347 lines
15 KiB
Python
347 lines
15 KiB
Python
from src.services.ai_agent_autonomous_runtime_control import (
|
||
build_ai_agent_autonomous_runtime_control,
|
||
build_runtime_receipt_readback_from_rows,
|
||
classify_deploy_control_plane_observation,
|
||
)
|
||
|
||
|
||
def test_ai_agent_autonomous_runtime_control_uses_current_owner_directive():
|
||
data = build_ai_agent_autonomous_runtime_control()
|
||
|
||
assert data["schema_version"] == "ai_agent_autonomous_runtime_control_v1"
|
||
assert data["program_status"]["runtime_authority"] == (
|
||
"current_owner_directive_controlled_ai_automation"
|
||
)
|
||
assert data["program_status"]["deploy_readback_marker"] == (
|
||
"p2_416_d1n_autonomous_runtime_control_prod_readback_v2"
|
||
)
|
||
assert data["program_status"]["deploy_attempt_note"] == (
|
||
"cd_internal_control_plane_readback_retry_20260628_2"
|
||
)
|
||
assert data["program_status"]["legacy_no_send_no_live_rules_overridden"] is True
|
||
assert data["program_status"]["implementation_completion_percent"] == 88
|
||
assert data["current_policy"]["low_risk_controlled_apply_allowed"] is True
|
||
assert data["current_policy"]["medium_risk_controlled_apply_allowed"] is True
|
||
assert data["current_policy"]["high_risk_controlled_apply_allowed"] is True
|
||
assert data["current_policy"]["owner_review_required_for_low_medium_high"] is False
|
||
assert data["current_policy"]["telegram_gateway_required"] is True
|
||
assert data["current_policy"]["direct_bot_api_allowed"] is False
|
||
assert data["current_policy"]["post_apply_verifier_required"] is True
|
||
assert data["current_policy"]["km_learning_writeback_required"] is True
|
||
|
||
|
||
def test_ai_agent_autonomous_runtime_control_exposes_reports_and_executor_receipts():
|
||
data = build_ai_agent_autonomous_runtime_control()
|
||
|
||
cadences = {item["cadence"]: item for item in data["report_delivery"]["cadences"]}
|
||
assert set(cadences) == {"daily", "weekly", "monthly"}
|
||
assert {item["telegram_gateway_delivery_enabled"] for item in cadences.values()} == {True}
|
||
assert {item["direct_bot_api_allowed"] for item in cadences.values()} == {False}
|
||
assert "run_daily_report_loop" in cadences["daily"]["worker"]
|
||
assert "run_weekly_report_loop" in cadences["weekly"]["worker"]
|
||
assert "run_monthly_report_loop" in cadences["monthly"]["worker"]
|
||
|
||
operation_types = {
|
||
item["operation_type"]
|
||
for item in data["controlled_executor"]["operation_receipts"]
|
||
}
|
||
assert {
|
||
"ansible_candidate_matched",
|
||
"ansible_check_mode_executed",
|
||
"ansible_apply_executed",
|
||
"incident_evidence.post_execution_state",
|
||
"knowledge_entries",
|
||
}.issubset(operation_types)
|
||
assert data["rollups"]["automated_risk_tier_count"] == 3
|
||
assert data["rollups"]["report_cadence_enabled_count"] == 3
|
||
assert data["rollups"]["direct_bot_api_allowed_count"] == 0
|
||
assert data["rollups"]["legacy_policy_overridden_count"] >= 4
|
||
assert data["runtime_receipt_readback"]["db_read_status"] == "not_queried"
|
||
|
||
|
||
def test_ai_agent_autonomous_runtime_control_exposes_internal_control_loop():
|
||
data = build_ai_agent_autonomous_runtime_control()
|
||
|
||
integration = data["control_plane_integration"]
|
||
assert integration["schema_version"] == "ai_agent_autonomous_runtime_internal_loop_v1"
|
||
assert integration["status"] == "mcp_rag_km_playbook_log_control_loop_declared"
|
||
assert {sensor["normalized_event"] for sensor in integration["mcp_sensors"]} == {
