fix(agent): normalize ssh session timeout blocker
Some checks failed
CD Pipeline / workflow-shape (push) Successful in 0s
CD Pipeline / cancel-stale-cd (push) Has been skipped
CD Pipeline / tests (push) Successful in 35s
CD Pipeline / build-and-deploy (push) Failing after 27s
CD Pipeline / post-deploy-checks (push) Has been skipped
Some checks failed
CD Pipeline / workflow-shape (push) Successful in 0s
CD Pipeline / cancel-stale-cd (push) Has been skipped
CD Pipeline / tests (push) Successful in 35s
CD Pipeline / build-and-deploy (push) Failing after 27s
CD Pipeline / post-deploy-checks (push) Has been skipped
This commit is contained in:
@@ -614,6 +614,14 @@ def _queue_readback_normalizer_contract() -> list[dict[str, Any]]:
|
||||
],
|
||||
"learning_targets": ["km", "rag", "playbook", "mcp", "verifier", "ai_agent"],
|
||||
},
|
||||
{
|
||||
"field_id": "latest_visible_harbor_110_repair_remote_ssh_server_accepts_key_then_session_timeout",
|
||||
"purpose": "classify whether 110 accepts the SSH key and then times out during session, PAM, account, or shell setup",
|
||||
"writes_blockers": [
|
||||
"gitea_queue_harbor_110_remote_ssh_server_accepts_key_then_session_timeout",
|
||||
],
|
||||
"learning_targets": ["km", "rag", "playbook", "mcp", "verifier", "ai_agent"],
|
||||
},
|
||||
{
|
||||
"field_id": "current_cd_workflow_runner_readiness",
|
||||
"purpose": "classify whether current CD is waiting on a non110 runner label",
|
||||
|
||||
@@ -37,7 +37,7 @@ def _assert_log_controlled_writeback_executor(payload: dict):
|
||||
assert payload["rollups"]["current_blocker_control_path_blocked_count"] == 1
|
||||
assert (
|
||||
payload["rollups"]["current_blocker_control_path_pressure_blocked_count"]
|
||||
== 1
|
||||
== 0
|
||||
)
|
||||
assert payload["rollups"]["current_blocker_local_recovery_package_count"] == 1
|
||||
assert payload["rollups"]["runtime_dispatch_performed"] is False
|
||||
@@ -75,11 +75,11 @@ def _assert_log_controlled_writeback_executor(payload: dict):
|
||||
"forbidden_runtime_actions"
|
||||
]
|
||||
assert current_queue["external_control_path_blocker"] == (
|
||||
"remote_ssh_publickey_auth_stalled"
|
||||
"remote_ssh_server_accepts_key_then_session_timeout"
|
||||
)
|
||||
assert current_queue["node_load_classifier"] == "high_load"
|
||||
assert current_queue["node_load_high"] is True
|
||||
assert current_queue["control_path_pressure_blocker"] == "node_load_high"
|
||||
assert current_queue["node_load_classifier"] == "load_not_high"
|
||||
assert current_queue["node_load_high"] is False
|
||||
assert current_queue["control_path_pressure_blocker"] == ""
|
||||
assert context["raw_payload_required"] is False
|
||||
|
||||
boundaries = payload["operation_boundaries"]
|
||||
|
||||
@@ -67,7 +67,7 @@ def _assert_executor_readback(payload: dict, *, public_endpoint: bool = False):
|
||||
assert payload["rollups"]["current_blocker_control_path_blocked_count"] == 1
|
||||
assert (
|
||||
payload["rollups"]["current_blocker_control_path_pressure_blocked_count"]
|
||||
== 1
|
||||
== 0
|
||||
)
|
||||
assert payload["rollups"]["current_blocker_local_recovery_package_count"] == 1
|
||||
assert (
|
||||
@@ -129,8 +129,8 @@ def _assert_executor_readback(payload: dict, *, public_endpoint: bool = False):
|
||||
"controlled_recovery_packaged_waiting_control_path_readback"
|
||||
)
|
||||
assert current_queue[0]["runner_label"] == "awoooi-non110-host"
|
||||
assert current_queue[0]["node_load_classifier"] == "high_load"
|
||||
assert current_queue[0]["node_load_high"] is True
|
||||
assert current_queue[0]["node_load_classifier"] == "load_not_high"
|
||||
assert current_queue[0]["node_load_high"] is False
|
||||
assert current_queue[0]["registry_v2_status"] == 502
|
||||
