# AUTO-GENERATED by scripts/build_concepts_yaml.py — DO NOT EDIT BY HAND. # Single source of truth for canonical concepts, derived from # CONCEPT: markers in agent_utilities/ (*.py, *.rs). generated_by: scripts/build_concepts_yaml.py total_concepts: 1186 total_pillars: 9 pillars: - AU-AHE - AU-ECO - AU-KG - AU-ORCH - AU-OS - EG-AHE - EG-KG - EG-ORCH - EG-OS concepts: - id: AU-AHE.assimilation.baseline-overfit-gate name: AU-AHE.assimilation.baseline-overfit-gate pillar: AU-AHE status: live code_paths: - agent_utilities/harness/baseline_overfit_gate.py doc: AU-AHE.assimilation.baseline-overfit-gate - id: AU-AHE.assimilation.decision-distillation name: the expert agent writes one per decision; a nightly distill pillar: AU-AHE status: live code_paths: - agent_utilities/models/domains/finance.py - agent_utilities/models/schema_packs/finance.py doc: the expert agent writes one per decision; a nightly distill - id: AU-AHE.assimilation.empirical-parity-evidence-assimilation name: empirical parity evidence for the assimilation program pillar: AU-AHE status: live code_paths: - agent_utilities/harness/__init__.py - agent_utilities/harness/assimilation_benchmark.py doc: empirical parity evidence for the assimilation program - id: AU-AHE.assimilation.merge-entities name: merge entities pillar: AU-AHE status: live code_paths: - agent_utilities/knowledge_graph/assimilation/dedup.py - agent_utilities/knowledge_graph/assimilation/entity_resolution.py doc: merge entities - id: AU-AHE.assimilation.microstructure-signal-fusion name: closes the priors→weights loop pillar: AU-AHE status: live code_paths: - agent_utilities/domains/finance/signal_fusion.py - agent_utilities/knowledge_graph/orchestration/engine_finance.py - agent_utilities/models/domains/finance.py - agent_utilities/models/knowledge_graph.py - agent_utilities/models/schema_packs/finance.py doc: closes the priors→weights loop - id: AU-AHE.assimilation.research-auto-merge name: consider promoting the team pillar: AU-AHE status: live code_paths: - agent_utilities/knowledge_graph/research/auto_merge.py - agent_utilities/knowledge_graph/research/loop_controller.py doc: consider promoting the team - id: AU-AHE.assimilation.research-pipeline name: microstructure, trading, pricing pillar: AU-AHE status: live code_paths: - agent_utilities/automation/research_pipeline.py doc: microstructure, trading, pricing - id: AU-AHE.assimilation.research-source-grading name: AU-AHE.assimilation.research-source-grading pillar: AU-AHE status: live code_paths: - agent_utilities/knowledge_graph/research/fleet_relevance.py doc: AU-AHE.assimilation.research-source-grading - id: AU-AHE.assimilation.trading-curator name: concrete subclasses pillar: AU-AHE status: live code_paths: - agent_utilities/knowledge_graph/distillation/trading_curator.py - agent_utilities/models/domains/finance.py - agent_utilities/models/schema_packs/finance.py doc: concrete subclasses - id: AU-AHE.assimilation.transliteration-singularization-extend-ahe name: transliteration + singularization extend the AHE-3.69 ladder pillar: AU-AHE status: live code_paths: - agent_utilities/knowledge_graph/assimilation/dedup.py - agent_utilities/knowledge_graph/assimilation/entity_resolution.py doc: transliteration + singularization extend the AHE-3.69 ladder - id: AU-AHE.evaluation.action-outcome-feedback name: the self-healing half of fail-loud pillar: AU-AHE status: live code_paths: - agent_utilities/knowledge_graph/adaptation/feedback.py - agent_utilities/mcp/tools/write_ingest_tools.py - agent_utilities/orchestration/agent_runner.py doc: the self-healing half of fail-loud - id: AU-AHE.evaluation.adaptive-reasoning-effort name: Combines step-level and trajectory-level signals pillar: AU-AHE status: live code_paths: - agent_utilities/__init__.py - agent_utilities/core/config.py - agent_utilities/graph/horizon_curriculum.py - agent_utilities/graph/parallel_engine.py - agent_utilities/graph/reward_decomposition.py - agent_utilities/harness/__init__.py - agent_utilities/harness/eval_corpus.py - agent_utilities/harness/evaluation_engine.py - agent_utilities/harness/imodel_evolver.py - agent_utilities/harness/reasoning_effort.py - agent_utilities/harness/red_team.py - agent_utilities/harness/reliability_corpus.py - agent_utilities/harness/reliability_scorers.py - agent_utilities/models/imodel.py - agent_utilities/tools/eval_harness.py doc: Combines step-level and trajectory-level signals - id: AU-AHE.evaluation.adversarial-verification name: Adversarial verification passed — no issues found pillar: AU-AHE status: live code_paths: - agent_utilities/capabilities/adversarial_verifier.py - agent_utilities/graph/verification.py doc: Adversarial verification passed — no issues found - id: AU-AHE.evaluation.backtest-harness name: Detected mathematical/quantitative topology. Escalate to reasoning model pillar: AU-AHE status: live code_paths: - agent_utilities/core/agentspec_catalog.py - agent_utilities/graph/_router_impl.py - agent_utilities/graph/horizon_curriculum.py - agent_utilities/graph/reward_decomposition.py - agent_utilities/graph/verification.py - agent_utilities/harness/__init__.py - agent_utilities/harness/background_spawner.py - agent_utilities/harness/continuous_evaluation_engine.py - agent_utilities/knowledge_graph/memory/optimization_engine.py - agent_utilities/knowledge_graph/memory/strategies/heavy_thinking_cache.py - agent_utilities/knowledge_graph/retrieval/hybrid_retriever.py - agent_utilities/models/knowledge_graph.py - agent_utilities/models/schema_packs/finance.py - agent_utilities/patterns/manual_testing.py doc: Detected mathematical/quantitative topology. Escalate to reasoning model - id: AU-AHE.evaluation.capability-benchmark-regression-ratchet name: capability-benchmark regression ratchet re-measuring a published worktree against a persisted baseline and abandoning the branch on any tracked-capability regression pillar: AU-AHE status: live code_paths: - agent_utilities/harness/__init__.py - agent_utilities/harness/documentation_benchmark.py - agent_utilities/knowledge_graph/research/capability_ratchet.py doc: capability-benchmark regression ratchet re-measuring a published worktree against a persisted baseline and abandoning the branch on any tracked-capability regression - id: AU-AHE.evaluation.debug-swallow-justification name: DoomLoopDetector pillar: AU-AHE status: live code_paths: - agent_utilities/graph/_router_impl.py - agent_utilities/graph/verification.py - agent_utilities/knowledge_graph/adaptation/anomaly_consumer.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/research/loop_controller.py doc: DoomLoopDetector - id: AU-AHE.evaluation.disconfirming-evidence-log name: disconfirming-evidence research log, fed each round pillar: AU-AHE status: live code_paths: - agent_utilities/harness/continuous_evaluation_engine.py doc: disconfirming-evidence research log, fed each round - id: AU-AHE.evaluation.edit-claims-fix name: an edit claims a fix via a pillar: AU-AHE status: live code_paths: - agent_utilities/harness/harness_foundry_benchmark.py - agent_utilities/harness/manifest.py - agent_utilities/harness/verifier.py doc: an edit claims a fix via a - id: AU-AHE.evaluation.evaluation-monitoring name: Evaluation & Monitoring pillar: AU-AHE status: live code_paths: - agent_utilities/models/knowledge_graph.py doc: Evaluation & Monitoring - id: AU-AHE.evaluation.failure-analysis-loop name: Opik Test Suite pillar: AU-AHE status: live code_paths: - agent_utilities/harness/eval_corpus.py - agent_utilities/knowledge_graph/adaptation/failure_analyzer.py doc: Opik Test Suite - id: AU-AHE.evaluation.generationnode-records name: A GenerationNode records pillar: AU-AHE status: live code_paths: - agent_utilities/harness/eval_corpus.py - agent_utilities/models/knowledge_graph.py - agent_utilities/prompting/structured.py doc: A GenerationNode records - id: AU-AHE.evaluation.interpretability-tests name: Find historically successful model combinations pillar: AU-AHE status: live code_paths: - agent_utilities/capabilities/teams.py - agent_utilities/graph/routing/strategies/team_reuse.py - agent_utilities/graph/verification.py - agent_utilities/harness/continuous_evaluation_engine.py - agent_utilities/harness/imodel_evolver.py - agent_utilities/knowledge_graph/retrieval/memory_retriever.py - agent_utilities/models/imodel.py - agent_utilities/models/knowledge_graph.py - agent_utilities/tools/team_tools.py - agent_utilities/workflows/distillation_hook.py doc: Find historically successful model combinations - id: AU-AHE.evaluation.judge-calibration name: which judge prompt version produced pillar: AU-AHE status: live code_paths: - agent_utilities/harness/continuous_evaluation_engine.py - agent_utilities/harness/g_eval.py - agent_utilities/harness/judge_calibration.py - agent_utilities/models/knowledge_graph.py doc: which judge prompt version produced - id: AU-AHE.evaluation.longmemeval-validation-harness name: LongMemEval-S Validation Harness pillar: AU-AHE status: live code_paths: - agent_utilities/server/app.py - agent_utilities/server/routers/benchmark.py doc: LongMemEval-S Validation Harness - id: AU-AHE.evaluation.multi-strategy-evaluation name: Multi-Strategy Evaluation pillar: AU-AHE status: live code_paths: - agent_utilities/harness/continuous_evaluation_engine.py doc: Multi-Strategy Evaluation - id: AU-AHE.evaluation.parity-surpass-scoreboard name: validate a pillar: AU-AHE status: live code_paths: - agent_utilities/harness/harness_foundry_benchmark.py - agent_utilities/harness/harness_gate.py - agent_utilities/mcp/kg_server.py doc: validate a - id: AU-AHE.evaluation.plain-english-regression-assertions name: Plain-English regression assertions with verified-remediation auto-lock pillar: AU-AHE status: live code_paths: - agent_utilities/harness/continuous_evaluation_engine.py doc: Plain-English regression assertions with verified-remediation auto-lock - id: AU-AHE.evaluation.predict-before-resolve-calibration name: predict-before-resolve calibration over rounds; the pillar: AU-AHE status: live code_paths: - agent_utilities/harness/__init__.py - agent_utilities/harness/continuous_evaluation_engine.py doc: predict-before-resolve calibration over rounds; the - id: AU-AHE.evaluation.reads-avoided-feedback name: via pillar: AU-AHE status: live code_paths: - agent_utilities/knowledge_graph/adaptation/feedback.py - agent_utilities/knowledge_graph/retrieval/code_context.py - agent_utilities/mcp/tools/write_ingest_tools.py doc: via - id: AU-AHE.evaluation.reasoning-topology-benchmark name: AU-AHE.evaluation.reasoning-topology-benchmark pillar: AU-AHE status: live code_paths: - agent_utilities/graph/reasoning/benchmark.py doc: AU-AHE.evaluation.reasoning-topology-benchmark - id: AU-AHE.evaluation.return-none-on-failure name: a REAL pillar: AU-AHE status: live code_paths: - agent_utilities/workflows/localized_repair.py - agent_utilities/workflows/skill_compiler.py doc: a REAL - id: AU-AHE.harness.agentic-engineering-patterns name: Agentic Engineering Patterns pillar: AU-AHE status: live code_paths: - agent_utilities/harness/engineering.py doc: Agentic Engineering Patterns - id: AU-AHE.harness.ahe-2 name: AU-AHE.harness.ahe-2 pillar: AU-AHE status: live code_paths: - agent_utilities/harness/g_eval.py doc: AU-AHE.harness.ahe-2 - id: AU-AHE.harness.ahe-3 name: AU-AHE.harness.ahe-3 pillar: AU-AHE status: live code_paths: - agent_utilities/harness/memorydata/scoreboard.py doc: AU-AHE.harness.ahe-3 - id: AU-AHE.harness.audit-gap-detector name: KG_LOOP_AUDIT default OFF pillar: AU-AHE status: live code_paths: - agent_utilities/core/config.py - agent_utilities/harness/audit_gap_detector.py - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/mcp/tools/evolution_tools.py doc: KG_LOOP_AUDIT default OFF - id: AU-AHE.harness.callers-feed-back-per name: callers feed back a per-query reward so the pillar: AU-AHE status: live code_paths: - agent_utilities/harness/evolve_agent.py - agent_utilities/harness/memorydata/bakeoff.py - agent_utilities/harness/memorydata/router_method.py doc: callers feed back a per-query reward so the - id: AU-AHE.harness.canonical-gap-lifecycle name: the unified Gap→SDD→Implement→Promote→Close pillar: AU-AHE status: live code_paths: - agent_utilities/capabilities/governed_capability_authoring.py - agent_utilities/knowledge_graph/adaptation/failure_analyzer.py - agent_utilities/knowledge_graph/adaptation/skill_evolver.py - agent_utilities/knowledge_graph/assimilation/plan_synthesis.py - agent_utilities/knowledge_graph/research/change_publisher.py - agent_utilities/knowledge_graph/research/gaps.py - agent_utilities/knowledge_graph/research/spec_proposals.py - agent_utilities/mcp/tools/state_tools.py doc: the unified Gap→SDD→Implement→Promote→Close - id: AU-AHE.harness.capability-ratchet name: verified apply-verify-rollback from the ManifestVerifier confirm-or-revert recommendation over measured before-and-after capability scores pillar: AU-AHE status: live code_paths: - agent_utilities/knowledge_graph/research/capability_ratchet.py - agent_utilities/knowledge_graph/research/change_publisher.py doc: verified apply-verify-rollback from the ManifestVerifier confirm-or-revert recommendation over measured before-and-after capability scores - id: AU-AHE.harness.citation-quality-tracking name: Citation Quality Tracking pillar: AU-AHE status: live code_paths: - agent_utilities/harness/citation_tracker.py doc: Citation Quality Tracking - id: AU-AHE.harness.co-evolution-loop name: CONCEPT pillar: AU-AHE status: live code_paths: - agent_utilities/harness/co_evolution.py doc: CONCEPT - id: AU-AHE.harness.co-evolve-research name: co-evolves pillar: AU-AHE status: live code_paths: - agent_utilities/harness/hote_tri_evolution.py - agent_utilities/knowledge_graph/research/loop_controller.py doc: co-evolves - id: AU-AHE.harness.empirical-evidence-that-latent name: empirical evidence that the latent-native enhancements move pillar: AU-AHE status: live code_paths: - agent_utilities/harness/__init__.py - agent_utilities/harness/latent_efficiency_benchmark.py doc: empirical evidence that the latent-native enhancements move - id: AU-AHE.harness.evolution-branch-bridge name: Evolution-to-branch bridge publishing promoted proposals as regression-gated reviewable local git branches via change synthesis, RLM-sandbox validation and a governed ChangePublisher seam pillar: AU-AHE status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/research/auto_merge.py - agent_utilities/knowledge_graph/research/change_publisher.py - agent_utilities/knowledge_graph/research/change_synthesis.py - agent_utilities/orchestration/fleet_reconciler.py doc: Evolution-to-branch bridge publishing promoted proposals as regression-gated reviewable local git branches via change synthesis, RLM-sandbox validation and a governed ChangePublisher seam - id: AU-AHE.harness.evolutionary-aggregation name: population-drift / diversity-collapse signal pillar: AU-AHE status: live code_paths: - agent_utilities/__init__.py - agent_utilities/graph/hierarchical_planner.py - agent_utilities/graph/population_drift.py - agent_utilities/graph/workspace_attention.py - agent_utilities/harness/agentic_evolution_engine.py - agent_utilities/harness/self_guided_play.py - agent_utilities/harness/variant_pool.py - agent_utilities/models/imodel.py - agent_utilities/observability/config_versioning.py - agent_utilities/patterns/__init__.py - agent_utilities/patterns/exploration.py - agent_utilities/patterns/first_run_tests.py - agent_utilities/tools/self_improvement_tools.py doc: population-drift / diversity-collapse signal - id: AU-AHE.harness.evolvable-sampling-profiles name: Evolvable sampling profiles via parametric variant mutation scored by the capability-reward EMA and tournament-promoted per task-class into the live model registry pillar: AU-AHE status: live code_paths: - agent_utilities/agent/sampling_profile.py - agent_utilities/harness/variant_pool.py - agent_utilities/models/model_registry.py doc: Evolvable sampling profiles via parametric variant mutation scored by the capability-reward EMA and tournament-promoted per task-class into the live model registry - id: AU-AHE.harness.experience-node-architecture name: Experience Node Architecture pillar: AU-AHE status: live code_paths: - agent_utilities/security/execution_stability_engine.py doc: Experience Node Architecture - id: AU-AHE.harness.exploration-discovery name: Exploration & Discovery pillar: AU-AHE status: live code_paths: - agent_utilities/models/knowledge_graph.py doc: Exploration & Discovery - id: AU-AHE.harness.failure-evolution name: Failure-Driven Evolution pillar: AU-AHE status: live code_paths: - agent_utilities/core/config.py - agent_utilities/graph/parallel_engine.py - agent_utilities/harness/trace_backend.py - agent_utilities/knowledge_graph/adaptation/failure_analyzer.