ea0d697e51
Some checks failed
Code Review / ai-code-review (push) Successful in 13s
CD Pipeline / tests (push) Successful in 1m54s
CD Pipeline / build-and-deploy (push) Successful in 5m8s
CD Pipeline / post-deploy-checks (push) Failing after 1m21s
Ansible / Reboot Recovery Contract / validate (push) Has been cancelled
939 lines
37 KiB
JSON
939 lines
37 KiB
JSON
{
|
|
"candidate_groups": {
|
|
"production_baseline": [
|
|
"openclaw_incumbent"
|
|
],
|
|
"replay_or_integration_blocked": [
|
|
"claude_agent_sdk_remediator",
|
|
"crewai_flows_crews",
|
|
"google_adk_stack",
|
|
"langgraph_incident_kernel",
|
|
"microsoft_agent_framework",
|
|
"nemo_nemotron_fabric",
|
|
"openai_agents_sdk_coordinator"
|
|
],
|
|
"watch_only_candidates": [
|
|
"agentos_framework",
|
|
"bernstein_agent_governance",
|
|
"hermes_agent_personal_platform",
|
|
"microsoft_agent_governance_toolkit",
|
|
"pydantic_deepagents",
|
|
"thclaws_agent_harness"
|
|
],
|
|
"watch_only_scorecard_prescreen_ready": []
|
|
},
|
|
"candidate_statuses": [
|
|
{
|
|
"approvals": {
|
|
"paid_api": false,
|
|
"production_routing": false,
|
|
"replay": false,
|
|
"sdk_install": false,
|
|
"shadow_or_canary": false
|
|
},
|
|
"candidate_id": "openclaw_incumbent",
|
|
"current_gate": "production_decision_core",
|
|
"display_name": "OpenClaw incumbent",
|
|
"evaluation_priority": "baseline",
|
|
"evidence": {
|
|
"latest_replay_summary": null,
|
|
"latest_smoke_gate": null,
|
|
"latest_smoke_matrix": null,
|
|
"latest_smoke_model": null
|
|
},
|
|
"gate_status": "production_baseline",
|
|
"integration_decision": "",
|
|
"operator_blockers": [],
|
|
"required_next_gate": "formal_replacement_adr_and_promotion_gate_required",
|
|
"role": "current_production_decision_core",
|
|
"score": null
|
|
},
|
|
{
|
|
"approvals": {
|
|
"paid_api": false,
|
|
"production_routing": false,
|
|
"replay": false,
|
|
"sdk_install": false,
|
|
"shadow_or_canary": false
|
|
},
|
|
"candidate_id": "openai_agents_sdk_coordinator",
|
|
"current_gate": "has_offline_replay_summary",
|
|
"display_name": "OpenAI Agents SDK Coordinator",
|
|
"evaluation_priority": "must_test",
|
|
"evidence": {
|
|
"latest_replay_summary": "docs/evaluations/agent_openai_coordinator_replay_summary_2026-06-02.json",
|
|
"latest_smoke_gate": null,
|
|
"latest_smoke_matrix": null,
|
|
"latest_smoke_model": null
|
|
},
|
|
"gate_status": "integration_blocked",
|
|
"integration_decision": "do_not_integrate_refresh_replay_gate",
|
|
"operator_blockers": [
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval",
|
|
"offline_adapter_contract_valid",
|
|
"50_record_hidden_label_replay_beats_openclaw_baseline",
|
|
"cost_approval_recorded"
|
|
],
|
|
"required_next_gate": "refresh_scorecard_then_offline_replay_or_promotion_gate",
|
|
"role": "coordinator_orchestrator",
|
|
"score": 0.87
|
|
},
|
|
{
|
|
"approvals": {
|
|
"paid_api": false,
|
|
"production_routing": false,
|
|
"replay": false,
|
|
"sdk_install": false,
|
|
"shadow_or_canary": false
|
|
},
|
|
"candidate_id": "langgraph_incident_kernel",
|
|
"current_gate": "has_offline_replay_summary",
|
|
"display_name": "LangGraph Incident Kernel",
|
|
"evaluation_priority": "must_test",
|
|
"evidence": {
|
|
"latest_replay_summary": "docs/evaluations/agent_langgraph_replay_summary_2026-06-02.json",
|
|
"latest_smoke_gate": null,
|
|
"latest_smoke_matrix": null,
|
|
"latest_smoke_model": null
|
|
},
|
|
"gate_status": "integration_blocked",
|
|
"integration_decision": "do_not_integrate_refresh_replay_gate",
|
|
"operator_blockers": [
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval",
|
|
"offline_adapter_contract_valid",
|
|
"50_record_hidden_label_replay_beats_openclaw_baseline"
|
|
],
|
|
"required_next_gate": "refresh_scorecard_then_offline_replay_or_promotion_gate",
|
|
"role": "durable_incident_workflow_kernel",
|
|
"score": 0.7867
|
|
},
|
|
{
|
|
"approvals": {
|
|
"paid_api": false,
|
|
"production_routing": false,
|
|
"replay": false,