assert current_queue[0]["controlled_recovery_package"] == (
|
||||
"recover-110-control-path-and-harbor-local.sh --check"
|
||||
@@ -187,7 +187,7 @@ def _assert_executor_readback(payload: dict, *, public_endpoint: bool = False):
|
||||
]
|
||||
for item in current_queue[0]["harbor_recovery_receipt_output_contract"]
|
||||
)
|
||||
assert current_queue[0]["queue_readback_normalizer_contract_count"] == 7
|
||||
assert current_queue[0]["queue_readback_normalizer_contract_count"] == 8
|
||||
assert [
|
||||
item["field_id"]
|
||||
for item in current_queue[0]["queue_readback_normalizer_contract"]
|
||||
@@ -197,6 +197,7 @@ def _assert_executor_readback(payload: dict, *, public_endpoint: bool = False):
|
||||
"latest_visible_harbor_110_repair_no_matching_runner_label",
|
||||
"latest_visible_harbor_110_repair_remote_control_channel_unavailable",
|
||||
"latest_visible_harbor_110_repair_remote_ssh_publickey_auth_stalled",
|
||||
"latest_visible_harbor_110_repair_remote_ssh_server_accepts_key_then_session_timeout",
|
||||
"current_cd_workflow_runner_readiness",
|
||||
"controlled_profile_no_matching_runner_labels",
|
||||
]
|
||||
@@ -237,9 +238,9 @@ def _assert_executor_readback(payload: dict, *, public_endpoint: bool = False):
|
||||
)
|
||||
assert current_queue[0]["runtime_apply_required_on_110_local_console"] is True
|
||||
assert current_queue[0]["external_control_path_blocker"] == (
|
||||
"remote_ssh_publickey_auth_stalled"
|
||||
"remote_ssh_server_accepts_key_then_session_timeout"
|
||||
)
|
||||
assert current_queue[0]["control_path_pressure_blocker"] == "node_load_high"
|
||||
assert current_queue[0]["control_path_pressure_blocker"] == ""
|
||||
assert current_queue[0]["control_channel_readback_required"] is True
|
||||
assert set(current_queue[0]["learning_writeback_targets"]) == set(batches)
|
||||
assert len(current_queue[0]["target_batches"]) == 6
|
||||
|
||||
@@ -167,7 +167,7 @@ def _assert_controlled_writeback_plan(payload: dict, *, public_endpoint: bool =
|
||||
assert {
|
||||
plan["current_blocker_recovery"]["external_control_path_blocker"]
|
||||
for plan in p0_plans
|
||||
} == {"remote_ssh_publickey_auth_stalled"}
|
||||
} == {"remote_ssh_server_accepts_key_then_session_timeout"}
|
||||
|
||||
boundaries = payload["operation_boundaries"]
|
||||
assert boundaries["plan_readback_only"] is True
|
||||
|
||||
@@ -107,11 +107,17 @@ def _assert_log_intelligence_payload(payload: dict):
|
||||
"harbor_110_remote_ssh_publickey_auth_stalled"
|
||||
)
|
||||
assert p0_sample["classification"]["ssh_auth_classification"] == (
|
||||
"remote_ssh_publickey_auth_stalled"
|
||||
"remote_ssh_server_accepts_key_then_session_timeout"
|
||||
)
|
||||
assert p0_sample["classification"]["remote_control_channel"] == "unavailable"
|
||||
assert p0_sample["classification"]["bounded_ssh_timeout_seen"] is True
|
||||
assert p0_sample["classification"]["remote_ssh_publickey_auth_stalled"] is True
|
||||
assert (
|
||||
p0_sample["classification"][
|
||||
"remote_ssh_server_accepts_key_then_session_timeout"
|
||||
]
|
||||
is True
|
||||
)
|
||||
assert p0_sample["classification"]["remote_ssh_auth_permission_denied"] is False
|
||||
assert p0_sample["classification"]["remote_ssh_reachable"] is True
|
||||
assert p0_sample["classification"]["controlled_recovery_package"] == (
|
||||
@@ -131,7 +137,13 @@ def _assert_log_intelligence_payload(payload: dict):
|
||||
"verify_harbor_queue_and_controlled_cd_lane",
|
||||
]
|
||||
assert recovery_plan[0]["mode"] == "read_only"
|
||||
assert recovery_plan[0]["expected_result"] == (
|
||||
"remote_ssh_server_accepts_key_then_session_timeout_classifier_without_secret_material"
|
||||
)
|
||||
assert recovery_plan[2]["mode"] == "controlled_apply"
|
||||