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/research/change_publisher.py - agent_utilities/knowledge_graph/research/loop_controller.py doc: Failure-Driven Evolution - id: AU-AHE.harness.forecasting-discipline name: operationalizes the research-craft habit of *forecasting every pillar: AU-AHE status: live code_paths: - agent_utilities/harness/forecasting.py doc: operationalizes the research-craft habit of *forecasting every - id: AU-AHE.harness.graph-native-team-evolution name: Graph-Native Team Evolution pillar: AU-AHE status: live code_paths: - agent_utilities/graph/team_evolution.py doc: Graph-Native Team Evolution - id: AU-AHE.harness.hardening-transparency-surface name: a MemoryData-contract agent method over the graph-os pillar: AU-AHE status: live code_paths: - agent_utilities/core/config.py - agent_utilities/harness/evolve_agent.py - agent_utilities/harness/memorydata/__init__.py - agent_utilities/harness/memorydata/adapter.py - agent_utilities/harness/memorydata/bakeoff.py - agent_utilities/harness/memorydata/client.py doc: a MemoryData-contract agent method over the graph-os - id: AU-AHE.harness.harness-evolution name: Agentic Harness Engineering / Evolution pillar: AU-AHE status: live code_paths: - agent_utilities/harness/agentic_evolution_engine.py - agent_utilities/harness/component_registry.py - agent_utilities/harness/constraint_engine.py - agent_utilities/harness/continuous_evaluation_engine.py - agent_utilities/harness/evidence_corpus.py - agent_utilities/harness/evolve_agent.py - agent_utilities/harness/manifest.py - agent_utilities/harness/replay_buffer.py - agent_utilities/harness/trace_backend.py - agent_utilities/harness/verifier.py - agent_utilities/knowledge_graph/kb/x_workflows.py - agent_utilities/knowledge_graph/orchestration/engine_ahe.py - agent_utilities/models/knowledge_graph.py - agent_utilities/models/schema_definition.py - agent_utilities/models/schema_packs/evolution.py - agent_utilities/rlm/config.py doc: Agentic Harness Engineering / Evolution - id: AU-AHE.harness.instead-context-stuffing-small name: instead of context-stuffing; small traces use pillar: AU-AHE status: live code_paths: - agent_utilities/harness/online_scoring.py - agent_utilities/harness/tool_judge.py doc: instead of context-stuffing; small traces use - id: AU-AHE.harness.kg-held-out-certification name: AU-AHE.harness.kg-held-out-certification pillar: AU-AHE status: live code_paths: - agent_utilities/harness/co_evolution.py - agent_utilities/harness/harness_grounding.py doc: AU-AHE.harness.kg-held-out-certification - id: AU-AHE.harness.loop-exit-conditions name: AU-ORCH.execution.delegation-reasoning-off pillar: AU-AHE status: live code_paths: - agent_utilities/capabilities/content_guardrails.py - agent_utilities/graph/state.py - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/orchestration/agent_runner.py - agent_utilities/orchestration/engine.py - agent_utilities/orchestration/loop_guards.py doc: AU-ORCH.execution.delegation-reasoning-off - id: AU-AHE.harness.manifest-verify name: '** manifest-verify →' pillar: AU-AHE status: live code_paths: - agent_utilities/harness/aegis_loop.py - agent_utilities/harness/manifest.py doc: '** manifest-verify →' - id: AU-AHE.harness.multi-loop-convergence-monitor name: Optional convergence monitor for multi-loop tasks pillar: AU-AHE status: live code_paths: - agent_utilities/core/cognitive_scheduler.py doc: Optional convergence monitor for multi-loop tasks - id: AU-AHE.harness.onlinescorenode name: → OnlineScoreNode pillar: AU-AHE status: live code_paths: - agent_utilities/harness/online_scoring.py doc: → OnlineScoreNode - id: AU-AHE.harness.overnight-loop-driver name: Unattended overnight loop-driver + morning-summary write-back pillar: AU-AHE status: live code_paths: - agent_utilities/claude_harness/__init__.py - agent_utilities/claude_harness/overnight_runner.py - agent_utilities/cli/__init__.py doc: Unattended overnight loop-driver + morning-summary write-back - id: AU-AHE.harness.per-dimension-ship-outcome name: per-dimension ship-outcome ledger pillar: AU-AHE status: live code_paths: - agent_utilities/harness/aegis_loop.py doc: per-dimension ship-outcome ledger - id: AU-AHE.harness.per-task-adaptation-speed name: per-task adaptation-speed instrumentation pillar: AU-AHE status: live code_paths: - agent_utilities/harness/__init__.py - agent_utilities/harness/adaptation_speed.py - agent_utilities/harness/hote_tri_evolution.py doc: per-task adaptation-speed instrumentation - id: AU-AHE.harness.pre-emit-quality-gate name: pre-emit quality gate on the live execution path pillar: AU-AHE status: live code_paths: - agent_utilities/core/execution/engine.py - agent_utilities/harness/__init__.py - agent_utilities/harness/provenance_gate.py - agent_utilities/harness/quality_gates.py - agent_utilities/harness/self_guided_play.py doc: pre-emit quality gate on the live execution path - id: AU-AHE.harness.preference-corpus-reliability name: Preference-Corpus Reliability pillar: AU-AHE status: live code_paths: - agent_utilities/harness/preference_pairs.py - agent_utilities/knowledge_graph/adaptation/feedback.py doc: Preference-Corpus Reliability - id: AU-AHE.harness.promotion-governance-validator name: Promotion Governance Validator pillar: AU-AHE status: live code_paths: - agent_utilities/knowledge_graph/adaptation/failure_analyzer.py - agent_utilities/knowledge_graph/research/auto_merge.py - agent_utilities/knowledge_graph/research/promotion_governance.py doc: Promotion Governance Validator - id: AU-AHE.harness.proposal-group-analysis name: Analyzes a group of proposals pillar: AU-AHE status: live code_paths: - agent_utilities/graph/workspace_attention.py doc: Analyzes a group of proposals - id: AU-AHE.harness.proven-team-reuse name: Proven Team Reuse pillar: AU-AHE status: live code_paths: - agent_utilities/core/registry/kg_adapter.py doc: Proven Team Reuse - id: AU-AHE.harness.receives-trace-id-must name: Receives the trace_id; must only pillar: AU-AHE status: live code_paths: - agent_utilities/harness/online_scoring.py - agent_utilities/harness/trace_backend.py - agent_utilities/models/knowledge_graph.py doc: Receives the trace_id; must only - id: AU-AHE.harness.research-craft-discipline name: Research-Craft Discipline pillar: AU-AHE status: live code_paths: - agent_utilities/harness/research_log.py doc: Research-Craft Discipline - id: AU-AHE.harness.run-aegis-loop-over name: AU-AHE.harness.run-aegis-loop-over pillar: AU-AHE status: live code_paths: - agent_utilities/harness/aegis_loop.py doc: AU-AHE.harness.run-aegis-loop-over - id: AU-AHE.harness.runtime-reliability-loop name: extends the canonical gap flywheel pillar: AU-AHE status: live code_paths: - agent_utilities/core/contextual_model.py - agent_utilities/knowledge_graph/core/engine_breaker.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/research/runtime_reliability.py - agent_utilities/messaging/router.py - agent_utilities/orchestration/agent_runner.py doc: extends the canonical gap flywheel - id: AU-AHE.harness.sai-controller name: the controller that operationalizes Superhuman Adaptable pillar: AU-AHE status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/research/sai_factory.py doc: the controller that operationalizes Superhuman Adaptable - id: AU-AHE.harness.sai-task name: the pillar: AU-AHE status: live code_paths: - agent_utilities/harness/__init__.py - agent_utilities/harness/sai_task.py doc: the - id: AU-AHE.harness.search-distillation-harvester name: a search-distillation harvester that converts the reasoning router pillar: AU-AHE status: live code_paths: - agent_utilities/harness/search_distillation.py - agent_utilities/knowledge_graph/core/reasoner.py doc: a search-distillation harvester that converts the reasoning router - id: AU-AHE.harness.self-improvement-overview name: AU-AHE.harness.self-improvement-overview pillar: AU-AHE status: live code_paths: - agent_utilities/models/schema_packs/finance.py doc: AU-AHE.harness.self-improvement-overview - id: AU-AHE.harness.single-file-code-synthesis name: autonomous single-file code-synthesis stage that generates a real diff for an attributed promoted proposal so the deployed evolution loop emits code instead of only a prose plan pillar: AU-AHE status: live code_paths: - agent_utilities/knowledge_graph/enrichment/distill.py - agent_utilities/knowledge_graph/research/change_publisher.py - agent_utilities/knowledge_graph/research/change_synthesis.py - agent_utilities/knowledge_graph/research/code_synthesis.py doc: autonomous single-file code-synthesis stage that generates a real diff for an attributed promoted proposal so the deployed evolution loop emits code instead of only a prose plan - id: AU-AHE.harness.structured-output-repair name: classify → bounded targeted pillar: AU-AHE status: live code_paths: - agent_utilities/capabilities/composition.py - agent_utilities/capabilities/output_repair.py doc: classify → bounded targeted - id: AU-AHE.harness.swe-failure-remediation name: SWE-failure-driven remediation pillar: AU-AHE status: live code_paths: - agent_utilities/harness/swebench_remediation.py doc: SWE-failure-driven remediation - id: AU-AHE.harness.swebench-http-surface name: SWE-bench harness HTTP surface pillar: AU-AHE status: live code_paths: - agent_utilities/harness/swebench_harness.py - agent_utilities/server/routers/swebench.py doc: SWE-bench harness HTTP surface - id: AU-AHE.harness.swebench-instance-corpus name: SWE-bench instance corpus pillar: AU-AHE status: live code_paths: - agent_utilities/harness/swebench_corpus.py doc: SWE-bench instance corpus - id: AU-AHE.harness.team-config-precheck name: Check for matching TeamConfig before LLM planning pillar: AU-AHE status: live code_paths: - agent_utilities/graph/_router_impl.py doc: Check for matching TeamConfig before LLM planning - id: AU-AHE.harness.trading-team-seed name: AU-AHE.harness.trading-team-seed pillar: AU-AHE status: live code_paths: - agent_utilities/graph/trading_team_seed.py doc: AU-AHE.harness.trading-team-seed - id: AU-AHE.harness.unified-artifact-lineage name: skill pillar: AU-AHE status: live code_paths: - agent_utilities/knowledge_graph/research/evolution_state.py - agent_utilities/models/knowledge_graph.py doc: skill - id: AU-AHE.harness.unified-promotion-gate name: the SDD/develop vector pillar: AU-AHE status: live code_paths: - agent_utilities/harness/evolve_agent.py - agent_utilities/knowledge_graph/research/auto_merge.py - agent_utilities/knowledge_graph/research/change_publisher.py - agent_utilities/knowledge_graph/research/evolution_state.py - agent_utilities/knowledge_graph/research/skill_evolution.py - agent_utilities/mcp/tools/ops_causal_tools.py - agent_utilities/models/knowledge_graph.py - agent_utilities/orchestration/action_policy.py - agent_utilities/orchestration/artifact_promotion.py doc: the SDD/develop vector - id: AU-AHE.harness.variant-pool name: ─────────────────────────────────── pillar: AU-AHE status: live code_paths: - agent_utilities/harness/aegis_loop.py - agent_utilities/harness/harness_foundry_benchmark.py doc: ─────────────────────────────────── - id: AU-AHE.harness.when-outcome-names-agent name: when the outcome names the agent that produced it pillar: AU-AHE status: live code_paths: - agent_utilities/harness/memorydata/bakeoff.py - agent_utilities/harness/memorydata/samples.py - agent_utilities/knowledge_graph/adaptation/feedback.py doc: when the outcome names the agent that produced it - id: AU-AHE.harness.when-task-is-scope name: when a task is in scope, run a short pillar: AU-AHE status: live code_paths: - agent_utilities/harness/__init__.py - agent_utilities/harness/agentic_evolution_engine.py - agent_utilities/harness/self_guided_play.py doc: when a task is in scope, run a short - id: AU-AHE.harness.width-diverse-best-k name: width of the *diverse* best-of-k fan-out — harder pillar: AU-AHE status: live code_paths: - agent_utilities/graph/test_time_diversity.py - agent_utilities/harness/reasoning_effort.py - agent_utilities/models/knowledge_graph.py doc: width of the *diverse* best-of-k fan-out — harder - id: AU-AHE.optimization.candidate-replaces-incumbent-only name: a candidate replaces the incumbent only when it pillar: AU-AHE status: live code_paths: - agent_utilities/core/config.py - agent_utilities/harness/program_optimization.py doc: a candidate replaces the incumbent only when it - id: AU-AHE.optimization.concept-matching-routing-policy name: concept-matching pillar: AU-AHE status: live code_paths: - agent_utilities/harness/policy_optimization.py doc: concept-matching - id: AU-AHE.optimization.eval-distillation name: Eval & Distillation pillar: AU-AHE status: live code_paths: - agent_utilities/knowledge_graph/memory/optimization_engine.py doc: Eval & Distillation - id: AU-AHE.optimization.few-shot-demo-set name: Few-shot demo-set refinement pillar: AU-AHE status: live code_paths: - agent_utilities/harness/program_optimization.py doc: Few-shot demo-set refinement - id: AU-AHE.optimization.optimizable-target-registry name: one entry point for every optimizable target pillar: AU-AHE status: live code_paths: - agent_utilities/harness/optimization_backend.py - agent_utilities/harness/program_optimization.py doc: one entry point for every optimizable target - id: AU-AHE.optimization.performance-anomaly-consumer name: Performance Anomaly Consumer pillar: AU-AHE status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/adaptation/anomaly_consumer.py - agent_utilities/knowledge_graph/adaptation/failure_analyzer.py - agent_utilities/knowledge_graph/core/engine_tasks.py doc: Performance Anomaly Consumer - id: AU-AHE.optimization.physical-distillation-engine name: Physical Knowledge Distillation pillar: AU-AHE status: live code_paths: - agent_utilities/knowledge_graph/distillation/skill_graph_distiller.py - agent_utilities/knowledge_graph/distillation/skill_graph_importer.py doc: Physical Knowledge Distillation - id: AU-AHE.optimization.prompt-hardening-cycle name: The offline-deterministic proxy for pillar: AU-AHE status: live code_paths: - agent_utilities/harness/program_optimization.py doc: The offline-deterministic proxy for - id: AU-AHE.optimization.real-optimization-metric name: the real optimization metric pillar: AU-AHE status: live code_paths: - agent_utilities/harness/program_optimization.py doc: the real optimization metric - id: AU-AHE.optimization.recursive-distillation-loop name: a recursive-distillation loop that fine-tunes a new prior from the search-distilled corpus, gates the candidate model behind a monotone capability ratchet, and promotes it only on a non-regressing improvement