|
|
"sdk_install": false,
|
|
"shadow_or_canary": false
|
|
},
|
|
"candidate_id": "nemo_nemotron_fabric",
|
|
"current_gate": "blocked_existing_replay_evidence",
|
|
"display_name": "NVIDIA NeMo Agent Toolkit + Nemotron Fabric",
|
|
"evaluation_priority": "must_test",
|
|
"evidence": {
|
|
"latest_replay_summary": null,
|
|
"latest_smoke_gate": "docs/evaluations/agent_nemotron_contract_tuned_49b_v15_smoke_gate_2026-06-02.json",
|
|
"latest_smoke_matrix": "docs/evaluations/agent_nemotron_contract_tuned_smoke_matrix_2026-06-02.json",
|
|
"latest_smoke_model": "nvidia/llama-3.3-nemotron-super-49b-v1.5"
|
|
},
|
|
"gate_status": "integration_blocked",
|
|
"integration_decision": "do_not_integrate_refresh_evidence_then_smoke_gate",
|
|
"operator_blockers": [
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval",
|
|
"5_record_smoke_gate_passes",
|
|
"latency_and_output_contract_blockers_resolved",
|
|
"cost_approval_recorded"
|
|
],
|
|
"required_next_gate": "refresh_source_evidence_then_5_record_smoke_only",
|
|
"role": "agent_fabric_tool_model_evaluator",
|
|
"score": 0.8033
|
|
},
|
|
{
|
|
"approvals": {
|
|
"paid_api": false,
|
|
"production_routing": false,
|
|
"replay": false,
|
|
"sdk_install": false,
|
|
"shadow_or_canary": false
|
|
},
|
|
"candidate_id": "claude_agent_sdk_remediator",
|
|
"current_gate": "has_offline_replay_summary",
|
|
"display_name": "Claude Agent SDK Remediator",
|
|
"evaluation_priority": "must_test",
|
|
"evidence": {
|
|
"latest_replay_summary": "docs/evaluations/agent_claude_remediator_replay_summary_2026-06-02.json",
|
|
"latest_smoke_gate": null,
|
|
"latest_smoke_matrix": null,
|
|
"latest_smoke_model": null
|
|
},
|
|
"gate_status": "integration_blocked",
|
|
"integration_decision": "do_not_integrate_refresh_replay_gate",
|
|
"operator_blockers": [
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval",
|
|
"offline_adapter_contract_valid",
|
|
"50_record_hidden_label_replay_beats_openclaw_baseline",
|
|
"cost_approval_recorded"
|
|
],
|
|
"required_next_gate": "refresh_scorecard_then_offline_replay_or_promotion_gate",
|
|
"role": "devops_code_remediation_agent",
|
|
"score": 0.7533
|
|
},
|
|
{
|
|
"approvals": {
|
|
"paid_api": false,
|
|
"production_routing": false,
|
|
"replay": false,
|
|
"sdk_install": false,
|
|
"shadow_or_canary": false
|
|
},
|
|
"candidate_id": "google_adk_stack",
|
|
"current_gate": "not_yet_replayed",
|
|
"display_name": "Google Agent Development Kit Stack",
|
|
"evaluation_priority": "can_test",
|
|
"evidence": {
|
|
"latest_replay_summary": null,
|
|
"latest_smoke_gate": null,
|
|
"latest_smoke_matrix": null,
|
|
"latest_smoke_model": null
|
|
},
|
|
"gate_status": "integration_blocked",
|
|
"integration_decision": "do_not_integrate_prepare_no_cost_offline_adapter",
|
|
"operator_blockers": [
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval",
|
|
"offline_adapter_contract_valid",
|
|
"50_record_hidden_label_replay_beats_openclaw_baseline",
|
|
"cost_approval_recorded"
|
|
],
|
|
"required_next_gate": "create_no_sdk_no_api_adapter_then_offline_replay",
|
|
"role": "gemini_vertex_agent_stack",
|
|
"score": 0.73
|
|
},
|
|
{
|
|
"approvals": {
|
|
"paid_api": false,
|
|
"production_routing": false,
|
|
"replay": false,
|
|
"sdk_install": false,
|
|
"shadow_or_canary": false
|
|
},
|
|
"candidate_id": "microsoft_agent_framework",
|
|
"current_gate": "not_yet_replayed",
|
|
"display_name": "Microsoft Agent Framework",
|
|
"evaluation_priority": "can_test",
|
|
"evidence": {
|
|
"latest_replay_summary": null,
|
|
"latest_smoke_gate": null,
|
|
"latest_smoke_matrix": null,
|
|
"latest_smoke_model": null
|
|
},
|
|
"gate_status": "integration_blocked",
|
|
"integration_decision": "do_not_integrate_prepare_no_cost_offline_adapter",
|
|
"operator_blockers": [
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval",
|
|
"offline_adapter_contract_valid",
|
|
"50_record_hidden_label_replay_beats_openclaw_baseline",
|
|
