File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 456, in add require(not any(set(c["acceptance_ids"]) & set(contract["acceptance_ids"]) for c in existing), "同一受入項目の重複タスクは禁止") File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 50, in require raise GateError(message) runner.core.GateError: 同一受入項目の重複タスクは禁止 ====================================================================== ERROR: test_review_changes_blocks_candidate (test_runner.RunnerTests.test_review_changes_blocks_candidate) ---------------------------------------------------------------------- Traceback (most recent call last): File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/tests/test_runner.py", line 387, in test_review_changes_blocks_candidate self.submit(); self.r.validate("T001") ^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 920, in validate self.verify(task_id,wt,task["submitted"],"validation") File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 905, in verify require(passed,f"test_failed: {report}") File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 50, in require raise GateError(message) runner.core.GateError: test_failed: /Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/.runtime/RP13-01/tmp/agent-control-test-ek5j0rrq/state/test/runs/ccbdbadd674d471790b58dfccc000502-validation.json ====================================================================== ERROR: test_review_refresh_requires_new_candidate (test_runner.RunnerTests.test_review_refresh_requires_new_candidate) ---------------------------------------------------------------------- Traceback (most recent call last): File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/tests/test_runner.py", line 355, in test_review_refresh_requires_new_candidate self.candidate() File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/tests/test_runner.py", line 268, in candidate self.submit(); self.r.validate("T001") ^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 920, in validate self.verify(task_id,wt,task["submitted"],"validation") File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 905, in verify require(passed,f"test_failed: {report}") File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 50, in require raise GateError(message) runner.core.GateError: test_failed: /Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/.runtime/RP13-01/tmp/agent-control-test-9gx5fk5x/state/test/runs/fbd882e8b90a4176bdc634ffbc2b8610-validation.json ====================================================================== ERROR: test_reviewer_sees_committed_tests_outside_worker_scope (test_runner.RunnerTests.test_reviewer_sees_committed_tests_outside_worker_scope) ---------------------------------------------------------------------- Traceback (most recent call last): File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/tests/test_runner.py", line 347, in test_reviewer_sees_committed_tests_outside_worker_scope self.r.validate("T001") File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 920, in validate self.verify(task_id,wt,task["submitted"],"validation") File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 905, in verify require(passed,f"test_failed: {report}") File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 50, in require raise GateError(message) runner.core.GateError: test_failed: /Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/.runtime/RP13-01/tmp/agent-control-test-klgcd5r6/state/test/runs/5240f0471f874dbbb4e4b6e4e93e49dd-validation.json ====================================================================== ERROR: test_validation_python_does_not_depend_on_shell_path (test_runner.RunnerTests.test_validation_python_does_not_depend_on_shell_path) ---------------------------------------------------------------------- Traceback (most recent call last): File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/tests/test_runner.py", line 319, in test_validation_python_does_not_depend_on_shell_path self.r.validate("T001") File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 920, in validate self.verify(task_id,wt,task["submitted"],"validation") File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 905, in verify require(passed,f"test_failed: {report}") File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 50, in require raise GateError(message) runner.core.GateError: test_failed: /Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/.runtime/RP13-01/tmp/agent-control-test-i2v7e5pu/state/test/runs/11dd6edca7c147729690e768086ed4ce-validation.json ====================================================================== ERROR: test_wrong_candidate_denied (test_runner.RunnerTests.test_wrong_candidate_denied) ---------------------------------------------------------------------- Traceback (most recent call last): File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/tests/test_runner.py", line 370, in test_wrong_candidate_denied t=self.candidate() ^^^^^^^^^^^^^^^^ File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/tests/test_runner.py", line 268, in candidate self.submit(); self.r.validate("T001") ^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 920, in validate self.verify(task_id,wt,task["submitted"],"validation") File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 905, in verify require(passed,f"test_failed: {report}") File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/runner/core.py", line 50, in require raise GateError(message) runner.core.GateError: test_failed: /Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/.runtime/RP13-01/tmp/agent-control-test-p6512mu6/state/test/runs/261f9be981534152b1a1673f67d84a72-validation.json ====================================================================== FAIL: test_actual_sandbox_write_boundary (test_runner.RunnerTests.test_actual_sandbox_write_boundary) ---------------------------------------------------------------------- Traceback (most recent call last): File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/tests/test_runner.py", line 472, in test_actual_sandbox_write_boundary self.assertEqual(permitted.returncode,0,permitted.stderr) AssertionError: 71 != 0 : b'sandbox-exec: sandbox_apply: Operation not permitted\n' ====================================================================== FAIL: test_agy_pty_without_keychain_access (test_runner.RunnerTests.test_agy_pty_without_keychain_access) ---------------------------------------------------------------------- Traceback (most recent call last): File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/tests/test_runner.py", line 288, in test_agy_pty_without_keychain_access self.assertEqual(result.returncode,0,result.stderr) AssertionError: 71 != 0 : sandbox-exec: sandbox_apply: Operation not permitted ====================================================================== FAIL: test_node_output_drained_to_protected_logs (test_runner.RunnerTests.test_node_output_drained_to_protected_logs) ---------------------------------------------------------------------- Traceback (most recent call last): File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/tests/test_runner.py", line 278, in test_node_output_drained_to_protected_logs self.assertEqual(code,0) AssertionError: 71 != 0 ====================================================================== FAIL: test_timeout_is_not_pass (test_runner.RunnerTests.test_timeout_is_not_pass) ---------------------------------------------------------------------- Traceback (most recent call last): File "/Users/korizatou114/Projects/TheTree-managed-worktrees/runner-p13-recovery/RP13-01-validation-704ed109/tests/test_runner.py", line 482, in test_timeout_is_not_pass self.assertEqual(code,124) AssertionError: 71 != 124 ---------------------------------------------------------------------- Ran 55 tests in 17.264s FAILED (failures=4, errors=11)