|
||
"RunObservation",
|
||
"RunnerLaneState",
|
||
"ProductionTruthSnapshot",
|
||
"FrontendTruthSnapshot",
|
||
}
|
||
assert "controlled_cd_lane_capacity_label_guardrails" in integration["rag_context_queries"]
|
||
assert "running_no_container_stale_ui" in integration["playbook_decision_classes"]
|
||
assert integration["km_writeback_contract"]["stores_raw_logs"] is False
|
||
assert integration["km_writeback_contract"]["stores_secret_values"] is False
|
||
assert integration["log_projection_contract"]["raw_html_or_long_log_allowed"] is False
|
||
assert data["rollups"]["mcp_sensor_count"] == 4
|
||
assert data["rollups"]["playbook_decision_class_count"] == 7
|
||
|
||
|
||
def test_deploy_control_plane_classifier_separates_stale_spinner_from_real_failure():
|
||
stale = classify_deploy_control_plane_observation(
|
||
run_status="running",
|
||
is_latest_deploy_intent=True,
|
||
active_task_container_count=0,
|
||
production_marker_hit=True,
|
||
latest_flow_closed=True,
|
||
runner_capacity_ok=True,
|
||
runner_forbidden_label_count=0,
|
||
)
|
||
assert stale["classification"] == "running_no_container_stale_ui"
|
||
assert stale["action"] == "treat_gitea_spinner_as_stale_and_keep_production_truth"
|
||
assert stale["safety_boundary"]["writes_runtime_state"] is False
|
||
assert stale["internal_writeback"]["km_writeback_required"] is True
|
||
|
||
failure = classify_deploy_control_plane_observation(
|
||
run_status="failure",
|
||
is_latest_deploy_intent=True,
|
||
active_task_container_count=0,
|
||
production_marker_hit=False,
|
||
latest_flow_closed=False,
|
||
runner_capacity_ok=True,
|
||
runner_forbidden_label_count=0,
|
||
)
|
||
assert failure["classification"] == "real_failure_requires_playbook_repair"
|
||
assert failure["action"] == "open_cd_repair_playbook_with_target_selector_and_verifier"
|
||
assert failure["safety_boundary"]["opens_legacy_runner"] is False
|
||
assert failure["internal_writeback"]["playbook_route_required"] is True
|
||
|
||
|
||
def test_ai_agent_autonomous_runtime_control_keeps_hard_blockers_and_redaction():
|
||
data = build_ai_agent_autonomous_runtime_control()
|
||
|
||
assert "secret_token_private_key_cookie_session_auth_header_cleartext" in data["hard_blockers"]
|
||
assert "drop_truncate_restore_prune_destructive_database_operation" in data["hard_blockers"]
|
||
assert "force_push_delete_repo_refs_or_visibility_change" in data["hard_blockers"]
|
||
visibility = data["visibility_contract"]
|
||
assert visibility["work_window_transcript_display_allowed"] is False
|
||
assert visibility["prompt_body_display_allowed"] is False
|
||
assert visibility["internal_reasoning_display_allowed"] is False
|
||
assert visibility["sensitive_value_display_allowed"] is False
|
||
assert visibility["telegram_unredacted_payload_display_allowed"] is False
|
||
|
||
|
||
def test_runtime_receipt_readback_summarizes_live_executor_closure_rows():
|
||
apply_op_id = "73b7a95c-3652-4c0d-bb4c-729e500acedb"
|
||
incident_id = "INC-20260627-64472B"
|
||
|
||
readback = build_runtime_receipt_readback_from_rows(
|
||
project_id="awoooi",
|
||
db_read_status="ok",
|
||
operation_count_rows=[
|
||
{
|
||
"operation_type": "ansible_apply_executed",
|
||
"status": "success",
|
||
"total": 1,
|
||
"recent": 1,
|
||
},
|
||
{
|
||
"operation_type": "ansible_check_mode_executed",
|
||
"status": "success",
|
||
"total": 1,
|
||
"recent": 1,
|
||
},
|
||
],
|
||
operation_latest_rows=[
|
||
{
|
||