"cost_approval_recorded"
|
|
],
|
|
"required_next_gate": "create_no_sdk_no_api_adapter_then_offline_replay",
|
|
"role": "enterprise_workflow_agent_stack",
|
|
"score": 0.81
|
|
},
|
|
{
|
|
"approvals": {
|
|
"paid_api": false,
|
|
"production_routing": false,
|
|
"replay": false,
|
|
"sdk_install": false,
|
|
"shadow_or_canary": false
|
|
},
|
|
"candidate_id": "crewai_flows_crews",
|
|
"current_gate": "not_yet_replayed",
|
|
"display_name": "CrewAI Flows + Crews",
|
|
"evaluation_priority": "secondary",
|
|
"evidence": {
|
|
"latest_replay_summary": null,
|
|
"latest_smoke_gate": null,
|
|
"latest_smoke_matrix": null,
|
|
"latest_smoke_model": null
|
|
},
|
|
"gate_status": "integration_blocked",
|
|
"integration_decision": "do_not_integrate_prepare_no_cost_offline_adapter",
|
|
"operator_blockers": [
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval",
|
|
"offline_adapter_contract_valid",
|
|
"50_record_hidden_label_replay_beats_openclaw_baseline"
|
|
],
|
|
"required_next_gate": "create_no_sdk_no_api_adapter_then_offline_replay",
|
|
"role": "rapid_agent_team_prototype",
|
|
"score": 0.6033
|
|
},
|
|
{
|
|
"approvals": {
|
|
"paid_api": false,
|
|
"production_routing": false,
|
|
"replay": false,
|
|
"sdk_install": false,
|
|
"shadow_or_canary": false
|
|
},
|
|
"candidate_id": "hermes_agent_personal_platform",
|
|
"current_gate": "watch_only_primary_source_monitoring",
|
|
"display_name": "NousResearch Hermes Agent",
|
|
"evaluation_priority": "watch_only",
|
|
"evidence": {
|
|
"latest_replay_summary": null,
|
|
"latest_smoke_gate": null,
|
|
"latest_smoke_matrix": null,
|
|
"latest_smoke_model": null
|
|
},
|
|
"gate_status": "watch_only_blocked",
|
|
"integration_decision": "do_not_integrate_watch_only_primary_source_monitoring",
|
|
"operator_blockers": [
|
|
"discovery_classification_must_recommend_watch_addition",
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval",
|
|
"operator_confirms_primary_sources",
|
|
"watch_registry_baseline_refreshed",
|
|
"explicit_priority_upgrade_before_replay",
|
|
"cost_approval_recorded"
|
|
],
|
|
"required_next_gate": "continue_watch_only_until_primary_source_evidence_is_sufficient",
|
|
"role": "personal_agent_platform_candidate",
|
|
"score": null
|
|
},
|
|
{
|
|
"approvals": {
|
|
"paid_api": false,
|
|
"production_routing": false,
|
|
"replay": false,
|
|
"sdk_install": false,
|
|
"shadow_or_canary": false
|
|
},
|
|
"candidate_id": "microsoft_agent_governance_toolkit",
|
|
"current_gate": "watch_only_primary_source_monitoring",
|
|
"display_name": "Microsoft Agent Governance Toolkit",
|
|
"evaluation_priority": "watch_only",
|
|
"evidence": {
|
|
"latest_replay_summary": null,
|
|
"latest_smoke_gate": null,
|
|
"latest_smoke_matrix": null,
|
|
"latest_smoke_model": null
|
|
},
|
|
"gate_status": "watch_only_blocked",
|
|
"integration_decision": "do_not_integrate_watch_only_primary_source_monitoring",
|
|
"operator_blockers": [
|
|
"discovery_classification_must_recommend_watch_addition",
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval",
|
|
"operator_confirms_primary_sources",
|
|
"watch_registry_baseline_refreshed",
|
|
"explicit_priority_upgrade_before_replay"
|
|
],
|
|
"required_next_gate": "continue_watch_only_until_primary_source_evidence_is_sufficient",
|
|
"role": "agent_governance_policy_evaluator_candidate",
|
|
"score": null
|
|
},
|
|
{
|
|
"approvals": {
|
|
"paid_api": false,
|
|
"production_routing": false,
|
|
"replay": false,
|
|
"sdk_install": false,
|
|
"shadow_or_canary": false
|
|
},
|
|
"candidate_id": "thclaws_agent_harness",
|
|
"current_gate": "watch_only_primary_source_monitoring",
|
|
"display_name": "thClaws Agent Harness",
|
|
"evaluation_priority": "watch_only",
|
|
"evidence": {
|
|
"latest_replay_summary": null,
|
|
"latest_smoke_gate": null,
|
|
"latest_smoke_matrix": null,
|
|
"latest_smoke_model": null
|
|
},
|
|
"gate_status": "watch_only_blocked",
|
|