so test-time search converts into a stronger next prior pillar: AU-AHE status: live code_paths: - agent_utilities/harness/recursive_distill.py - agent_utilities/mcp/tools/analysis_tools.py doc: a recursive-distillation loop that fine-tunes a new prior from the search-distilled corpus, gates the candidate model behind a monotone capability ratchet, and promotes it only on a non-regressing improvement so test-time search converts into a stronger next prior - id: AU-AHE.optimization.run-outcome-prompt-evolution name: run outcomes feed propose-only prompt evolution pillar: AU-AHE status: live code_paths: - agent_utilities/harness/program_optimization.py - agent_utilities/harness/run_outcome_prompt_evolution.py doc: run outcomes feed propose-only prompt evolution - id: AU-AHE.optimization.skillopt-langfuse-signal name: the config/param opt-in pillar: AU-AHE status: live code_paths: - agent_utilities/harness/langfuse_skill_signal.py - agent_utilities/knowledge_graph/research/loop_controller.py doc: the config/param opt-in - id: AU-AHE.optimization.skillopt-native-reflact name: over EXISTING pillar: AU-AHE status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/knowledge_graph/research/skill_evolution.py - agent_utilities/knowledge_graph/research/skill_gate.py - agent_utilities/models/knowledge_graph.py - agent_utilities/orchestration/action_policy.py doc: over EXISTING - id: AU-AHE.optimization.telemetry-optimization name: Telemetry-Driven Optimization pillar: AU-AHE status: live code_paths: - agent_utilities/graph/_router_impl.py - agent_utilities/models/schema_definition.py doc: Telemetry-Driven Optimization - id: AU-AHE.optimization.trace-derived-training-examples name: closing the cohesive-loop gap pillar: AU-AHE status: live code_paths: - agent_utilities/harness/program_optimization.py - agent_utilities/harness/trace_examples.py doc: closing the cohesive-loop gap - id: AU-AHE.optimization.workflow-distillation name: Workflow Distillation Pipeline pillar: AU-AHE status: live code_paths: - agent_utilities/core/config.py - agent_utilities/workflows/distillation_hook.py doc: Workflow Distillation Pipeline - id: AU-AHE.org.role-experience name: Each item pillar: AU-AHE status: live code_paths: - agent_utilities/knowledge_graph/adaptation/feedback.py - agent_utilities/orchestration/org_runtime.py doc: Each item - id: AU-AHE.reward.cache-rollout-signals name: ────────────────────────── pillar: AU-AHE status: live code_paths: - agent_utilities/graph/training_signals.py doc: ────────────────────────── - id: AU-AHE.reward.decomposed-reward-framework name: Decomposed Reward Signals pillar: AU-AHE status: live code_paths: - agent_utilities/graph/__init__.py doc: Decomposed Reward Signals - id: AU-AHE.reward.horizon-task-curriculum name: Horizon-Aware Task Curriculum pillar: AU-AHE status: live code_paths: - agent_utilities/graph/__init__.py doc: Horizon-Aware Task Curriculum - id: AU-AHE.reward.langfuse-evolution-signal name: is the pillar: AU-AHE status: live code_paths: - agent_utilities/harness/eval_corpus.py - agent_utilities/harness/langfuse_signal.py - agent_utilities/harness/trace_backend.py - agent_utilities/knowledge_graph/research/claim_flywheel.py doc: is the - id: AU-AHE.reward.reward-dataset-primitives name: Reward / dataset primitives pillar: AU-AHE status: live code_paths: - agent_utilities/graph/training_signals.py doc: Reward / dataset primitives - id: AU-AHE.reward.search-task-corpus name: ────────────────── pillar: AU-AHE status: live code_paths: - agent_utilities/graph/training_signals.py - agent_utilities/knowledge_graph/search_synthesis/__init__.py doc: ────────────────── - id: AU-AHE.reward.this-is-read-back name: this is the read-back half of agent-step policy pillar: AU-AHE status: live code_paths: - agent_utilities/graph/agent_step_po.py - agent_utilities/graph/reward_decomposition.py - agent_utilities/graph/routing/strategies/policy.py - agent_utilities/orchestration/agent_runner.py doc: this is the read-back half of agent-step policy - id: AU-AHE.reward.unified-reward-signal name: AU-AHE.reward.unified-reward-signal pillar: AU-AHE status: live code_paths: - agent_utilities/harness/reward_signal.py doc: AU-AHE.reward.unified-reward-signal - id: AU-AHE.rlm.long-context-benchmark name: Long-Context RLM Benchmark Harness and Paper-Comparison Scoreboard pillar: AU-AHE status: live code_paths: - agent_utilities/rlm/benchmarks/__init__.py - agent_utilities/rlm/benchmarks/base.py - agent_utilities/rlm/benchmarks/baselines.py - agent_utilities/rlm/benchmarks/cost.py - agent_utilities/rlm/benchmarks/runner.py - agent_utilities/rlm/benchmarks/scoreboard.py - agent_utilities/rlm/benchmarks/tasks/__init__.py - agent_utilities/rlm/benchmarks/tasks/_datasets.py - agent_utilities/rlm/benchmarks/tasks/browsecomp_plus.py - agent_utilities/rlm/benchmarks/tasks/longbench_codeqa.py - agent_utilities/rlm/benchmarks/tasks/oolong.py - agent_utilities/rlm/benchmarks/tasks/oolong_pairs.py - agent_utilities/rlm/benchmarks/tasks/s_niah.py - agent_utilities/rlm/predict_rlm.py - agent_utilities/rlm/repl.py doc: Long-Context RLM Benchmark Harness and Paper-Comparison Scoreboard - id: AU-AHE.rlm.memory-aware-test-time-scaling name: Memory-Aware pillar: AU-AHE status: live code_paths: - agent_utilities/graph/hierarchical_planner.py doc: Memory-Aware - id: AU-AHE.rlm.token-usage-surface name: surface token usage pillar: AU-AHE status: live code_paths: - agent_utilities/rlm/runner.py doc: surface token usage - id: AU-AHE.sdd.loop-authored-spec name: author each draft pillar: AU-AHE status: live code_paths: - agent_utilities/knowledge_graph/enrichment/distill.py - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/sdd/__init__.py doc: author each draft - id: AU-AHE.sdd.recursive-improvement-instrumentation-aggregating name: recursive-improvement instrumentation aggregating per-cycle proposal merge and capability-delta metrics so the self-evolution loop can measure its own rate and per-mechanism contribution pillar: AU-AHE status: live code_paths: - agent_utilities/knowledge_graph/research/improvement_ledger.py - agent_utilities/knowledge_graph/research/loop_controller.py doc: recursive-improvement instrumentation aggregating per-cycle proposal merge and capability-delta metrics so the self-evolution loop can measure its own rate and per-mechanism contribution - id: AU-AHE.sdd.spec-driven-development name: Spec-Driven Development pillar: AU-AHE status: live code_paths: - agent_utilities/sdd/__init__.py doc: Spec-Driven Development - id: AU-AHE.trainer.join-inference name: join inference pillar: AU-AHE status: live code_paths: - agent_utilities/knowledge_graph/ingestion/gpu_slot_scheduler.py doc: join inference - id: AU-ECO.bus.agent-bus-awareness name: agent-to-agent messaging. Governed by the ActionPolicy pillar: AU-ECO status: live code_paths: - agent_utilities/agent/factory.py - agent_utilities/tools/agent_tools.py doc: agent-to-agent messaging. Governed by the ActionPolicy - id: AU-ECO.bus.agent-to-agent-bus name: graph_bus MCP tool and REST twin for agent-to-agent messaging pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/tools/bus_tools.py doc: graph_bus MCP tool and REST twin for agent-to-agent messaging - id: AU-ECO.bus.agentbus-federated-agent-agent name: AgentBus federated agent-to-agent communication bus over the KG pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/bus.py - agent_utilities/orchestration/action_policy.py doc: AgentBus federated agent-to-agent communication bus over the KG - id: AU-ECO.bus.auto-register-online-presence name: auto-register + online presence on any bus touch pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/tools/bus_tools.py - agent_utilities/messaging/bus.py doc: auto-register + online presence on any bus touch - id: AU-ECO.bus.bus-register-under-served name: bus register under the served auth profile pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/tools/bus_tools.py - agent_utilities/messaging/bus.py doc: bus register under the served auth profile - id: AU-ECO.bus.federation-relay name: lazy import, same as pre-refactor pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/tools/bus_tools.py - agent_utilities/messaging/bus.py - agent_utilities/messaging/federation.py doc: lazy import, same as pre-refactor - id: AU-ECO.bus.log-backend-resolution name: required engine-broker or Kafka log pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/bus_log.py doc: required engine-broker or Kafka log - id: AU-ECO.bus.native-capability name: the AgentBus is a NATIVE capability, not an opt-in persona pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/bus.py doc: the AgentBus is a NATIVE capability, not an opt-in persona - id: AU-ECO.bus.operator-view-agentbus name: a growing log or pending send pillar: AU-ECO status: live code_paths: - agent_utilities/deployment/doctor.py - agent_utilities/messaging/bus.py - agent_utilities/observability/gateway_metrics.py doc: a growing log or pending send - id: AU-ECO.bus.partitioned-log-delivery name: durable partitioned log as the AgentBus delivery/wakeup plane pillar: AU-ECO status: live code_paths: - agent_utilities/core/config.py - agent_utilities/messaging/bus.py - agent_utilities/messaging/bus_log.py doc: durable partitioned log as the AgentBus delivery/wakeup plane - id: AU-ECO.bus.pluggable-event-queue name: Pluggable Event Queue Backend pillar: AU-ECO status: live code_paths: - agent_utilities/knowledge_graph/core/event_backend.py - agent_utilities/knowledge_graph/core/kafka_queue_backend.py - agent_utilities/knowledge_graph/core/queue_backend.py doc: Pluggable Event Queue Backend - id: AU-ECO.bus.store-and-forward-log name: durable topic log materialized to tenant inboxes pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/bus.py doc: durable topic log materialized to tenant inboxes - id: AU-ECO.bus.universal-bus-tools name: universal AgentBus tools pillar: AU-ECO status: live code_paths: - agent_utilities/tools/tool_registry.py doc: universal AgentBus tools - id: AU-ECO.connector.agent-source-ingestion name: AU-ECO.connector.agent-source-ingestion pillar: AU-ECO status: live code_paths: - agent_utilities/ingestion/__init__.py - agent_utilities/ingestion/agent_sources/__init__.py - agent_utilities/ingestion/agent_sources/_jsonl.py - agent_utilities/ingestion/agent_sources/parsers/__init__.py - agent_utilities/ingestion/agent_sources/parsers/antigravity.py - agent_utilities/ingestion/agent_sources/parsers/claude.py - agent_utilities/ingestion/agent_sources/parsers/codex.py - agent_utilities/ingestion/agent_sources/parsers/generic_jsonl.py - agent_utilities/ingestion/agent_sources/registry.py - agent_utilities/ingestion/collector.py doc: AU-ECO.connector.agent-source-ingestion - id: AU-ECO.connector.apply-any-query-analysis name: apply any query-analysis source-type restriction to pillar: AU-ECO status: live code_paths: - agent_utilities/knowledge_graph/retrieval/hybrid_retriever.py - agent_utilities/knowledge_graph/retrieval/query_analysis.py doc: apply any query-analysis source-type restriction to - id: AU-ECO.connector.document-source-framework name: This is deliberately a THIRD, narrower research feed pillar: AU-ECO status: live code_paths: - agent_utilities/gateway/schemas/graph_core.py - agent_utilities/knowledge_graph/core/source_catalog.py - agent_utilities/knowledge_graph/ontology/__init__.py - agent_utilities/mcp/kg_server.py - agent_utilities/mcp/tools/ontology_tools.py - agent_utilities/protocols/source_connectors/__init__.py - agent_utilities/protocols/source_connectors/base.py - agent_utilities/protocols/source_connectors/connectors/__init__.py - agent_utilities/protocols/source_connectors/connectors/arxiv.py - agent_utilities/protocols/source_connectors/connectors/database.py - agent_utilities/protocols/source_connectors/connectors/filesystem.py - agent_utilities/protocols/source_connectors/connectors/rest.py - agent_utilities/protocols/source_connectors/connectors/web.py doc: This is deliberately a THIRD, narrower research feed - id: AU-ECO.connector.external-permission-sync name: External Permission Sync pillar: AU-ECO status: live code_paths: - agent_utilities/protocols/source_connectors/base.py - agent_utilities/protocols/source_connectors/permission_sync.py doc: External Permission Sync - id: AU-ECO.connector.factory-ingestion-adaptor name: the discovery half of the self-registering pattern. Called pillar: AU-ECO status: live code_paths: - agent_utilities/knowledge_graph/ontology/__init__.py - agent_utilities/mcp/kg_server.py - agent_utilities/protocols/source_connectors/connectors/__init__.py - agent_utilities/protocols/source_connectors/registry.py doc: the discovery half of the self-registering pattern. Called - id: AU-ECO.connector.git-markdown-revision-connector name: Git-Markdown Revision Connector pillar: AU-ECO status: live code_paths: - agent_utilities/protocols/source_connectors/connectors/git_markdown.py doc: Git-Markdown Revision Connector - id: AU-ECO.connector.git-task-resolver name: Git issue/PR -> SWE task resolver pillar: AU-ECO status: live code_paths: - agent_utilities/integrations/git_resolver.py - agent_utilities/server/app.py - agent_utilities/server/routers/enhanced.py - agent_utilities/server/routers/git_webhooks.py doc: Git issue/PR -> SWE task resolver - id: AU-ECO.connector.incremental-poll-watermark name: incremental poll keyed on a crawl-time watermark + seen ids pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/tools/ontology_tools.py - agent_utilities/protocols/source_connectors/base.py - agent_utilities/protocols/source_connectors/checkpoint.py - agent_utilities/protocols/source_connectors/connectors/database.py - agent_utilities/protocols/source_connectors/connectors/filesystem.py - agent_utilities/protocols/source_connectors/connectors/rest.py - agent_utilities/protocols/source_connectors/connectors/web.py doc: incremental poll keyed on a crawl-time watermark + seen ids - id: AU-ECO.connector.ingest-external-ard-registry name: ingest an external ARD registry pillar: AU-ECO status: live code_paths: - agent_utilities/protocols/source_connectors/connectors/ard.py doc: ingest an external ARD registry - id: AU-ECO.connector.mcp-package-adapter name: MCP Agent-Package Connector Adapter pillar: AU-ECO status: live code_paths: - agent_utilities/protocols/source_connectors/connectors/mcp_package.py doc: MCP Agent-Package Connector Adapter - id: AU-ECO.connector.mcp-tool-connector name: ───────────────── pillar: AU-ECO status: live code_paths: - agent_utilities/protocols/source_connectors/connectors/mcp_tool.py doc: ───────────────── - id: AU-ECO.connector.okf-roundtrip-sync name: the KG→OKF push arm of the pillar: AU-ECO status: live code_paths: - agent_utilities/knowledge_graph/distillation/okf_bundle.py - agent_utilities/knowledge_graph/enrichment/writeback/sinks/okf.py doc: the KG→OKF push arm of the - id: AU-ECO.connector.openwiki-preset name: independent of file mtimes pillar: AU-ECO status: live code_paths: - agent_utilities/knowledge_graph/distillation/okf_bundle.py - agent_utilities/protocols/source_connectors/connectors/filesystem.py doc: independent of file mtimes - id: AU-ECO.connector.package-manifest-catalog name: declarative catalog driving the MCP fleet adapter pillar: AU-ECO status: live code_paths: - agent_utilities/protocols/source_connectors/connectors/package_manifest.py doc: declarative catalog driving the MCP fleet adapter - id: AU-ECO.connector.posix-owner-mapping name: explicit source groups → pillar: AU-ECO status: live code_paths: - agent_utilities/protocols/source_connectors/connectors/filesystem.py doc: explicit source groups → - id: AU-ECO.connector.preset-cursor-poll name: when the tool/preset