"op_id": apply_op_id,
|
||
"parent_op_id": "check-mode-op",
|
||
"operation_type": "ansible_apply_executed",
|
||
"status": "success",
|
||
"actor": "ansible_controlled_apply_worker",
|
||
"incident_id": incident_id,
|
||
"catalog_id": "ansible:188-momo-backup-user",
|
||
"playbook_path": "infra/ansible/playbooks/188-momo-backup-user.yml",
|
||
"execution_mode": "controlled_apply",
|
||
"returncode": "0",
|
||
"duration_ms": 7727,
|
||
},
|
||
],
|
||
verifier_count_rows=[
|
||
{"verification_result": "success", "total": 1, "recent": 1},
|
||
],
|
||
verifier_latest_rows=[
|
||
{
|
||
"id": "evidence-1",
|
||
"incident_id": incident_id,
|
||
"verification_result": "success",
|
||
"apply_op_id": apply_op_id,
|
||
"catalog_id": "ansible:188-momo-backup-user",
|
||
"playbook_path": "infra/ansible/playbooks/188-momo-backup-user.yml",
|
||
"returncode": "0",
|
||
},
|
||
],
|
||
km_count_rows=[
|
||
{"status": "review", "total": 1, "recent": 1},
|
||
],
|
||
km_latest_rows=[
|
||
{
|
||
"id": "km-1",
|
||
"title": "AI 自動修復沉澱：INC-20260627-64472B",
|
||
"related_incident_id": incident_id,
|
||
"related_playbook_id": "ansible:188-momo-backup-user",
|
||
"path_type": "ansible_apply_receipt:73b7a95c",
|
||
"status": "review",
|
||
"created_by": "ai_agent_ansible_worker",
|
||
},
|
||
],
|
||
telegram_count_rows=[
|
||
{"send_status": "sent", "total": 1, "recent": 1},
|
||
],
|
||
telegram_latest_rows=[
|
||
{
|
||
"message_id": "telegram-row-1",
|
||
"run_id": "telegram-run-1",
|
||
"message_type": "final",
|
||
"send_status": "sent",
|
||
"provider_message_id": "12345",
|
||
"incident_id": incident_id,
|
||
"action": "controlled_apply_result",
|
||
},
|
||
],
|
||
)
|
||
|
||
assert readback["db_read_status"] == "ok"
|
||
assert readback["writes_on_read"] is False
|
||
assert readback["ansible_apply_executed"]["total"] == 1
|
||
assert readback["post_apply_verifier"]["by_status"]["success"] == 1
|
||
assert readback["km_writeback"]["by_status"]["review"] == 1
|
||
assert readback["telegram_receipt"]["by_status"]["sent"] == 1
|
||
assert readback["latest_flow_closure"] == {
|
||
"apply_op_id": apply_op_id,
|
||
"incident_id": incident_id,
|
||
"has_post_apply_verifier": True,
|
||
"has_km_writeback": True,
|
||
"has_telegram_receipt": True,
|
||
"closed": True,
|
||
"missing": [],
|
||
}
|
||
assert readback["latest_failure_classification"]["classification"] == (
|
||
"latest_controlled_apply_closed_success"
|
||
)
|
||
assert readback["controlled_retry_package"]["status"] == "not_required_for_latest_apply"
|
||
|
||
|
||
def test_runtime_receipt_readback_classifies_closed_failed_apply_as_ai_repair():
|
||
apply_op_id = "94925d5e-6fdc-49c3-90e8-f0a0d57a6a58"
|
||
incident_id = "INC-20260628-A40A9A"
|
||
|
||
readback = build_runtime_receipt_readback_from_rows(
|
||
project_id="awoooi",
|
||
db_read_status="ok",
|
||
operation_count_rows=[
|
||
{
|
||
"operation_type": "ansible_apply_executed",
|
||
"status": "failed",
|
||
"total": 1,
|
||
"recent": 1,
|
||
},
|
||
],
|
||
operation_latest_rows=[
|
||
{
|
||
"op_id": apply_op_id,
|
||
"parent_op_id": "8b555f41-e81f-4d8e-956b-fb20d358db63",
|
||
"operation_type": "ansible_apply_executed",
|
||
"status": "failed",
|
||
"actor": "ansible_controlled_apply_worker",
|
||
"incident_id": incident_id,
|
||
"catalog_id": "ansible:188-ai-web",
|
||
"playbook_path": "infra/ansible/playbooks/188-ai-web.yml",
|
||
"execution_mode": "controlled_apply",
|
||
"returncode": "2",
|
||
"duration_ms": 4797,
|
||
},
|
||
],
|