"integration_decision": "do_not_integrate_watch_only_primary_source_monitoring",
|
|
"operator_blockers": [
|
|
"discovery_classification_must_recommend_watch_addition",
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval",
|
|
"operator_confirms_primary_sources",
|
|
"watch_registry_baseline_refreshed",
|
|
"explicit_priority_upgrade_before_replay",
|
|
"cost_approval_recorded"
|
|
],
|
|
"required_next_gate": "continue_watch_only_until_primary_source_evidence_is_sufficient",
|
|
"role": "agent_framework_or_orchestrator_candidate",
|
|
"score": null
|
|
},
|
|
{
|
|
"approvals": {
|
|
"paid_api": false,
|
|
"production_routing": false,
|
|
"replay": false,
|
|
"sdk_install": false,
|
|
"shadow_or_canary": false
|
|
},
|
|
"candidate_id": "pydantic_deepagents",
|
|
"current_gate": "watch_only_primary_source_monitoring",
|
|
"display_name": "Pydantic DeepAgents",
|
|
"evaluation_priority": "watch_only",
|
|
"evidence": {
|
|
"latest_replay_summary": null,
|
|
"latest_smoke_gate": null,
|
|
"latest_smoke_matrix": null,
|
|
"latest_smoke_model": null
|
|
},
|
|
"gate_status": "watch_only_blocked",
|
|
"integration_decision": "do_not_integrate_watch_only_primary_source_monitoring",
|
|
"operator_blockers": [
|
|
"discovery_classification_must_recommend_watch_addition",
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval",
|
|
"operator_confirms_primary_sources",
|
|
"watch_registry_baseline_refreshed",
|
|
"explicit_priority_upgrade_before_replay",
|
|
"cost_approval_recorded"
|
|
],
|
|
"required_next_gate": "continue_watch_only_until_primary_source_evidence_is_sufficient",
|
|
"role": "agent_framework_or_orchestrator_candidate",
|
|
"score": null
|
|
},
|
|
{
|
|
"approvals": {
|
|
"paid_api": false,
|
|
"production_routing": false,
|
|
"replay": false,
|
|
"sdk_install": false,
|
|
"shadow_or_canary": false
|
|
},
|
|
"candidate_id": "agentos_framework",
|
|
"current_gate": "watch_only_primary_source_monitoring",
|
|
"display_name": "AgentOS Framework",
|
|
"evaluation_priority": "watch_only",
|
|
"evidence": {
|
|
"latest_replay_summary": null,
|
|
"latest_smoke_gate": null,
|
|
"latest_smoke_matrix": null,
|
|
"latest_smoke_model": null
|
|
},
|
|
"gate_status": "watch_only_blocked",
|
|
"integration_decision": "do_not_integrate_watch_only_primary_source_monitoring",
|
|
"operator_blockers": [
|
|
"discovery_classification_must_recommend_watch_addition",
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval",
|
|
"operator_confirms_primary_sources",
|
|
"watch_registry_baseline_refreshed",
|
|
"explicit_priority_upgrade_before_replay",
|
|
"cost_approval_recorded"
|
|
],
|
|
"required_next_gate": "continue_watch_only_until_primary_source_evidence_is_sufficient",
|
|
"role": "agent_framework_or_orchestrator_candidate",
|
|
"score": null
|
|
},
|
|
{
|
|
"approvals": {
|
|
"paid_api": false,
|
|
"production_routing": false,
|
|
"replay": false,
|
|
"sdk_install": false,
|
|
"shadow_or_canary": false
|
|
},
|
|
"candidate_id": "bernstein_agent_governance",
|
|
"current_gate": "watch_only_primary_source_monitoring",
|
|
"display_name": "Bernstein Agent Governance",
|
|
"evaluation_priority": "watch_only",
|
|
"evidence": {
|
|
"latest_replay_summary": null,
|
|
"latest_smoke_gate": null,
|
|
"latest_smoke_matrix": null,
|
|
"latest_smoke_model": null
|
|
},
|
|
"gate_status": "watch_only_blocked",
|
|
"integration_decision": "do_not_integrate_watch_only_primary_source_monitoring",
|
|
"operator_blockers": [
|
|
"discovery_classification_must_recommend_watch_addition",
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval",
|
|
"operator_confirms_primary_sources",
|
|
"watch_registry_baseline_refreshed",
|
|
"explicit_priority_upgrade_before_replay",
|
|
"cost_approval_recorded"
|
|
],
|
|
"required_next_gate": "continue_watch_only_until_primary_source_evidence_is_sufficient",
|
|
"role": "agent_governance_policy_evaluator_candidate",
|
|
"score": null
|
|
}
|
|
],
|
|
"current_decision": "openclaw_remains_production_decision_core",