exposes a cursor pillar: AU-ECO status: live code_paths: - agent_utilities/protocols/source_connectors/connectors/mcp_package.py doc: when the tool/preset exposes a cursor - id: AU-ECO.connector.social-content-ingestion name: Social Content Ingestion pillar: AU-ECO status: live code_paths: - agent_utilities/knowledge_graph/kb/x_ingestion.py - agent_utilities/knowledge_graph/kb/x_workflows.py doc: Social Content Ingestion - id: AU-ECO.interop.a2a-agent-sync name: A2A Agent Sync pillar: AU-ECO status: live code_paths: - agent_utilities/graph/builder.py doc: A2A Agent Sync - id: AU-ECO.interop.a2a-config-loading name: A2A Config File Loading pillar: AU-ECO status: live code_paths: - agent_utilities/protocols/a2a_config.py doc: A2A Config File Loading - id: AU-ECO.interop.a2a-native-planner name: A2A-Native PlannerAgent pillar: AU-ECO status: live code_paths: - agent_utilities/protocols/a2a_graph_skill.py doc: A2A-Native PlannerAgent - id: AU-ECO.interop.ard-federation-relay name: ARD federation relay pillar: AU-ECO status: live code_paths: - agent_utilities/ecosystem/ard_federation.py doc: ARD federation relay - id: AU-ECO.interop.ecosystem-management name: Ecosystem Management pillar: AU-ECO status: live code_paths: - agent_utilities/ecosystem/__init__.py doc: Ecosystem Management - id: AU-ECO.interop.ecosystem-topology-map name: Ecosystem Topology Map pillar: AU-ECO status: live code_paths: - agent_utilities/knowledge_graph/core/ecosystem_topology.py doc: Ecosystem Topology Map - id: AU-ECO.interop.gateway-client-sdk name: Surface Gateway Client SDK pillar: AU-ECO status: live code_paths: - agent_utilities/gateway_client/__init__.py - agent_utilities/gateway_client/client.py doc: Surface Gateway Client SDK - id: AU-ECO.interop.multi-agent-bft-consensus name: Multi-agent BFT consensus for A2A pillar: AU-ECO status: live code_paths: - agent_utilities/protocols/a2a.py doc: Multi-agent BFT consensus for A2A - id: AU-ECO.interop.standardized-api-surface name: Standardized API Surface pillar: AU-ECO status: live code_paths: - agent_utilities/server/routers/__init__.py doc: Standardized API Surface - id: AU-ECO.mcp.catalog-rest-surface name: AU-ECO.mcp.catalog-rest-surface pillar: AU-ECO status: live code_paths: - agent_utilities/server/routers/mcp_catalog.py doc: AU-ECO.mcp.catalog-rest-surface - id: AU-ECO.mcp.client-side-chat-session name: client-side chat/session ingestion for Claude + Antigravity pillar: AU-ECO status: live code_paths: - agent_utilities/cli/__init__.py - agent_utilities/gateway/usage_api.py - agent_utilities/ingestion/collector.py - agent_utilities/mcp/tools/write_ingest_tools.py doc: client-side chat/session ingestion for Claude + Antigravity - id: AU-ECO.mcp.cross-process-prompt-harvest name: promotes prompts pillar: AU-ECO status: live code_paths: - agent_utilities/agent/registry_builder.py - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/knowledge_graph/ingestion/fleet_prompt_harvest.py - agent_utilities/mcp/multiplexer.py - agent_utilities/mcp/server_factory.py doc: promotes prompts - id: AU-ECO.mcp.cross-process-skill-harvest name: Cross-Process Skill Harvest pillar: AU-ECO status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/knowledge_graph/ingestion/fleet_prompt_harvest.py - agent_utilities/knowledge_graph/ingestion/fleet_skill_harvest.py - agent_utilities/knowledge_graph/ingestion/skill_workflow_ingest.py - agent_utilities/mcp/multiplexer.py doc: Cross-Process Skill Harvest - id: AU-ECO.mcp.eco-serves-two-ard name: Assembles fleet MCP servers + KG skills into ARD resources, signs pillar: AU-ECO status: live code_paths: - agent_utilities/ecosystem/ard_registry.py - agent_utilities/mcp/kg_server.py - agent_utilities/server/routers/ard.py doc: Assembles fleet MCP servers + KG skills into ARD resources, signs - id: AU-ECO.mcp.fastmcp-middleware name: Assimilated from FastMCP pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/middlewares.py doc: Assimilated from FastMCP - id: AU-ECO.mcp.full-api-mcp-surface name: Full engine API + MCP surface pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/tools/engine_tools.py - agent_utilities/mcp/tools/graph_tools.py doc: Full engine API + MCP surface - id: AU-ECO.mcp.gateway-dispatch-isolation name: run the blocking call on pillar: AU-ECO status: live code_paths: - agent_utilities/gateway/registry_api.py - agent_utilities/mcp/kg_server.py doc: run the blocking call on - id: AU-ECO.mcp.graph-reach-mcp-tool name: graph_reach MCP tool and REST twin for outbound user messaging pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/tools/reach_tools.py doc: graph_reach MCP tool and REST twin for outbound user messaging - id: AU-ECO.mcp.harness-exposure name: Harness MCP Exposure pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/harness_server.py doc: Harness MCP Exposure - id: AU-ECO.mcp.intent-surface-condensed-collapse name: operations behind the one intent contract pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/connector_surface.py - agent_utilities/mcp/graphos_surface.py - agent_utilities/mcp/intent_contract.py - agent_utilities/mcp/kg_server.py - agent_utilities/mcp/multiplexer.py - agent_utilities/mcp/readme_tools.py - agent_utilities/mcp/skill_coverage.py - agent_utilities/mcp/tools/intent_tools.py - agent_utilities/mcp/verbose_tools.py doc: operations behind the one intent contract - id: AU-ECO.mcp.intent-surface-cpd-ranking name: The packaged CPD set is pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/tools/intent_tools.py doc: The packaged CPD set is - id: AU-ECO.mcp.intent-surface-delegation-shape name: It pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/tools/intent_tools.py doc: It - id: AU-ECO.mcp.intent-surface-outcome-learning name: ONE learner, reused — the same pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/tools/intent_tools.py doc: ONE learner, reused — the same - id: AU-ECO.mcp.intent-surface-resolution-cache name: when the SAME pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/tools/intent_tools.py doc: when the SAME - id: AU-ECO.mcp.intent-surface-selection-accuracy name: hand-labelled corpus, one case per pillar: AU-ECO status: live code_paths: - agent_utilities/knowledge_graph/retrieval/intent_selection_accuracy.py doc: hand-labelled corpus, one case per - id: AU-ECO.mcp.intent-surface-tool-lifecycle name: standalone so both the meta-tool itself and the pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/multiplexer.py doc: standalone so both the meta-tool itself and the - id: AU-ECO.mcp.kg-skill-verb-coverage name: Graph-OS domain-skill coverage pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/skill_coverage.py doc: Graph-OS domain-skill coverage - id: AU-ECO.mcp.knowledge-graph-exposure name: Knowledge Graph MCP Exposure pillar: AU-ECO status: live code_paths: - agent_utilities/gateway/graph_api.py - agent_utilities/mcp/kg_server.py doc: Knowledge Graph MCP Exposure - id: AU-ECO.mcp.live-server-metadata-cache name: Live MCP server connection for tool metadata caching pillar: AU-ECO status: live code_paths: - agent_utilities/knowledge_graph/core/engine_mcp_discovery.py doc: Live MCP server connection for tool metadata caching - id: AU-ECO.mcp.oauth-log-hygiene name: AU-ECO.mcp.oauth-log-hygiene pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/oauth_log_hygiene.py doc: AU-ECO.mcp.oauth-log-hygiene - id: AU-ECO.mcp.profile-differences-from-client name: Profile differences from the engine-client breaker pillar: AU-ECO status: live code_paths: - agent_utilities/core/config.py - agent_utilities/graph/parallel_engine.py - agent_utilities/knowledge_graph/core/engine_breaker.py - agent_utilities/mcp/child_resilience.py - agent_utilities/mcp/multiplexer.py - agent_utilities/observability/gateway_metrics.py doc: Profile differences from the engine-client breaker - id: AU-ECO.mcp.protocol-compat-bridge name: closes D-OB-18 pillar: AU-ECO status: live code_paths: - agent_utilities/httpsupport/client_protocol.py - agent_utilities/httpsupport/httpx2_adapter.py - agent_utilities/httpsupport/httpx_adapter.py - agent_utilities/httpsupport/transport_factory.py - agent_utilities/mcp/httpx_boundary.py - agent_utilities/mcp/kg_server.py - agent_utilities/mcp/protocol_compat.py doc: closes D-OB-18 - id: AU-ECO.mcp.remote-oauth-broker name: Deliverable 2 of NE-008 pillar: AU-ECO status: live code_paths: - agent_utilities/gateway/remote_oauth_api.py - agent_utilities/mcp/remote_oauth_broker.py doc: Deliverable 2 of NE-008 - id: AU-ECO.mcp.skills-over-mcp-provider name: absent/empty for pillar: AU-ECO status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/mcp/multiplexer.py - agent_utilities/mcp/server_factory.py doc: absent/empty for - id: AU-ECO.mcp.stable-dispatch-bounded-retry name: AU-ECO.mcp.stable-dispatch-bounded-retry pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/multiplexer.py doc: AU-ECO.mcp.stable-dispatch-bounded-retry - id: AU-ECO.mcp.standardized-interfaces name: MCP Standardized Interfaces pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/__init__.py - agent_utilities/mcp/action_dispatch.py - agent_utilities/mcp/concurrency.py - agent_utilities/mcp/context_helpers.py - agent_utilities/mcp/delegated_auth.py - agent_utilities/mcp/multiplexer.py - agent_utilities/mcp/server_factory.py doc: MCP Standardized Interfaces - id: AU-ECO.mcp.stdio-static-purity-gate name: AU-ECO.mcp.stdio-static-purity-gate pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/server_factory.py doc: AU-ECO.mcp.stdio-static-purity-gate - id: AU-ECO.mcp.tasks-workitem-bridge name: mount the native WorkItem-backed pillar: AU-ECO status: live code_paths: - agent_utilities/knowledge_graph/core/work_durability.py - agent_utilities/mcp/server_factory.py - agent_utilities/mcp/tasks_extension.py - agent_utilities/mcp/tools/mcp_apps.py doc: mount the native WorkItem-backed - id: AU-ECO.mcp.tool-mode-standardization name: one entry per CRUD pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/_graphos_action_manifest.py doc: one entry per CRUD - id: AU-ECO.mcp.two-surfaces-mcp-rest name: the generic pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/tools/intent_tools.py doc: the generic - id: AU-ECO.mcp.unified-mcp-skill-a2a-ingest name: Unified MCP/Skill/A2A ingestion pipeline with live pillar: AU-ECO status: live code_paths: - agent_utilities/knowledge_graph/core/engine_ingestion.py doc: Unified MCP/Skill/A2A ingestion pipeline with live - id: AU-ECO.mcp.usage-cost-observability-surface name: usage/cost/ pillar: AU-ECO status: live code_paths: - agent_utilities/gateway/usage_api.py - agent_utilities/gateway_client/client.py - agent_utilities/mcp/tools/write_ingest_tools.py - agent_utilities/server/app.py doc: usage/cost/ - id: AU-ECO.mcp.verbose-auto-wire name: dynamic pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/verbose_tools.py doc: dynamic - id: AU-ECO.mcp.webui-governed-mcp-delegation name: AU-ECO.mcp.webui-governed-mcp-delegation pillar: AU-ECO status: live code_paths: - agent_utilities/server/app.py - agent_utilities/server/webui_mcp_delegation.py doc: AU-ECO.mcp.webui-governed-mcp-delegation - id: AU-ECO.mcp.webui-voice-transcription-delegation name: AU-ECO.mcp.webui-voice-transcription-delegation pillar: AU-ECO status: live code_paths: - agent_utilities/server/app.py - agent_utilities/server/webui_voice_delegation.py doc: AU-ECO.mcp.webui-voice-transcription-delegation - id: AU-ECO.messaging.alert-intake name: messaging alert-intake enabled on port pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/alert_intake.py - agent_utilities/messaging/daemon.py doc: messaging alert-intake enabled on port - id: AU-ECO.messaging.blocking-store-memory name: store_memory is a BLOCKING call pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/kg_ingest.py doc: store_memory is a BLOCKING call - id: AU-ECO.messaging.burst-mode-coalescing name: collapse a rapid run of messages into ONE reply pillar: AU-ECO status: live code_paths: - agent_utilities/core/config.py - agent_utilities/messaging/coalescer.py - agent_utilities/messaging/router.py doc: collapse a rapid run of messages into ONE reply - id: AU-ECO.messaging.conversational-history-backfill name: BUG-041 pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/backfill.py - agent_utilities/messaging/inbox.py doc: BUG-041 - id: AU-ECO.messaging.conversational-retention-guard name: BUG-041 investigation pillar: AU-ECO status: live code_paths: - agent_utilities/knowledge_graph/core/maintainer.py doc: BUG-041 investigation - id: AU-ECO.messaging.debounce-relevance-sweep name: do NOT fire the heavy relevance sweep immediately on every pillar: AU-ECO status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py doc: do NOT fire the heavy relevance sweep immediately on every - id: AU-ECO.messaging.debounce-timer-cancel name: after each turn that pass already *writes* the new memento under the pillar: AU-ECO status: live code_paths: - agent_utilities/knowledge_graph/memory/session_memento_cache.py - agent_utilities/messaging/coalescer.py - agent_utilities/messaging/router.py doc: after each turn that pass already *writes* the new memento under the - id: AU-ECO.messaging.durable-inbound-pending name: record the inbound turn DURABLY as pending BEFORE we attempt the pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/inbox.py - agent_utilities/messaging/router.py doc: record the inbound turn DURABLY as pending BEFORE we attempt the - id: AU-ECO.messaging.eco-2 name: AU-ECO.messaging.eco-2 pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/commands.py doc: AU-ECO.messaging.eco-2 - id: AU-ECO.messaging.elicitation-loop-bridge name: elicitation and loop bridge so a blocked loop reaches the user and resumes on reply pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/router.py - agent_utilities/messaging/service.py doc: elicitation and loop bridge so a blocked loop reaches the user and resumes on reply - id: AU-ECO.messaging.episodic-memory-recall name: this is episodic memory the universal recall reads on demand; pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/kg_ingest.py doc: this is episodic memory the universal recall reads on demand; - id: AU-ECO.messaging.fire-and-forget-tasks name: fire-and-forget background tasks pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/router.py doc: fire-and-forget background tasks - id: AU-ECO.messaging.image-attachment-fallback name: image attachments are carried on the fallback pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/router.py doc: image attachments are carried on the fallback - id: AU-ECO.messaging.inbound-messaging-router-runs name: the inbound messaging router runs in its OWN process pillar: AU-ECO status: live code_paths: - agent_utilities/gateway/daemon.py - agent_utilities/messaging/daemon.py doc: the inbound messaging router runs in its OWN process - id: AU-ECO.messaging.inbound-router name: AU-ECO.messaging.inbound-router pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/router.py doc: AU-ECO.messaging.inbound-router - id: AU-ECO.messaging.last-active-channel name: also reach the user on their last-active channel pillar: AU-ECO status: live code_paths: - agent_utilities/observability/approval_manager.py doc: also reach the user on their last-active channel - id: AU-ECO.messaging.last-active-channel-routing name: Last-active channel routing state for the messaging reach service pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/router.py - agent_utilities/messaging/service.py doc: Last-active channel routing state for the messaging reach service - id: AU-ECO.messaging.make-fleet-credentials-present name: every process pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/daemon.py doc: every