assert recovery_plan[2]["expected_result"] == (
|
||||
"ssh_session_pam_account_or_shell_path_repaired_without_key_material_read"
|
||||
)
|
||||
assert recovery_plan[2]["runtime_write_allowed_only_on_110_local_console"] is True
|
||||
assert "read-public-gitea-actions-queue.py --json" in p0_sample[
|
||||
"classification"
|
||||
|
||||
@@ -261,12 +261,10 @@ def test_awoooi_priority_work_order_readback_overlays_ai_loop_current_blocker_qu
|
||||
"harbor_110_remote_ssh_publickey_auth_stalled"
|
||||
)
|
||||
assert state["ai_loop_current_blocker_control_path_blocker"] == (
|
||||
"remote_ssh_publickey_auth_stalled"
|
||||
"remote_ssh_server_accepts_key_then_session_timeout"
|
||||
)
|
||||
assert state["ai_loop_current_blocker_control_path_pressure_blocker"] == (
|
||||
"node_load_high"
|
||||
)
|
||||
assert state["ai_loop_current_blocker_node_load_classifier"] == "high_load"
|
||||
assert state["ai_loop_current_blocker_control_path_pressure_blocker"] == ""
|
||||
assert state["ai_loop_current_blocker_node_load_classifier"] == "load_not_high"
|
||||
assert evidence["ai_loop_current_blocker_execution_queue_count"] == 1
|
||||
assert evidence["ai_loop_current_blocker_id"] == (
|
||||
"harbor_110_remote_ssh_publickey_auth_stalled"
|
||||
@@ -283,12 +281,10 @@ def test_awoooi_priority_work_order_readback_overlays_ai_loop_current_blocker_qu
|
||||
"controlled_after_110_local_console_preflight"
|
||||
)
|
||||
assert evidence["ai_loop_current_blocker_control_path_blocker"] == (
|
||||
"remote_ssh_publickey_auth_stalled"
|
||||
"remote_ssh_server_accepts_key_then_session_timeout"
|
||||
)
|
||||
assert evidence["ai_loop_current_blocker_control_path_pressure_blocker"] == (
|
||||
"node_load_high"
|
||||
)
|
||||
assert evidence["ai_loop_current_blocker_node_load_classifier"] == "high_load"
|
||||
assert evidence["ai_loop_current_blocker_control_path_pressure_blocker"] == ""
|
||||
assert evidence["ai_loop_current_blocker_node_load_classifier"] == "load_not_high"
|
||||
assert set(evidence["ai_loop_current_blocker_learning_writeback_targets"]) == {
|
||||
"km",
|
||||
"rag",
|
||||
@@ -369,6 +365,7 @@ def test_awoooi_priority_work_order_readback_overlays_ai_loop_current_blocker_qu
|
||||
"latest_visible_harbor_110_repair_no_matching_runner_label",
|
||||
"latest_visible_harbor_110_repair_remote_control_channel_unavailable",
|
||||
"latest_visible_harbor_110_repair_remote_ssh_publickey_auth_stalled",
|
||||
"latest_visible_harbor_110_repair_remote_ssh_server_accepts_key_then_session_timeout",
|
||||
"current_cd_workflow_runner_readiness",
|
||||
"controlled_profile_no_matching_runner_labels",
|
||||
]
|
||||
@@ -394,11 +391,9 @@ def test_awoooi_priority_work_order_readback_overlays_ai_loop_current_blocker_qu
|
||||
assert payload["summary"]["ai_loop_current_blocker_id"] == (
|
||||
"harbor_110_remote_ssh_publickey_auth_stalled"
|
||||
)
|
||||
assert payload["summary"]["ai_loop_current_blocker_control_path_pressure_blocker"] == (
|
||||
"node_load_high"
|
||||
)
|
||||
assert payload["summary"]["ai_loop_current_blocker_control_path_pressure_blocker"] == ""
|
||||
assert payload["summary"]["ai_loop_current_blocker_node_load_classifier"] == (
|
||||
"high_load"
|
||||
"load_not_high"
|
||||
)
|
||||
assert payload["summary"]["ai_loop_current_blocker_local_console_phase_count"] == 5
|
||||
assert payload["summary"][
|
||||
@@ -429,7 +424,7 @@ def test_awoooi_priority_work_order_readback_overlays_ai_loop_current_blocker_qu
|
||||
payload["summary"][
|
||||
"ai_loop_current_blocker_queue_readback_normalizer_contract_count"
|
||||
]
|
||||
== 7
|
||||
== 8
|
||||
)
|
||||
assert payload["summary"][
|
||||
"ai_loop_current_blocker_queue_readback_normalizer_field_ids"
|
||||
|
||||
Reference in New Issue
Block a user