|
|
"evaluation_cadence": {
|
|
"next_scheduled_run_at": "2026-06-29T09:00:00+08:00",
|
|
"operator_review_gate": "priority_upgrade_required_before_scorecard_replay_sdk_api_shadow_canary_or_production",
|
|
"primary_source_policy": "primary_sources_only_no_llm_no_sdk_no_paid_api",
|
|
"schedule": "weekly_monday_0900_asia_taipei",
|
|
"timezone": "Asia/Taipei",
|
|
"trigger_modes": [
|
|
"scheduled_weekly",
|
|
"manual_dispatch",
|
|
"operator_triggered_after_primary_source_signal"
|
|
],
|
|
"workflow": ".gitea/workflows/agent-market-watch.yaml"
|
|
},
|
|
"forbidden_actions_without_new_approval": [
|
|
"replace_openclaw",
|
|
"enter_shadow_or_canary",
|
|
"install_new_agent_sdk",
|
|
"call_paid_provider_api",
|
|
"run_replay_for_watch_only_candidate",
|
|
"change_production_routing"
|
|
],
|
|
"generated_at": "2026-06-25T02:35:15.699321+00:00",
|
|
"inputs": {
|
|
"candidate_registry_schema_version": "agent_replacement_candidates_v1",
|
|
"discovery_classification_generated_at": "2026-06-25T02:34:09.078342+00:00",
|
|
"integration_review_generated_at": "2026-06-25T02:33:53.438121+00:00",
|
|
"promotion_review_generated_at": "2026-06-25T02:34:25.892815+00:00",
|
|
"watch_report_generated_at": "2026-06-25T02:33:12.868785+00:00"
|
|
},
|
|
"market_watch_health": {
|
|
"blocked_from_integration": 13,
|
|
"freshness_sla_hours": 168,
|
|
"operator_blockers": [
|
|
"unclassified_discovery_watch_additions_remaining",
|
|
"integration_queue_not_empty"
|
|
],
|
|
"source_failures_block_priority_upgrade": false,
|
|
"stale_after": "2026-06-29T15:00:00+08:00",
|
|
"stale_grace_hours": 6,
|
|
"status": "blocked"
|
|
},
|
|
"next_allowed_actions": [
|
|
"continue_weekly_primary_source_market_watch",
|
|
"rerun_existing_replay_only_after_evidence_or_adapter_change"
|
|
],
|
|
"operator_decision_queue": [
|
|
{
|
|
"approval_boundary": {
|
|
"market_scorecard_update_required": false,
|
|
"paid_api_approval_required": true,
|
|
"priority_upgrade_required": false,
|
|
"production_routing_approval_required": true,
|
|
"replacement_adr_required": true,
|
|
"replay_approval_required": true,
|
|
"sdk_install_approval_required": true,
|
|
"shadow_or_canary_approval_required": true
|
|
},
|
|
"candidate_id": "claude_agent_sdk_remediator",
|
|
"display_name": "Claude Agent SDK Remediator",
|
|
"evidence_refs": [
|
|
"docs/evaluations/agent_claude_remediator_replay_summary_2026-06-02.json"
|
|
],
|
|
"priority": 10,
|
|
"queue_status": "blocked_needs_evidence",
|
|
"recommended_action": "refresh_scorecard_then_offline_replay_or_promotion_gate",
|
|
"risk_notes": [
|
|
"Best fit is code and DevOps remediation, not necessarily central incident arbitration.",
|
|
"API cost, subscription separation, and vendor boundary must be validated.",
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval"
|
|
]
|
|
},
|
|
{
|
|
"approval_boundary": {
|
|
"market_scorecard_update_required": false,
|
|
"paid_api_approval_required": false,
|
|
"priority_upgrade_required": false,
|
|
"production_routing_approval_required": true,
|
|
"replacement_adr_required": true,
|
|
"replay_approval_required": true,
|
|
"sdk_install_approval_required": true,
|
|
"shadow_or_canary_approval_required": true
|
|
},
|
|
"candidate_id": "crewai_flows_crews",
|
|
"display_name": "CrewAI Flows + Crews",
|
|
"evidence_refs": [],
|
|
"priority": 10,
|
|
"queue_status": "blocked_needs_evidence",
|
|
"recommended_action": "create_no_sdk_no_api_adapter_then_offline_replay",
|
|
"risk_notes": [
|
|
"Better for rapid automation teams than high-risk production AIOps core.",
|
|
"Durability, strict audit, and permission boundary must be proven in replay.",
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval"
|
|
]
|
|
},
|
|
{
|
|
"approval_boundary": {
|
|
"market_scorecard_update_required": false,
|
|
"paid_api_approval_required": true,
|
|
"priority_upgrade_required": false,
|
|
"production_routing_approval_required": true,
|
|
"replacement_adr_required": true,