process - id: AU-ECO.messaging.mattermost-backend name: Mattermost as a first-class bidirectional messaging platform pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/backends/mattermost.py doc: Mattermost as a first-class bidirectional messaging platform - id: AU-ECO.messaging.messaging-as-renderer name: messaging is a RENDERER of the orchestrator pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/router.py - agent_utilities/messaging/service.py - agent_utilities/orchestration/reactions.py doc: messaging is a RENDERER of the orchestrator - id: AU-ECO.messaging.messaging-ontology-shape-so name: Messaging ontology shape so reach channels are reasoned over pillar: AU-ECO status: live code_paths: - agent_utilities/knowledge_graph/ontology/interfaces.py doc: Messaging ontology shape so reach channels are reasoned over - id: AU-ECO.messaging.messaging-reach-service-governed name: Messaging reach service for governed outbound and channel routing pillar: AU-ECO status: live code_paths: - agent_utilities/core/config.py - agent_utilities/messaging/backends/mattermost.py - agent_utilities/messaging/daemon.py - agent_utilities/messaging/service.py - agent_utilities/orchestration/action_policy.py - agent_utilities/server/webui_contact_delivery.py doc: Messaging reach service for governed outbound and channel routing - id: AU-ECO.messaging.messaging-renderer-core-reaction name: the messaging renderer of a core reaction pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/backends/mattermost.py - agent_utilities/messaging/backends/slack.py - agent_utilities/messaging/backends/telegram.py - agent_utilities/messaging/router.py - agent_utilities/orchestration/reactions.py doc: the messaging renderer of a core reaction - id: AU-ECO.messaging.model-routed-inbound-responder name: registry-routed inbound responder pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/router.py doc: registry-routed inbound responder - id: AU-ECO.messaging.native-backend-abstraction name: Universal-capability — the orchestrator emits ONE Markdown answer; each pillar: AU-ECO status: live code_paths: - agent_utilities/__init__.py - agent_utilities/capabilities/manager.py - agent_utilities/core/config.py - agent_utilities/core/paths.py - agent_utilities/core/registry/package_adapter.py - agent_utilities/core/registry/plugin_adapter.py - agent_utilities/domains/finance/quant_mcp_tools.py - agent_utilities/ecosystem/hook_installer.py - agent_utilities/graph/tool_resolver.py - agent_utilities/knowledge_graph/adaptation/skill_evolver.py - agent_utilities/knowledge_graph/memory/cli.py - agent_utilities/mcp/tools/ontology_tools.py - agent_utilities/mcp/toolset_factory.py - agent_utilities/messaging/__init__.py - agent_utilities/messaging/backends/__init__.py - agent_utilities/messaging/backends/discord.py - agent_utilities/messaging/backends/googlechat.py - agent_utilities/messaging/backends/googlemeet.py - agent_utilities/messaging/backends/imessage.py - agent_utilities/messaging/backends/irc.py - agent_utilities/messaging/backends/line.py - agent_utilities/messaging/backends/matrix.py - agent_utilities/messaging/backends/mattermost.py - agent_utilities/messaging/backends/nextcloud.py - agent_utilities/messaging/backends/signal.py - agent_utilities/messaging/backends/slack.py - agent_utilities/messaging/backends/synology.py - agent_utilities/messaging/backends/teams.py - agent_utilities/messaging/backends/telegram.py - agent_utilities/messaging/backends/twitch.py - agent_utilities/messaging/backends/voicecall.py - agent_utilities/messaging/backends/whatsapp.py - agent_utilities/messaging/base.py - agent_utilities/messaging/capabilities.py - agent_utilities/messaging/kg_ingest.py - agent_utilities/messaging/models.py - agent_utilities/messaging/registry.py - agent_utilities/messaging/render.py - agent_utilities/messaging/router.py - agent_utilities/models/knowledge_graph.py - agent_utilities/models/schema_packs/finance.py - agent_utilities/orchestration/durable_execution.py - agent_utilities/protocols/a2a_epistemic.py - agent_utilities/protocols/acp_adapter.py - agent_utilities/security/permissions_kernel.py - agent_utilities/server/app.py - agent_utilities/server/routers/agent_ui.py - agent_utilities/server/routers/core.py - agent_utilities/tools/agent_tools.py - agent_utilities/tools/browser/browser_control.py - agent_utilities/tools/browser/browser_manager.py - agent_utilities/tools/developer_tools.py - agent_utilities/tools/dynamic_tool_orchestrator.py - agent_utilities/tools/jupyter_adapter.py - agent_utilities/tools/onboarding_tools.py - agent_utilities/tools/sandbox_executor.py - agent_utilities/tools/tool_filtering.py - agent_utilities/tools/tool_registry.py doc: Universal-capability — the orchestrator emits ONE Markdown answer; each - id: AU-ECO.messaging.post-conversation-enrichment name: Post-conversation concept extraction + KG linking for chat pillar: AU-ECO status: live code_paths: - agent_utilities/core/config.py - agent_utilities/messaging/enrichment.py - agent_utilities/messaging/router.py doc: Post-conversation concept extraction + KG linking for chat - id: AU-ECO.messaging.sending-reply-failed name: Sending reply failed pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/router.py doc: Sending reply failed - id: AU-ECO.messaging.shared-by-every-messaging name: shared by every messaging platform AND pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/commands.py doc: shared by every messaging platform AND - id: AU-ECO.messaging.single-inbound-command-dispatcher name: the single inbound command dispatcher used by every platform pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/backends/telegram.py - agent_utilities/messaging/base.py - agent_utilities/messaging/commands.py - agent_utilities/messaging/daemon.py - agent_utilities/messaging/router.py doc: the single inbound command dispatcher used by every platform - id: AU-ECO.messaging.surfaced name: Surfaced pillar: AU-ECO status: live code_paths: - agent_utilities/core/config.py - agent_utilities/messaging/enrichment.py doc: Surfaced - id: AU-ECO.messaging.telegram-voice-note name: transcribe voice notes to text via Whisper pillar: AU-ECO status: live code_paths: - agent_utilities/core/config.py - agent_utilities/messaging/backends/telegram.py doc: transcribe voice notes to text via Whisper - id: AU-ECO.messaging.telegram-webhook-receiver-started name: webhook mode uses python-telegram-bot pillar: AU-ECO status: live code_paths: - agent_utilities/core/config.py - agent_utilities/messaging/backends/telegram.py doc: webhook mode uses python-telegram-bot - id: AU-ECO.messaging.universal-agent-reach-user name: Universal agent reach_user tool over the messaging reach service pillar: AU-ECO status: live code_paths: - agent_utilities/tools/agent_tools.py - agent_utilities/tools/tool_registry.py doc: Universal agent reach_user tool over the messaging reach service - id: AU-ECO.messaging.universal-graph-agent name: the universal graph agent a chat turn routes to. Defaults to the pillar: AU-ECO status: live code_paths: - agent_utilities/core/config.py - agent_utilities/messaging/router.py - agent_utilities/orchestration/agent_runner.py - agent_utilities/orchestration/manager.py - agent_utilities/orchestration/session_continuity.py doc: the universal graph agent a chat turn routes to. Defaults to the - id: AU-ECO.messaging.voice-attachment-fallback name: the server populates pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/backends/discord.py - agent_utilities/messaging/backends/mattermost.py - agent_utilities/messaging/backends/slack.py - agent_utilities/messaging/models.py - agent_utilities/messaging/router.py doc: the server populates - id: AU-ECO.messaging.whisper-transcription name: Voice input → transcript via Whisper pillar: AU-ECO status: live code_paths: - agent_utilities/messaging/voice.py doc: Voice input → transcript via Whisper - id: AU-ECO.multiplexer.catalog-probe-ttl-staleness name: fleet catalog-probe cache TTL pillar: AU-ECO status: live code_paths: - agent_utilities/core/config.py - agent_utilities/mcp/multiplexer.py doc: fleet catalog-probe cache TTL - id: AU-ECO.multiplexer.condensed-server-load name: only the condensed pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/multiplexer.py doc: only the condensed - id: AU-ECO.multiplexer.running-vs-dispatchable-metrics name: child health is pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/multiplexer.py - agent_utilities/observability/gateway_metrics.py doc: child health is - id: AU-ECO.multiplexer.tool-gateway-catalog name: catalog-aware, collision-free prefix assignment pillar: AU-ECO status: live code_paths: - agent_utilities/capabilities/fleet_tool_search.py - agent_utilities/core/config.py - agent_utilities/mcp/catalog_reconciliation.py - agent_utilities/mcp/multiplexer.py - agent_utilities/mcp/shared_multiplexer.py - agent_utilities/mcp/tools/config_tools.py doc: catalog-aware, collision-free prefix assignment - id: AU-ECO.reactions.emitted-alongside-reply name: first-class reaction output any agent turn can emit, shared by every pillar: AU-ECO status: live code_paths: - agent_utilities/orchestration/reactions.py doc: first-class reaction output any agent turn can emit, shared by every - id: AU-ECO.reactions.one-emote-registry-governance name: one emote registry and governance gate shared pillar: AU-ECO status: live code_paths: - agent_utilities/orchestration/action_policy.py - agent_utilities/orchestration/reactions.py doc: one emote registry and governance gate shared - id: AU-ECO.toolkit.adaptive-tool-provisioning name: Adaptive Tool Provisioning pillar: AU-ECO status: live code_paths: - agent_utilities/graph/adaptive_provisioning.py doc: Adaptive Tool Provisioning - id: AU-ECO.toolkit.browser-agent-tier name: Optional browser-agent tier for the developer-workspace runtime pillar: AU-ECO status: live code_paths: - agent_utilities/runtime/browser_tier.py - agent_utilities/runtime/events.py doc: Optional browser-agent tier for the developer-workspace runtime - id: AU-ECO.toolkit.capability-tool-binding name: bind tools from declared capability intents pillar: AU-ECO status: live code_paths: - agent_utilities/agent/factory.py doc: bind tools from declared capability intents - id: AU-ECO.toolkit.codebase-map-generator name: Codebase Map Generator pillar: AU-ECO status: live code_paths: - agent_utilities/tools/codebase_map_tools.py doc: Codebase Map Generator - id: AU-ECO.toolkit.database-traversal-tools name: native database traversal tools pillar: AU-ECO status: live code_paths: - agent_utilities/tools/db_tools.py - agent_utilities/tools/tool_registry.py doc: native database traversal tools - id: AU-ECO.toolkit.media-gateway-failure-path name: transcribed text can then flow into the KG through the pillar: AU-ECO status: live code_paths: - agent_utilities/ecosystem/media/__init__.py - agent_utilities/ecosystem/media/gateway.py - agent_utilities/ecosystem/media/transcription.py - agent_utilities/tools/tool_registry.py doc: transcribed text can then flow into the KG through the - id: AU-ECO.toolkit.media-transcription-bridge name: Media Transcription Bridge pillar: AU-ECO status: live code_paths: - agent_utilities/ecosystem/media/transcription.py doc: Media Transcription Bridge - id: AU-ECO.toolkit.model-pricing-catalog name: Unified model pricing catalog pillar: AU-ECO status: live code_paths: - agent_utilities/pricing/catalog.py - agent_utilities/pricing/litellm.py - agent_utilities/pricing/model.py - agent_utilities/pricing/normalize.py - agent_utilities/pricing/store.py doc: Unified model pricing catalog - id: AU-ECO.toolkit.provider-prompt-adaptation name: Provider Prompt Adaptation pillar: AU-ECO status: live code_paths: - agent_utilities/prompting/provider_adapter.py doc: Provider Prompt Adaptation - id: AU-ECO.toolkit.self-describing-registry name: Self-Describing Function Registry pillar: AU-ECO status: live code_paths: - agent_utilities/core/registry/kg_adapter.py - agent_utilities/knowledge_graph/core/tenant_sharing.py - agent_utilities/knowledge_graph/orchestration/engine_query.py doc: Self-Describing Function Registry - id: AU-ECO.toolkit.self-documenting-plugin-bundle name: Plugin Bundle Distribution System pillar: AU-ECO status: live code_paths: - agent_utilities/ecosystem/plugin_bundle.py doc: Plugin Bundle Distribution System - id: AU-ECO.toolkit.shared-kg-layer name: KG as a first-class shared knowledge/reasoning layer for all agents pillar: AU-ECO status: live code_paths: - agent_utilities/tools/kg_tools.py - agent_utilities/tools/tool_registry.py doc: KG as a first-class shared knowledge/reasoning layer for all agents - id: AU-ECO.toolkit.token-cost-source name: single source of token cost for the whole stack pillar: AU-ECO status: live code_paths: - agent_utilities/pricing/__init__.py doc: single source of token cost for the whole stack - id: AU-ECO.toolkit.tool-ref-integrity-gate name: Capability-bound tool/skill resolution pillar: AU-ECO status: live code_paths: - agent_utilities/agent/capability_resolver.py doc: Capability-bound tool/skill resolution - id: AU-ECO.toolkit.unified-delegation-surface name: ONE delegation surface. This is a thin wrapper over the SAME pillar: AU-ECO status: live code_paths: - agent_utilities/tools/agent_tools.py doc: ONE delegation surface. This is a thin wrapper over the SAME - id: AU-ECO.toolkit.workflow-gap-fill name: gap-fill the workflow pillar: AU-ECO status: live code_paths: - agent_utilities/graph/parallel_engine.py doc: gap-fill the workflow - id: AU-ECO.ui.company-infrastructure-orchestration name: Company Infrastructure Orchestration pillar: AU-ECO status: live code_paths: - agent_utilities/models/company.py - agent_utilities/models/knowledge_graph.py doc: Company Infrastructure Orchestration - id: AU-ECO.ui.fleet-http-client-library name: Fleet HTTP Client Library pillar: AU-ECO status: live code_paths: - agent_utilities/httpsupport/__init__.py - agent_utilities/httpsupport/auth.py - agent_utilities/httpsupport/client.py - agent_utilities/httpsupport/pagination.py - agent_utilities/httpsupport/rate_limit.py - agent_utilities/httpsupport/redaction.py doc: Fleet HTTP Client Library - id: AU-ECO.ui.frontend-contribution name: AU-ECO.ui.frontend-contribution pillar: AU-ECO status: live code_paths: - agent_utilities/core/frontend_providers.py doc: AU-ECO.ui.frontend-contribution - id: AU-ECO.ui.mcp-apps-host name: AU-ECO.ui.mcp-apps-host pillar: AU-ECO status: live code_paths: - agent_utilities/mcp/tools/mcp_apps.py doc: AU-ECO.ui.mcp-apps-host - id: AU-KG.audit.durable-error-detail name: AU-KG.audit.durable-error-detail pillar: AU-KG status: live code_paths: - agent_utilities/gateway/daemon.py - agent_utilities/observability/error_detail_sink.py - agent_utilities/security/error_surface.py doc: AU-KG.audit.durable-error-detail - id: AU-KG.audit.error-detail-resolution name: AU-KG.audit.error-detail-resolution pillar: AU-KG status: live code_paths: - agent_utilities/mcp/tools/analyze_suite.py - agent_utilities/security/error_surface.py doc: AU-KG.audit.error-detail-resolution - id: AU-KG.audit.graph-ownership-disposition name: deterministic ownership disposition pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/maintenance/graph_ownership.py - agent_utilities/knowledge_graph/maintenance/graph_ownership_apply.py - agent_utilities/mcp/tools/governance_tools.py doc: deterministic ownership disposition - id: AU-KG.audit.hash-chain-verify name: routes to the engine pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/graph_compute.py - agent_utilities/mcp/tools/audit_tools.py doc: routes to the engine - id: AU-KG.audit.hydration-absent-vs-hidden name: AU-KG.audit.hydration-absent-vs-hidden pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/hydration_manifest.py - agent_utilities/mcp/kg_server.py doc: AU-KG.audit.hydration-absent-vs-hidden - id: AU-KG.audit.hydration-manifest-signed name: builds ON pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/hydration_manifest.py - agent_utilities/mcp/kg_server.py doc: builds ON - id: AU-KG.audit.kg-native-audit-sink name: PA-R1.7 pillar: AU-KG status: live code_paths: - agent_utilities/capabilities/composition.py - agent_utilities/capabilities/kg_audit_sink.py doc: PA-R1.7 - id: AU-KG.audit.repository-job-provenance-bridge name: RMDD-19 repository job provenance pillar: AU-KG status: live code_paths: - agent_utilities/observability/gateway_metrics.py - agent_utilities/observability/repository_metrics.py - agent_utilities/observability/repository_provenance.py doc: RMDD-19 repository job provenance - id: AU-KG.audit.tool-call-acted-on-reverse-index name: AU-KG.audit.tool-call-acted-on-reverse-index pillar: AU-KG status: live code_paths: - agent_utilities/orchestration/agent_runner.py - agent_utilities/orchestration/manager.py doc: AU-KG.audit.tool-call-acted-on-reverse-index - id: AU-KG.audit.trace-id-assigned-at-emission name: AU-KG.audit.trace-id-assigned-at-emission pillar: AU-KG status: live code_paths: - agent_utilities/harness/trace_backend.py - agent_utilities/observability/trace_ontology.py doc: AU-KG.audit.trace-id-assigned-at-emission - id: AU-KG.audit.trace-retention-legal-hold name: pruned RunTrace/ToolCall/ pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/maintainer.py - agent_utilities/observability/trace_ontology.py doc: pruned RunTrace/ToolCall/ - id: AU-KG.backend.age-postgresql-tier name: the durable PostgreSQL graph tier executed via a bounded regex pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/backends/age_backend.py doc: the durable PostgreSQL graph tier executed via a bounded regex - id: AU-KG.backend.authority-backend name: the authority is the single shared pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/backends/__init__.py doc: the authority is the single shared - id: AU-KG.backend.authority-has-already-acked name: The authority has already acked; this must not wait on the pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/backends/fanout_backend.py doc: The authority has already acked; this must not wait on the - id: AU-KG.backend.authority-write-tail name: vector search competes for the same pool under load; pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/backends/age_backend.py - agent_utilities/knowledge_graph/backends/postgresql_backend.py doc: vector search competes for the same pool under load; - id: AU-KG.backend.backend-modes name: redb-authoritative persistence is the DEFAULT backend mode (THE FLIP to durable-by-default) pillar: AU-KG status: live code_paths: - epistemic-graph/crates/eg-ann/src/redb_store.rs - epistemic-graph/crates/eg-core/src/cold_tier.rs - epistemic-graph/tests/test_graceful_shutdown.py doc: redb-authoritative persistence is the DEFAULT backend mode (THE FLIP to durable-by-default) - id: AU-KG.backend.cache-lives-as name: the cache lives as pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/backends/base.py - agent_utilities/knowledge_graph/enrichment/cards.py doc: the cache lives as - id: AU-KG.backend.cache-lives-as-248 name: route around these to the engine pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/backends/base.py doc: route around these to the engine - id: AU-KG.backend.company-brain-write-guard name: Company Brain Infrastructure pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/backends/__init__.py - agent_utilities/knowledge_graph/backends/brain_guarded_backend.py - agent_utilities/knowledge_graph/backends/contrib/ladybug_backend.py - agent_utilities/knowledge_graph/core/company_brain.py - agent_utilities/knowledge_graph/core/cypher_scoping.py - agent_utilities/knowledge_graph/core/engine.py - agent_utilities/knowledge_graph/core/graph_compute.py - agent_utilities/knowledge_graph/core/materialization.py - agent_utilities/knowledge_graph/core/secured_reads.py - agent_utilities/knowledge_graph/core/tenant_sharing.py - agent_utilities/knowledge_graph/enrichment/pipeline.py - agent_utilities/server/routers/enhanced.py doc: Company Brain Infrastructure - id: AU-KG.backend.concept-2 name: ── pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/backends/postgresql_backend.py doc: ── - id: AU-KG.backend.connection-registry name: Role-aware multi-database registry plus live config mutation pillar: AU-KG status: live code_paths: - agent_utilities/deployment/config_generator.py - agent_utilities/knowledge_graph/core/connection_registry.py - agent_utilities/knowledge_graph/core/source_catalog.py - agent_utilities/mcp/tools/analysis_tools.py doc: Role-aware multi-database registry plus live config mutation - id: AU-KG.backend.continuous-stardog-mirror name: OFF by pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py doc: OFF by - id: AU-KG.backend.declared-columns-so-schema name: Declared columns so schema-backed Kuzu can pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/backends/contrib/ladybug_backend.py - agent_utilities/knowledge_graph/core/gitlab_indexer.py - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/mcp/tools/query_tools.py - agent_utilities/models/schema_definition.py - agent_utilities/protocols/source_connectors/connectors/mcp_tool.py doc: Declared columns so schema-backed Kuzu can - id: AU-KG.backend.derive-mirror-set name: derive the mirror set from connections with role= pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/backends/__init__.py doc: derive the mirror set from connections with role= - id: AU-KG.backend.explicit-graph-selection name: explicit physical engine graph, independent of pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/mcp/kg_server.py - agent_utilities/mcp/tools/ontology_tools.py - agent_utilities/mcp/tools/query_tools.py - agent_utilities/mcp/tools/write_ingest_tools.py - agent_utilities/security/error_surface.py doc: explicit physical engine graph, independent of - id: AU-KG.backend.fanout-dedup name: de-duplicate fan-out targets by the engine pillar: AU-KG status: live code_paths: - agent_utilities/mcp/kg_server.py doc: de-duplicate fan-out targets by the engine - id: AU-KG.backend.keyed-ingest-partitions name: Keyed ingest partitions for per-tenant and per-repo ordering pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/core/kafka_queue_backend.py - agent_utilities/knowledge_graph/ingest_worker.py - agent_utilities/messaging/bus_log.py doc: Keyed ingest partitions for per-tenant and per-repo ordering - id: AU-KG.backend.kvcache-vllm-connector name: the Python LMCache/vLLM connector reads its endpoint and pillar: AU-KG status: live code_paths: - agent_utilities/core/contextual_model.py - agent_utilities/knowledge_graph/retrieval/context_compiler.py - agent_utilities/kvcache/__init__.py - agent_utilities/kvcache/config.py - agent_utilities/kvcache/l2_native_connector.py - agent_utilities/kvcache/policy.py doc: the Python LMCache/vLLM connector reads its endpoint and - id: AU-KG.backend.lmcache-native-connector name: the LMCache-side *native connector* half of the EG-187 pillar: AU-KG status: live code_paths: - agent_utilities/kvcache/l2_native_connector.py doc: the LMCache-side *native connector* half of the EG-187 - id: AU-KG.backend.mirror-health-repair name: Concurrent N-way mirrored graph backend pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/backends/__init__.py - agent_utilities/knowledge_graph/backends/base.py - agent_utilities/knowledge_graph/backends/contrib/falkordb_backend.py - agent_utilities/knowledge_graph/backends/contrib/ladybug_backend.py - agent_utilities/knowledge_graph/backends/fanout_backend.py - agent_utilities/knowledge_graph/backends/mirror_target.py - agent_utilities/knowledge_graph/core/engine.py - agent_utilities/knowledge_graph/extraction/ontology_grounding.py - agent_utilities/knowledge_graph/extraction/readers_media.py - agent_utilities/knowledge_graph/extraction/structure_router.py - agent_utilities/knowledge_graph/migration.py - agent_utilities/observability/runtime_health.py doc: Concurrent N-way mirrored graph backend - id: AU-KG.backend.mirror-nonempty-default-guard name: Non-Empty Default Guard pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/backends/__init__.py - agent_utilities/knowledge_graph/backends/mirror_target.py doc: Non-Empty Default Guard - id: AU-KG.backend.mirror-outbox name: This one outbox file is opened by pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/backends/outbox.py doc: This one outbox file is opened by - id: AU-KG.backend.mirror-target-graph name: One uniform mirror *target* concept resolved once in the fan-out layer and mapped by each external backend onto its native isolation unit pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/backends/__init__.py - agent_utilities/knowledge_graph/backends/age_backend.py - agent_utilities/knowledge_graph/backends/contrib/falkordb_backend.py - agent_utilities/knowledge_graph/backends/contrib/neo4j_backend.py - agent_utilities/knowledge_graph/backends/mirror_target.py - agent_utilities/knowledge_graph/backends/postgresql_backend.py - agent_utilities/knowledge_graph/core/connection_registry.py doc: One uniform mirror *target* concept resolved once in the fan-out layer and mapped by each external backend onto its native isolation unit - id: AU-KG.backend.multi-connection-registry name: Multi-Connection Graph Registry. The engine has always been pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/backends/age_backend.py - agent_utilities/knowledge_graph/backends/base.py - agent_utilities/knowledge_graph/backends/fanout_backend.py - agent_utilities/knowledge_graph/backends/postgresql_backend.py - agent_utilities/knowledge_graph/core/connection_registry.py - agent_utilities/mcp/kg_server.py - agent_utilities/mcp/tools/ontology_tools.py - agent_utilities/mcp/tools/query_tools.py - agent_utilities/mcp/tools/write_ingest_tools.py doc: Multi-Connection Graph Registry. The engine has always been - id: AU-KG.backend.remote-kvcache-contract name: the Python half of the EG-187 remote KV-cache contract pillar: AU-KG status: live code_paths: - agent_utilities/kvcache/remote_backend.py doc: the Python half of the EG-187 remote KV-cache contract - id: AU-KG.backend.schedule-on-control-graph name: Schedule lives on the control graph; read it from there pillar: AU-KG status: live code_paths: - agent_utilities/core/schedule_engine.py - agent_utilities/knowledge_graph/core/engine.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/orchestration/engine_query.py - agent_utilities/orchestration/fleet_autoscaler.py - agent_utilities/security/secrets_client.py doc: Schedule lives on the control graph; read it from there - id: AU-KG.backend.selectable-queue-backend name: Fail-loud selectable ingest task-queue backend with explicit kafka and postgres and auto sqlite modes pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/__main__.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/core/kafka_queue_backend.py - agent_utilities/knowledge_graph/core/queue_backend.py - agent_utilities/knowledge_graph/ingest_worker.py - agent_utilities/orchestration/agent_dispatch.py doc: Fail-loud selectable ingest task-queue backend with explicit kafka and postgres and auto sqlite modes - id: AU-KG.backend.tolerant-parse name: tolerant of every shape this value arrives in pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/backends/__init__.py doc: tolerant of every shape this value arrives in - id: AU-KG.compute.adr-crud name: ADR CRUD. Body pillar: AU-KG status: live code_paths: - agent_utilities/mcp/kg_server.py doc: ADR CRUD. Body - id: AU-KG.compute.audiobookshelf-libraries-books-authors name: Audiobookshelf libraries/books/authors → pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/protocols/source_connectors/connectors/mcp_tool.py doc: Audiobookshelf libraries/books/authors → - id: AU-KG.compute.built-ast-extended name: engine built with ast-extended pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/gitlab_indexer.py - agent_utilities/knowledge_graph/enrichment/pipeline.py doc: engine built with ast-extended - id: AU-KG.compute.capability-abstraction name: Capability Abstraction Layer pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/hydration.py doc: Capability Abstraction Layer - id: AU-KG.compute.change-feed-subscription name: Engine change-feed subscription primitive for poll→push reactivity pillar: AU-KG status: live code_paths: - agent_utilities/graph/reactive/engine_subscription.py - agent_utilities/harness/world_model_task.py - agent_utilities/orchestration/fleet_autoscaler.py doc: Engine change-feed subscription primitive for poll→push reactivity - id: AU-KG.compute.code-intelligence-tools name: Code-Intelligence Tools pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/gpu_slot_scheduler.py - agent_utilities/tools/code_intelligence_tools.py doc: Code-Intelligence Tools - id: AU-KG.compute.concurrency-controller-sizing name: Uses the shared per-model bounded thread pool. At most pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/core/model_concurrency.py - agent_utilities/knowledge_graph/enrichment/semantic.py - agent_utilities/knowledge_graph/pipeline/phases/embedding.py doc: Uses the shared per-model bounded thread pool. At most - id: AU-KG.compute.config-keyed-embedder-client name: process-scoped embedder-client cache pillar: AU-KG status: live code_paths: - agent_utilities/core/embedding_utilities.py doc: process-scoped embedder-client cache - id: AU-KG.compute.confluence-first-class-delta name: Confluence first-class delta connector pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/core/hydration.py - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/protocols/source_connectors/connectors/mcp_tool.py doc: Confluence first-class delta connector - id: AU-KG.compute.connector-declared-page-drainer name: Connector-declared page drainer pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/chunked_drain.py doc: Connector-declared page drainer - id: AU-KG.compute.cross-pillar-synergy name: Provides the structural vector to match novel relation topologies pillar: AU-KG status: live code_paths: - agent_utilities/__init__.