||
verifier_count_rows=[
|
||
{"verification_result": "failed", "total": 1, "recent": 1},
|
||
],
|
||
verifier_latest_rows=[
|
||
{
|
||
"id": "evidence-1",
|
||
"incident_id": incident_id,
|
||
"verification_result": "failed",
|
||
"apply_op_id": apply_op_id,
|
||
"catalog_id": "ansible:188-ai-web",
|
||
"playbook_path": "infra/ansible/playbooks/188-ai-web.yml",
|
||
"returncode": "2",
|
||
},
|
||
],
|
||
km_count_rows=[
|
||
{"status": "REVIEW", "total": 1, "recent": 1},
|
||
],
|
||
km_latest_rows=[
|
||
{
|
||
"id": "km-1",
|
||
"title": "AI 自動修復沉澱：INC-20260628-A40A9A",
|
||
"related_incident_id": incident_id,
|
||
"related_playbook_id": "ansible:188-ai-web",
|
||
"path_type": "ansible_apply_receipt:94925d5e",
|
||
"status": "REVIEW",
|
||
"created_by": "ai_agent_ansible_worker",
|
||
},
|
||
],
|
||
telegram_count_rows=[
|
||
{"send_status": "sent", "total": 1, "recent": 1},
|
||
],
|
||
telegram_latest_rows=[
|
||
{
|
||
"message_id": "telegram-row-1",
|
||
"run_id": "telegram-run-1",
|
||
"message_type": "final",
|
||
"send_status": "sent",
|
||
"provider_message_id": "32016",
|
||
"incident_id": incident_id,
|
||
"action": "controlled_apply_result",
|
||
},
|
||
],
|
||
)
|
||
|
||
classification = readback["latest_failure_classification"]
|
||
assert classification["classification"] == "closed_failed_apply_requires_ai_repair"
|
||
assert classification["action"] == "queue_check_mode_replay_and_playbook_repair_candidate"
|
||
assert classification["target_selector"] == {
|
||
"incident_id": incident_id,
|
||
"apply_op_id": apply_op_id,
|
||
"parent_op_id": "8b555f41-e81f-4d8e-956b-fb20d358db63",
|
||
"catalog_id": "ansible:188-ai-web",
|
||
"playbook_path": "infra/ansible/playbooks/188-ai-web.yml",
|
||
"execution_mode": "controlled_apply",
|
||
}
|
||
assert classification["evidence"]["returncode"] == "2"
|
||
assert classification["evidence"]["verification_result"] == "failed"
|
||
assert classification["evidence"]["latest_flow_closed"] is True
|
||
assert classification["evidence"]["output_tail_in_readback"] is False
|
||
assert classification["evidence"]["unredacted_output_required"] is False
|
||
assert classification["safe_next_steps"] == [
|
||
"run_no_write_check_mode_replay",
|
||
"extract_sanitized_failed_task_summary",
|
||
"write_km_playbook_repair_candidate",
|
||
"retry_controlled_apply_only_after_check_mode_passes",
|
||
]
|
||
|
||
retry = readback["controlled_retry_package"]
|
||
assert retry["package_id"] == "ansible_retry:94925d5e"
|
||
assert retry["status"] == "ready_for_no_write_check_mode_replay"
|
||
assert retry["source_of_truth"] == {
|
||
"catalog_id": "ansible:188-ai-web",
|
||
"playbook_path": "infra/ansible/playbooks/188-ai-web.yml",
|
||
"source_diff_required_before_retry": True,
|
||
"failed_task_summary_required": True,
|
||
}
|
||
assert retry["preflight"]["no_write_check_mode_replay_required"] is True
|
||
assert retry["preflight"]["reuse_parent_check_mode_op_id"] == (
|
||
"8b555f41-e81f-4d8e-956b-fb20d358db63"
|
||
)
|
||
assert retry["apply_gate"]["controlled_apply_retry_allowed_now"] is False
|
||
assert retry["apply_gate"]["requires_check_mode_success_before_apply"] is True
|
||
assert retry["rollback"]["destructive_rollback_allowed"] is False
|
||
assert retry["post_apply"] == {
|
||
"post_apply_verifier_required": True,
|
||
"km_playbook_trust_writeback_required": True,
|
||
"telegram_receipt_required": True,
|
||
}
|
||
assert retry["next_ai_action"] == "run_no_write_check_mode_replay"
|