|
|
"replay_approval_required": true,
|
|
"sdk_install_approval_required": true,
|
|
"shadow_or_canary_approval_required": true
|
|
},
|
|
"candidate_id": "google_adk_stack",
|
|
"display_name": "Google Agent Development Kit Stack",
|
|
"evidence_refs": [],
|
|
"priority": 10,
|
|
"queue_status": "blocked_needs_evidence",
|
|
"recommended_action": "create_no_sdk_no_api_adapter_then_offline_replay",
|
|
"risk_notes": [
|
|
"Gemini/Vertex ecosystem dependency must be justified against current local-first policy.",
|
|
"AIOps tool safety and rollback gates still need AWOOOI-specific implementation.",
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval"
|
|
]
|
|
},
|
|
{
|
|
"approval_boundary": {
|
|
"market_scorecard_update_required": false,
|
|
"paid_api_approval_required": false,
|
|
"priority_upgrade_required": false,
|
|
"production_routing_approval_required": true,
|
|
"replacement_adr_required": true,
|
|
"replay_approval_required": true,
|
|
"sdk_install_approval_required": true,
|
|
"shadow_or_canary_approval_required": true
|
|
},
|
|
"candidate_id": "langgraph_incident_kernel",
|
|
"display_name": "LangGraph Incident Kernel",
|
|
"evidence_refs": [
|
|
"docs/evaluations/agent_langgraph_replay_summary_2026-06-02.json"
|
|
],
|
|
"priority": 10,
|
|
"queue_status": "blocked_needs_evidence",
|
|
"recommended_action": "refresh_scorecard_then_offline_replay_or_promotion_gate",
|
|
"risk_notes": [
|
|
"It is a workflow kernel, not a smarter model by itself.",
|
|
"Tool safety and evaluation metrics must be implemented by AWOOOI adapters.",
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval"
|
|
]
|
|
},
|
|
{
|
|
"approval_boundary": {
|
|
"market_scorecard_update_required": false,
|
|
"paid_api_approval_required": true,
|
|
"priority_upgrade_required": false,
|
|
"production_routing_approval_required": true,
|
|
"replacement_adr_required": true,
|
|
"replay_approval_required": true,
|
|
"sdk_install_approval_required": true,
|
|
"shadow_or_canary_approval_required": true
|
|
},
|
|
"candidate_id": "microsoft_agent_framework",
|
|
"display_name": "Microsoft Agent Framework",
|
|
"evidence_refs": [],
|
|
"priority": 10,
|
|
"queue_status": "blocked_needs_evidence",
|
|
"recommended_action": "create_no_sdk_no_api_adapter_then_offline_replay",
|
|
"risk_notes": [
|
|
"Public preview status and Microsoft ecosystem fit must be assessed.",
|
|
"Python/FastAPI/K8s integration cost is likely higher than LangGraph or NeMo.",
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval"
|
|
]
|
|
},
|
|
{
|
|
"approval_boundary": {
|
|
"market_scorecard_update_required": false,
|
|
"paid_api_approval_required": true,
|
|
"priority_upgrade_required": false,
|
|
"production_routing_approval_required": true,
|
|
"replacement_adr_required": true,
|
|
"replay_approval_required": true,
|
|
"sdk_install_approval_required": true,
|
|
"shadow_or_canary_approval_required": true
|
|
},
|
|
"candidate_id": "nemo_nemotron_fabric",
|
|
"display_name": "NVIDIA NeMo Agent Toolkit + Nemotron Fabric",
|
|
"evidence_refs": [
|
|
"nvidia/llama-3.3-nemotron-super-49b-v1.5",
|
|
"docs/evaluations/agent_nemotron_contract_tuned_49b_v15_smoke_gate_2026-06-02.json",
|
|
"docs/evaluations/agent_nemotron_contract_tuned_smoke_matrix_2026-06-02.json"
|
|
],
|
|
"priority": 10,
|
|
"queue_status": "blocked_needs_evidence",
|
|
"recommended_action": "refresh_source_evidence_then_5_record_smoke_only",
|
|
"risk_notes": [
|
|
"Needs AWOOOI-specific HITL and dangerous-action policy integration.",
|
|
"GPU/NIM operating cost must be compared against current local inference.",
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval"
|
|
]
|
|
},
|
|
{
|
|
"approval_boundary": {
|
|
"market_scorecard_update_required": false,
|
|
"paid_api_approval_required": true,
|
|
"priority_upgrade_required": false,
|
|
"production_routing_approval_required": true,
|
|
"replacement_adr_required": true,
|
|
"replay_approval_required": true,