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/core/synergy_engine.py - agent_utilities/knowledge_graph/memory/strategies/heavy_thinking_cache.py - agent_utilities/knowledge_graph/retrieval/hybrid_retriever.py - agent_utilities/models/imodel.py - agent_utilities/models/knowledge_graph.py doc: Provides the structural vector to match novel relation topologies - id: AU-KG.compute.data-is-private-its name: Data is private-to-its-owner by default; this is the explicit promotion path. action= pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/backends/brain_guarded_backend.py - agent_utilities/knowledge_graph/core/graph_compute.py - agent_utilities/knowledge_graph/core/tenant_registry.py - agent_utilities/knowledge_graph/core/tenant_sharing.py - agent_utilities/knowledge_graph/orchestration/engine_query.py - agent_utilities/mcp/tools/ontology_tools.py doc: Data is private-to-its-owner by default; this is the explicit promotion path. action= - id: AU-KG.compute.dockerhub-repositories name: DockerHub repositories → pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/protocols/source_connectors/connectors/mcp_tool.py doc: DockerHub repositories → - id: AU-KG.compute.engine-surface-manifest name: Every method under one of pillar: AU-KG status: live code_paths: - agent_utilities/mcp/tools/engine_surface_tools.py - agent_utilities/mcp/tools/engine_tools.py doc: Every method under one of - id: AU-KG.compute.firefly-iii-accounts-transactions name: Firefly III accounts/transactions/budgets → pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/protocols/source_connectors/connectors/mcp_tool.py doc: Firefly III accounts/transactions/budgets → - id: AU-KG.compute.first-class-action-conditioned name: a first-class action-conditioned world model wrapping the graph pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/world_model.py doc: a first-class action-conditioned world model wrapping the graph - id: AU-KG.compute.first-class-reasoner-paradigm name: a first-class Reasoner paradigm abstraction with an outcome-learning router that selects a reasoning paradigm per task by capability tags blended with a learned reward EMA and feeds the scored result back so routing self-improves pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/reasoner.py doc: a first-class Reasoner paradigm abstraction with an outcome-learning router that selects a reasoning paradigm per task by capability tags blended with a learned reward EMA and feeds the scored result back so routing self-improves - id: AU-KG.compute.first-class-rss-atom name: a feed is a first-class pillar: AU-KG status: live code_paths: - agent_utilities/automation/feed_sources.py doc: a feed is a first-class - id: AU-KG.compute.gitlab-api-gitlab-atlassian name: gitlab-api→gitlab, atlassian-agent→jira/confluence pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py doc: gitlab-api→gitlab, atlassian-agent→jira/confluence - id: AU-KG.compute.gramps-web-people-families name: Gramps Web people/families/events → pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py doc: Gramps Web people/families/events → - id: AU-KG.compute.graph-builder name: the registry graph persists as pillar: AU-KG status: live code_paths: - agent_utilities/graph/builder.py doc: the registry graph persists as - id: AU-KG.compute.graph-compute-engine name: High-Performance Graph Compute Engine pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/graph_compute.py doc: High-Performance Graph Compute Engine - id: AU-KG.compute.home-assistant-states name: Home Assistant states → pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/protocols/source_connectors/connectors/mcp_tool.py doc: Home Assistant states → - id: AU-KG.compute.http-route-graph name: the HTTP route pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/extractors/code_test.py - agent_utilities/knowledge_graph/enrichment/routes.py - agent_utilities/mcp/kg_server.py doc: the HTTP route - id: AU-KG.compute.inductive-knowledge-hypergraphs name: Inductive Knowledge Hypergraphs pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/hypergraph.py doc: Inductive Knowledge Hypergraphs - id: AU-KG.compute.interactive-lane-floor name: reserves a worker floor that non-interactive lanes can never pillar: AU-KG status: live code_paths: - agent_utilities/core/resource_priority.py - agent_utilities/knowledge_graph/core/task_lanes.py - agent_utilities/knowledge_graph/core/worker_scheduler.py doc: reserves a worker floor that non-interactive lanes can never - id: AU-KG.compute.jira-first-class-delta name: this generic capability is now only pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/core/hydration.py - agent_utilities/knowledge_graph/core/source_sync.py doc: this generic capability is now only - id: AU-KG.compute.kg-3 name: AU-KG.compute.kg-3 pillar: AU-KG status: live code_paths: - agent_utilities/harness/__init__.py - agent_utilities/harness/world_model_task.py - agent_utilities/knowledge_graph/core/world_model.py doc: AU-KG.compute.kg-3 - id: AU-KG.compute.lane-bound-task name: request cooperative cancellation pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py doc: request cooperative cancellation - id: AU-KG.compute.lane-soft-timeout name: per-lane SOFT execution timeout pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/task_lanes.py doc: per-lane SOFT execution timeout - id: AU-KG.compute.langfuse-traces-observations name: Langfuse traces/observations → pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/protocols/source_connectors/connectors/mcp_tool.py doc: Langfuse traces/observations → - id: AU-KG.compute.mcp-backed-dedicated-trackers name: each reaches its upstream ONLY pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py doc: each reaches its upstream ONLY - id: AU-KG.compute.model-display-optimization name: Model Display Optimization pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/model_display.py - agent_utilities/models/imodel.py doc: Model Display Optimization - id: AU-KG.compute.native-sparql-owl-shacl name: Engine-native SPARQL/OWL/SHACL pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/graph_compute.py - agent_utilities/knowledge_graph/pipeline/phases/shacl_gate.py doc: Engine-native SPARQL/OWL/SHACL - id: AU-KG.compute.numeric-kernel name: AU-KG.compute.numeric-kernel pillar: AU-KG status: live code_paths: - agent_utilities/numeric/__init__.py doc: AU-KG.compute.numeric-kernel - id: AU-KG.compute.numpy-scipy-drop name: AU-KG.compute.numpy-scipy-drop pillar: AU-KG status: live code_paths: - agent_utilities/harness/__init__.py - agent_utilities/numeric/__init__.py doc: AU-KG.compute.numpy-scipy-drop - id: AU-KG.compute.offloaded-memory-write name: a memory write offloaded from a SERVING process. The pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/mcp/tools/write_ingest_tools.py doc: a memory write offloaded from a SERVING process. The - id: AU-KG.compute.p99-latency-metric name: surface p99 alongside p95/max so a thin tail pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py doc: surface p99 alongside p95/max so a thin tail - id: AU-KG.compute.paperless-ngx-documents-correspondents name: Paperless-ngx documents/correspondents/tags → pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/protocols/source_connectors/connectors/mcp_tool.py doc: Paperless-ngx documents/correspondents/tags → - id: AU-KG.compute.per-channel-embedding-backfill name: Per-channel embedding backfill pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py doc: Per-channel embedding backfill - id: AU-KG.compute.persistent-task-tracking name: Persistent Task Tracking pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_task_query.py - agent_utilities/knowledge_graph/core/engine_tasks.py doc: Persistent Task Tracking - id: AU-KG.compute.plane-first-class-delta name: Plane first-class delta connector pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/core/source_sync.py doc: Plane first-class delta connector - id: AU-KG.compute.positional-interaction-encoding name: Compute positional interaction encoding for structural generalization pillar: AU-KG status: live code_paths: - agent_utilities/graph/verification.py doc: Compute positional interaction encoding for structural generalization - id: AU-KG.compute.priority-class-propagation name: carry the resource PriorityClass so a spawned/child agent pillar: AU-KG status: live code_paths: - agent_utilities/core/resource_priority.py - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/observability/correlation.py doc: carry the resource PriorityClass so a spawned/child agent - id: AU-KG.compute.pure-config-enumeration-fail name: Pure config enumeration; fail-safe pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/core/gpu_group_budget.py - agent_utilities/core/model_capacity_autoscale.py doc: Pure config enumeration; fail-safe - id: AU-KG.compute.reactive-push name: instead of re-querying the ENTIRE pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py doc: instead of re-querying the ENTIRE - id: AU-KG.compute.registered-edge-type name: The per-batch foreground check in pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py doc: The per-batch foreground check in - id: AU-KG.compute.reuse-model-latent name: the latent the model already computes pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/world_model.py doc: the latent the model already computes - id: AU-KG.compute.single-dropped-connection name: A single dropped connection pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_breaker.py doc: A single dropped connection - id: AU-KG.compute.spark-transform-jobs name: AU-KG.compute.spark-transform-jobs pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/backends/spark_jobs.py doc: AU-KG.compute.spark-transform-jobs - id: AU-KG.compute.spectral-cluster-navigator name: Financial regime detection extension pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/model_display.py - agent_utilities/knowledge_graph/core/spectral_navigator.py - agent_utilities/knowledge_graph/core/topological_analysis_engine.py - agent_utilities/knowledge_graph/orchestration/voi_budget_controller.py - agent_utilities/knowledge_graph/retrieval/single_shot_sira.py - agent_utilities/models/knowledge_graph.py - agent_utilities/models/schema_definition.py doc: Financial regime detection extension - id: AU-KG.compute.structural-fingerprint name: Structural Fingerprint Engine pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/fingerprint.py doc: Structural Fingerprint Engine - id: AU-KG.compute.surface-analytics-program name: AU-KG.compute.surface-analytics-program pillar: AU-KG status: live code_paths: - agent_utilities/numeric/__init__.py doc: AU-KG.compute.surface-analytics-program - id: AU-KG.compute.surfaces-universal-latency-signal name: Surfaces the universal latency signal pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/core/gpu_group_budget.py - agent_utilities/core/model_capacity_autoscale.py - agent_utilities/core/model_circuit_breaker.py - agent_utilities/core/model_concurrency.py doc: Surfaces the universal latency signal - id: AU-KG.compute.symbol-blast-radius name: Symbol Blast Radius Analyzer pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/blast_radius.py doc: Symbol Blast Radius Analyzer - id: AU-KG.compute.task-priority-tag name: tag this task pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py doc: tag this task - id: AU-KG.compute.technitium-dns-zones-records name: Technitium DNS zones+records → pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py doc: Technitium DNS zones+records → - id: AU-KG.compute.tokio-service-layer name: Tokio Service Layer pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/graph_compute.py doc: Tokio Service Layer - id: AU-KG.compute.topological-analogy name: Topological Analogy Engine pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/analogy_engine.py doc: Topological Analogy Engine - id: AU-KG.compute.topological-mincut-partitioning name: Mincut Partitioning pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/topological_partition.py doc: Mincut Partitioning - id: AU-KG.compute.trino-query-backend name: AU-KG.compute.trino-query-backend pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/backends/trino_backend.py - agent_utilities/knowledge_graph/core/tabular_query_service.py doc: AU-KG.compute.trino-query-backend - id: AU-KG.compute.tunnel-manager-hosts name: tunnel-manager hosts → pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py doc: tunnel-manager hosts → - id: AU-KG.compute.twenty-crm-people-companies name: Twenty CRM people/companies/opportunities → pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/protocols/source_connectors/connectors/mcp_tool.py doc: Twenty CRM people/companies/opportunities → - id: AU-KG.compute.uptime-kuma-monitors name: Uptime Kuma monitors → pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py doc: Uptime Kuma monitors → - id: AU-KG.compute.user-override-prompt-library name: the user-override layer of the prompt library, mirroring pillar: AU-KG status: live code_paths: - agent_utilities/agent/registry_builder.py - agent_utilities/core/paths.py - agent_utilities/core/schedule_engine.py - agent_utilities/knowledge_graph/backends/base.py - agent_utilities/knowledge_graph/core/graph_compute.py - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/messaging/bus.py doc: the user-override layer of the prompt library, mirroring - id: AU-KG.compute.workspace-attention-scoring name: WorkspaceAttention scoring for specialist priority pillar: AU-KG status: live code_paths: - agent_utilities/graph/executor.py doc: WorkspaceAttention scoring for specialist priority - id: AU-KG.coordination.embedder-breaker name: keeps a down embedder from being retry-stormed pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py doc: keeps a down embedder from being retry-stormed - id: AU-KG.coordination.engine-message-broker name: federated search fanned across registered external pillar: AU-KG status: live code_paths: - agent_utilities/mcp/tools/audit_tools.py - agent_utilities/mcp/tools/engine_surface_tools.py - agent_utilities/messaging/bus_log.py doc: federated search fanned across registered external - id: AU-KG.coordination.inductive-program-synthesis-search name: inductive program-synthesis search over a typed primitive composition DSL biased by a minimum-description-length prior so among programs that fit the examples the shortest is preferred a finite stand-in for the Solomonoff universal prior pillar: AU-KG status: live code_paths: - agent_utilities/harness/program_synthesis.py - agent_utilities/harness/selection_operators.py doc: inductive program-synthesis search over a typed primitive composition DSL biased by a minimum-description-length prior so among programs that fit the examples the shortest is preferred a finite stand-in for the Solomonoff universal prior - id: AU-KG.coordination.research-cohort-barrier name: the research-cohort barrier gate pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/core/task_lanes.py - agent_utilities/knowledge_graph/research/cohort.py doc: the research-cohort barrier gate - id: AU-KG.coordination.warm-fork-fanout name: warm-fork fan-out over the ORCH-1.86..93 warm-fork pillar: AU-KG status: live code_paths: - agent_utilities/mcp/tools/engine_surface_tools.py doc: warm-fork fan-out over the ORCH-1.86..93 warm-fork - id: AU-KG.domains.agent-calibration-reputation-tracking name: Agent Calibration and Reputation Tracking pillar: AU-KG status: live code_paths: - agent_utilities/domains/finance/calibration_tracker.py - agent_utilities/domains/finance/trading_swarm.py doc: Agent Calibration and Reputation Tracking - id: AU-KG.domains.company-intelligence-graph name: Company Intelligence Graph pillar: AU-KG status: live code_paths: - agent_utilities/models/company.py doc: Company Intelligence Graph - id: AU-KG.domains.company-operations name: Company Operations Domain pillar: AU-KG status: live code_paths: - agent_utilities/models/company.py doc: Company Operations Domain - id: AU-KG.domains.dividend-sustainability-credit-fixed name: Dividend Sustainability & Credit/Fixed-Income Quality pillar: AU-KG status: live code_paths: - agent_utilities/domains/finance/credit_quality.py doc: Dividend Sustainability & Credit/Fixed-Income Quality - id: AU-KG.domains.geopolitical-risk-scoring name: Geopolitical Risk Scoring pillar: AU-KG status: live code_paths: - agent_utilities/domains/finance/geopolitical_risk.py doc: Geopolitical Risk Scoring - id: AU-KG.domains.hr-workforce-management name: HR/Workforce Management pillar: AU-KG status: live code_paths: - agent_utilities/domains/hr/__init__.py doc: HR/Workforce Management - id: AU-KG.domains.lazy-symbol-loading name: Lazy symbol loading. The finance domain pulls heavy optional pillar: AU-KG status: live code_paths: - agent_utilities/domains/finance/__init__.py - agent_utilities/knowledge_graph/core/engine.py doc: Lazy symbol loading. The finance domain pulls heavy optional - id: AU-KG.domains.multi-domain-architecture name: Multi-Domain Architecture pillar: AU-KG status: live code_paths: - agent_utilities/domains/__init__.py