|
|
"sdk_install_approval_required": true,
|
|
"shadow_or_canary_approval_required": true
|
|
},
|
|
"candidate_id": "openai_agents_sdk_coordinator",
|
|
"display_name": "OpenAI Agents SDK Coordinator",
|
|
"evidence_refs": [
|
|
"docs/evaluations/agent_openai_coordinator_replay_summary_2026-06-02.json"
|
|
],
|
|
"priority": 10,
|
|
"queue_status": "blocked_needs_evidence",
|
|
"recommended_action": "refresh_scorecard_then_offline_replay_or_promotion_gate",
|
|
"risk_notes": [
|
|
"Cloud dependency and sensitive trace handling must pass AWOOOI privacy gates.",
|
|
"Built-in hosted execution tools need separate guardrail validation.",
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval"
|
|
]
|
|
},
|
|
{
|
|
"approval_boundary": {
|
|
"market_scorecard_update_required": true,
|
|
"paid_api_approval_required": true,
|
|
"priority_upgrade_required": true,
|
|
"production_routing_approval_required": true,
|
|
"replacement_adr_required": true,
|
|
"replay_approval_required": true,
|
|
"sdk_install_approval_required": true,
|
|
"shadow_or_canary_approval_required": true
|
|
},
|
|
"candidate_id": "agentos_framework",
|
|
"display_name": "AgentOS Framework",
|
|
"evidence_refs": [],
|
|
"priority": 40,
|
|
"queue_status": "watch_only_blocked",
|
|
"recommended_action": "continue_watch_only_until_primary_source_evidence_is_sufficient",
|
|
"risk_notes": [
|
|
"candidate missing from current market scorecard",
|
|
"discovery_classification_must_recommend_watch_addition",
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval"
|
|
]
|
|
},
|
|
{
|
|
"approval_boundary": {
|
|
"market_scorecard_update_required": true,
|
|
"paid_api_approval_required": true,
|
|
"priority_upgrade_required": true,
|
|
"production_routing_approval_required": true,
|
|
"replacement_adr_required": true,
|
|
"replay_approval_required": true,
|
|
"sdk_install_approval_required": true,
|
|
"shadow_or_canary_approval_required": true
|
|
},
|
|
"candidate_id": "bernstein_agent_governance",
|
|
"display_name": "Bernstein Agent Governance",
|
|
"evidence_refs": [],
|
|
"priority": 40,
|
|
"queue_status": "watch_only_blocked",
|
|
"recommended_action": "continue_watch_only_until_primary_source_evidence_is_sufficient",
|
|
"risk_notes": [
|
|
"candidate missing from current market scorecard",
|
|
"discovery_classification_must_recommend_watch_addition",
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval"
|
|
]
|
|
},
|
|
{
|
|
"approval_boundary": {
|
|
"market_scorecard_update_required": true,
|
|
"paid_api_approval_required": true,
|
|
"priority_upgrade_required": true,
|
|
"production_routing_approval_required": true,
|
|
"replacement_adr_required": true,
|
|
"replay_approval_required": true,
|
|
"sdk_install_approval_required": true,
|
|
"shadow_or_canary_approval_required": true
|
|
},
|
|
"candidate_id": "hermes_agent_personal_platform",
|
|
"display_name": "NousResearch Hermes Agent",
|
|
"evidence_refs": [],
|
|
"priority": 40,
|
|
"queue_status": "watch_only_blocked",
|
|
"recommended_action": "continue_watch_only_until_primary_source_evidence_is_sufficient",
|
|
"risk_notes": [
|
|
"candidate missing from current market scorecard",
|
|
"discovery_classification_must_recommend_watch_addition",
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval"
|
|
]
|
|
},
|
|
{
|
|
"approval_boundary": {
|
|
"market_scorecard_update_required": true,
|
|
"paid_api_approval_required": false,
|
|
"priority_upgrade_required": true,
|
|
"production_routing_approval_required": true,
|
|
"replacement_adr_required": true,
|
|
"replay_approval_required": true,
|
|
"sdk_install_approval_required": true,
|
|
"shadow_or_canary_approval_required": true
|
|
},
|
|
"candidate_id": "microsoft_agent_governance_toolkit",
|
|
"display_name": "Microsoft Agent Governance Toolkit",
|
|
"evidence_refs": [],
|
|
"priority": 40,
|
|
"queue_status": "watch_only_blocked",
|
|
"recommended_action": "continue_watch_only_until_primary_source_evidence_is_sufficient",
|
|
"risk_notes": [
|
|
"candidate missing from current market scorecard",
|
|
"discovery_classification_must_recommend_watch_addition",
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval"
|
|
]
|
|
},
|
|
{
|
|
"approval_boundary": {
|
|
"market_scorecard_update_required": true,
|
|
"paid_api_approval_required": true,
|
|
"priority_upgrade_required": true,
|
|
"production_routing_approval_required": true,
|
|
"replacement_adr_required": true,
|
|
"replay_approval_required": true,
|
|
"sdk_install_approval_required": true,
|
|
"shadow_or_canary_approval_required": true
|
|
},
|
|
"candidate_id": "pydantic_deepagents",
|
|
"display_name": "Pydantic DeepAgents",
|
|
"evidence_refs": [],
|
|
"priority": 40,
|
|
"queue_status": "watch_only_blocked",
|
|
"recommended_action": "continue_watch_only_until_primary_source_evidence_is_sufficient",
|
|
"risk_notes": [
|
|
"candidate missing from current market scorecard",
|
|
"discovery_classification_must_recommend_watch_addition",
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval"
|
|
]
|
|
},
|
|
{
|
|
"approval_boundary": {
|
|
"market_scorecard_update_required": true,
|
|
"paid_api_approval_required": true,
|
|
"priority_upgrade_required": true,
|
|
"production_routing_approval_required": true,
|
|
"replacement_adr_required": true,
|
|
"replay_approval_required": true,
|
|
"sdk_install_approval_required": true,
|
|
"shadow_or_canary_approval_required": true
|
|
},
|
|
"candidate_id": "thclaws_agent_harness",
|
|
"display_name": "thClaws Agent Harness",
|
|
"evidence_refs": [],
|
|
"priority": 40,
|
|
"queue_status": "watch_only_blocked",
|
|
"recommended_action": "continue_watch_only_until_primary_source_evidence_is_sufficient",
|
|
"risk_notes": [
|
|
"candidate missing from current market scorecard",
|
|
"discovery_classification_must_recommend_watch_addition",
|
|
"changed_sources_reviewed_by_operator",
|
|
"market_scorecard_refreshed_if_primary_sources_changed_semantically",
|
|
"no_sdk_install_without_dependency_approval",
|
|
"no_paid_provider_use_without_cost_and_data_boundary_approval"
|
|
]
|
|
},
|
|
{
|
|
"approval_boundary": {
|
|
"market_scorecard_update_required": false,
|
|
"paid_api_approval_required": false,
|
|
"priority_upgrade_required": false,
|
|
"production_routing_approval_required": true,
|
|
"replacement_adr_required": true,
|
|
"replay_approval_required": false,
|
|
"sdk_install_approval_required": false,
|
|
"shadow_or_canary_approval_required": false
|
|
},
|
|
"candidate_id": "openclaw_incumbent",
|
|
"display_name": "OpenClaw incumbent",
|
|
"evidence_refs": [],
|
|
"priority": 90,
|
|
"queue_status": "baseline_protected",
|
|
"recommended_action": "keep_openclaw_as_production_decision_core_until_formal_replacement_adr",
|
|
"risk_notes": [
|
|
"no_candidate_has_formal_replacement_approval"
|
|
]
|
|
}
|
|
],
|
|
"policy": {
|
|
"market_scorecard_update_approved": false,
|
|
"paid_api_calls_approved": false,
|
|
"priority_upgrade_approved": false,
|
|
"production_changes_approved": false,
|
|
"replacement_decision_allowed": false,
|
|
"replay_candidate_approved": false,
|
|
"sdk_installation_approved": false,
|
|
"shadow_or_canary_approved": false,
|
|
"snapshot_is_decision_source": false
|
|
},
|
|
"schema_version": "agent_market_governance_snapshot_v1",
|
|
"summary": {
|
|
"blocked_from_integration": 13,
|
|
"candidate_count": 13,
|
|
"changed_candidates": 13,
|
|
"eligible_for_market_scorecard_prescreen": 0,
|
|
"integration_queue_count": 13,
|
|
"market_scorecard_updates_approved": 0,
|
|
"paid_api_calls_approved": 0,
|
|
"priority_upgrades_approved": 0,
|
|
"production_changes_approved": 0,
|
|
"recommended_watch_additions_remaining": 5,
|
|
"replacement_decisions_approved": 0,
|
|
"replay_candidates_approved": 0,
|
|
"sdk_installations_approved": 0,
|
|
"shadow_or_canary_approved": 0,
|
|
"source_count": 34,
|
|
"source_failures": 0,
|
|
"watch_only_candidates_reviewed": 6
|
|
}
|
|
}
|