doc: Multi-Domain Architecture - id: AU-KG.domains.multi-market-composite-backtester name: Multi-Market Composite Backtester pillar: AU-KG status: live code_paths: - agent_utilities/domains/finance/composite_backtest.py doc: Multi-Market Composite Backtester - id: AU-KG.domains.ohlcv-gap-fill name: when True, gappy/irregular raw OHLCV is gap-filled onto a pillar: AU-KG status: live code_paths: - agent_utilities/domains/finance/engine_series.py - agent_utilities/domains/finance/features.py - agent_utilities/knowledge_graph/memory/timeseries/engine_backend.py doc: when True, gappy/irregular raw OHLCV is gap-filled onto a - id: AU-KG.domains.persona-decision-heuristic-enrichment name: Persona Decision-Heuristic Enrichment pillar: AU-KG status: live code_paths: - agent_utilities/domains/finance/persona_heuristics.py doc: Persona Decision-Heuristic Enrichment - id: AU-KG.domains.sentiment-fusion-signals name: Sentiment Fusion Signals pillar: AU-KG status: live code_paths: - agent_utilities/domains/finance/sentiment_fusion.py doc: Sentiment Fusion Signals - id: AU-KG.domains.trade-journal-bias-auditor name: the Palantir *many-to-many link backed by an object type* pillar: AU-KG status: live code_paths: - agent_utilities/domains/finance/trade_journal.py - agent_utilities/knowledge_graph/ontology/__init__.py - agent_utilities/knowledge_graph/ontology/links.py - agent_utilities/mcp/tools/ontology_tools.py - agent_utilities/mcp/tools/state_tools.py doc: the Palantir *many-to-many link backed by an object type* - id: AU-KG.enrichment.a2a-capability-extraction name: S4c pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/execute.py - agent_utilities/knowledge_graph/enrichment/extractors/a2a.py - agent_utilities/knowledge_graph/enrichment/extractors/config_models.py - agent_utilities/knowledge_graph/enrichment/pydantic_graph.py - agent_utilities/knowledge_graph/enrichment/synthesize.py doc: S4c - id: AU-KG.enrichment.atomic-triple-extraction name: AU-KG.enrichment.atomic-triple-extraction pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/extraction/__init__.py - agent_utilities/knowledge_graph/extraction/fact_extractor.py doc: AU-KG.enrichment.atomic-triple-extraction - id: AU-KG.enrichment.candidate-claim-extraction name: and Track 5 pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/extraction/candidate_claims.py - agent_utilities/mcp/tools/candidate_claim_tools.py doc: and Track 5 - id: AU-KG.enrichment.card-attempt-status name: keeps a down card LLM from being retry-stormed pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/core/task_lanes.py - agent_utilities/knowledge_graph/enrichment/cards.py - agent_utilities/knowledge_graph/enrichment/pipeline.py - agent_utilities/knowledge_graph/enrichment/query.py doc: keeps a down card LLM from being retry-stormed - id: AU-KG.enrichment.ciso-2 name: AU-KG.enrichment.ciso-2 pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/writeback/sinks/ciso_assistant.py doc: AU-KG.enrichment.ciso-2 - id: AU-KG.enrichment.ciso-assistant-extraction name: AU-KG.enrichment.ciso-assistant-extraction pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/extractors/ciso_assistant.py doc: AU-KG.enrichment.ciso-assistant-extraction - id: AU-KG.enrichment.community-reports name: AU-KG.enrichment.community-reports pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/pipeline/phases/community_reports.py doc: AU-KG.enrichment.community-reports - id: AU-KG.enrichment.compliance-posture-rollup name: Reuses pillar: AU-KG status: live code_paths: - agent_utilities/mcp/tools/compliance_tools.py doc: Reuses - id: AU-KG.enrichment.contextual-retrieval-enrichment name: situate each chunk within the document and embed context+chunk for better recall pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/engine.py - agent_utilities/knowledge_graph/ontology/contextual_enrichment.py - agent_utilities/knowledge_graph/ontology/document_processing.py - agent_utilities/mcp/tools/ontology_tools.py doc: situate each chunk within the document and embed context+chunk for better recall - id: AU-KG.enrichment.cross-layer-incident-correlation name: browse and drive the pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/research/candidate_insight.py - agent_utilities/mcp/tools/incident_tools.py - agent_utilities/observability/incidents.py doc: browse and drive the - id: AU-KG.enrichment.direction-repair name: AU-KG.enrichment.direction-repair pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/extraction/direction_repair.py doc: AU-KG.enrichment.direction-repair - id: AU-KG.enrichment.each-call-resolves-active name: '** Each call resolves the ACTIVE' pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/core/embedding_failover.py - agent_utilities/core/embedding_utilities.py - agent_utilities/core/model_capacity_autoscale.py - agent_utilities/core/model_circuit_breaker.py - agent_utilities/knowledge_graph/enrichment/semantic.py - agent_utilities/knowledge_graph/retrieval/embedding_versioning.py doc: '** Each call resolves the ACTIVE' - id: AU-KG.enrichment.entity-claim-extraction name: Entity-Claim Extraction for MAGMA Epistemic View pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/kb/entity_claim_extractor.py - agent_utilities/knowledge_graph/orchestration/engine_query.py doc: Entity-Claim Extraction for MAGMA Epistemic View - id: AU-KG.enrichment.extraction-outcome-taxonomy name: the ONE typed vocabulary pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/engine.py - agent_utilities/knowledge_graph/kb/entity_claim_extractor.py - agent_utilities/knowledge_graph/kb/extraction_run.py - agent_utilities/models/knowledge_graph.py doc: the ONE typed vocabulary - id: AU-KG.enrichment.extraction-run-provenance name: Extraction Run Provenance pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/kb/entity_claim_extractor.py - agent_utilities/knowledge_graph/kb/extraction_run.py - agent_utilities/models/knowledge_graph.py doc: Extraction Run Provenance - id: AU-KG.enrichment.http-route-extraction name: HTTP routes from handler decorators pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/pipeline.py doc: HTTP routes from handler decorators - id: AU-KG.enrichment.incident-ticket-routing name: A small pluggable-adapter pillar: AU-KG status: live code_paths: - agent_utilities/observability/incident_router.py doc: A small pluggable-adapter - id: AU-KG.enrichment.multimodal-readers name: Keys are normalised lowercase; an extension is stored with a pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/extraction/readers.py - agent_utilities/knowledge_graph/extraction/readers_office.py - agent_utilities/knowledge_graph/ingestion/engine.py - agent_utilities/protocols/source_connectors/connectors/__init__.py - agent_utilities/protocols/source_connectors/connectors/reader.py doc: Keys are normalised lowercase; an extension is stored with a - id: AU-KG.enrichment.ops-causal-graph name: The fleet ingests the SAME git pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/ops_causal_graph.py - agent_utilities/knowledge_graph/research/candidate_insight.py - agent_utilities/mcp/tools/incident_tools.py - agent_utilities/mcp/tools/ops_causal_tools.py - agent_utilities/observability/incident_router.py - agent_utilities/observability/incidents.py - agent_utilities/observability/repo_crosswalk.py doc: The fleet ingests the SAME git - id: AU-KG.enrichment.portfolio-intelligence name: AU-KG.enrichment.portfolio-intelligence pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/writeback/sinks/servicenow.py - agent_utilities/observability/portfolio_intelligence.py doc: AU-KG.enrichment.portfolio-intelligence - id: AU-KG.enrichment.proposals-live-as name: proposals live as pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/writeback/approval.py doc: proposals live as - id: AU-KG.enrichment.query-ingested-commit-history name: ─────────────────────────────── pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/git_history.py - agent_utilities/mcp/kg_server.py doc: ─────────────────────────────── - id: AU-KG.enrichment.read-them-here-so name: read them here so the pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/iac.py - agent_utilities/knowledge_graph/enrichment/pipeline.py doc: read them here so the - id: AU-KG.enrichment.relation-projection name: materialise the edges a node pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/backends/epistemic_graph_backend.py - agent_utilities/knowledge_graph/enrichment/relation_projection.py - agent_utilities/knowledge_graph/ingestion/envelope_ingest.py doc: materialise the edges a node - id: AU-KG.enrichment.second-brain-note-sync name: is the one-call personal-notes sync pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/extraction/second_brain_sync.py - agent_utilities/mcp/tools/write_ingest_tools.py doc: is the one-call personal-notes sync - id: AU-KG.enrichment.ticket-status-comment-writeback name: Ticket status and comment writeback pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/writeback/sinks/issue_tracker.py doc: Ticket status and comment writeback - id: AU-KG.enrichment.topic-classification-topology name: description=raw text pillar: AU-KG status: live code_paths: - agent_utilities/automation/worldmodel_pipeline.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/enrichment/topic_classifier.py - agent_utilities/knowledge_graph/ingestion/engine.py - agent_utilities/knowledge_graph/memory/native_ingest.py - agent_utilities/mcp/tools/write_ingest_tools.py doc: description=raw text - id: AU-KG.enrichment.worldview-subject-ontology name: a curated, reasonably-MECE pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/topic_classifier.py doc: a curated, reasonably-MECE - id: AU-KG.epistemic.aif name: AU-KG.epistemic.aif pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/argumentation/__init__.py - agent_utilities/knowledge_graph/argumentation/aif.py - agent_utilities/mcp/tools/argument_tools.py doc: AU-KG.epistemic.aif - id: AU-KG.etl.result-contract name: Connector-specific output is isolated under pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/knowledge_graph/core/table_ingest.py - agent_utilities/knowledge_graph/etl/pipeline.py - agent_utilities/knowledge_graph/etl/result.py doc: Connector-specific output is isolated under - id: AU-KG.etl.transform-primitives name: AU-KG.etl.transform-primitives pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/knowledge_graph/etl/transforms.py doc: AU-KG.etl.transform-primitives - id: AU-KG.evolution.insight-engine-closed-loop name: closed-loop agent mining pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/research/candidate_insight.py - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/knowledge_graph/research/trace_pattern_miner.py - agent_utilities/orchestration/action_policy.py doc: closed-loop agent mining - id: AU-KG.evolution.mining-flywheel name: writes back typed, descriptive KG facts pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/research/candidate_insight.py - agent_utilities/knowledge_graph/research/claim_flywheel.py - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/mcp/tools/claim_tools.py - agent_utilities/mcp/tools/ops_causal_tools.py - agent_utilities/mcp/tools/state_tools.py doc: writes back typed, descriptive KG facts - id: AU-KG.evolution.neural-relation-proposal-producer name: D-OB-11 pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/ocel_adapter.py doc: D-OB-11 - id: AU-KG.evolution.placement-mining-canary-loop name: manual-trigger pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/research/placement_mining.py - agent_utilities/mcp/tools/state_tools.py - agent_utilities/orchestration/action_policy.py doc: manual-trigger - id: AU-KG.evolution.unified-evidence-resource name: and stages them for pillar: AU-KG status: live code_paths: - agent_utilities/harness/program_optimization.py - agent_utilities/knowledge_graph/orchestration/research_orchestrator.py - agent_utilities/knowledge_graph/research/candidate_insight.py - agent_utilities/knowledge_graph/research/evidence.py - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/mcp/tools/engine_surface_tools.py - agent_utilities/models/knowledge_graph.py doc: and stages them for - id: AU-KG.identity.asset-occurrence name: migrate_legacy_assets_bulk progress callback failed pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/memory/cli.py - agent_utilities/knowledge_graph/memory/media_store.py - agent_utilities/mcp/tools/write_ingest_tools.py - agent_utilities/messaging/router.py doc: migrate_legacy_assets_bulk progress callback failed - id: AU-KG.identity.canonical-id-non-idempotence name: AU-KG.identity.canonical-id-non-idempotence pillar: AU-KG status: live code_paths: - agent_utilities/capabilities/kg_audit_sink.py doc: AU-KG.identity.canonical-id-non-idempotence - id: AU-KG.identity.entity-resolution-candidates name: exposed as a standalone pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/assimilation/identity_candidates.py - agent_utilities/mcp/tools/candidate_claim_tools.py - agent_utilities/models/knowledge_graph.py doc: exposed as a standalone - id: AU-KG.identity.evidence-spine-convergence name: Evidence write failed for occurrence pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/etl/lineage.py - agent_utilities/knowledge_graph/extraction/readers_media.py - agent_utilities/knowledge_graph/extraction/readers_office.py - agent_utilities/knowledge_graph/ingestion/engine.py - agent_utilities/knowledge_graph/kb/extraction_run.py - agent_utilities/knowledge_graph/memory/media_store.py - agent_utilities/knowledge_graph/research/candidate_insight.py - agent_utilities/messaging/router.py - agent_utilities/messaging/voice.py - agent_utilities/protocols/source_connectors/connectors/database.py doc: Evidence write failed for occurrence - id: AU-KG.identity.verified-carrier-required-federation name: AU-KG.identity.verified-carrier-required-federation pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/orchestration/engine_federation.py doc: AU-KG.identity.verified-carrier-required-federation - id: AU-KG.ingest.agent-utilities-checkout name: the agent-utilities checkout pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/assimilation/breadth_ingest.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/ingestion/engine.py doc: the agent-utilities checkout - id: AU-KG.ingest.ambient-connector-provenance name: '**' pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/knowledge_graph/etl/lineage.py doc: '**' - id: AU-KG.ingest.applying-agents-md-batch name: applying the AGENTS.md *batch-never-per-element* rule to pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/semantic.py - agent_utilities/knowledge_graph/pipeline/phases/embedding.py doc: applying the AGENTS.md *batch-never-per-element* rule to - id: AU-KG.ingest.arxiv-feed-connector name: native arXiv category codes pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/core/schedule_engine.py - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/protocols/source_connectors/connectors/arxiv.py doc: native arXiv category codes - id: AU-KG.ingest.atomic-compare-and-set name: atomic compare-and-set as a first-class pillar: AU-KG status: live code_paths: - agent_utilities/mcp/tools/write_ingest_tools.py doc: atomic compare-and-set as a first-class - id: AU-KG.ingest.attaching-this-root-logger name: Attaching this to the root logger routes all pillar: AU-KG status: live code_paths: - agent_utilities/__main__.py - agent_utilities/gateway/daemon.py - agent_utilities/observability/self_ingest.py - agent_utilities/orchestration/engine.py doc: Attaching this to the root logger routes all - id: AU-KG.ingest.backfeed-preflight name: per-field conflict resolution and a fail-closed gate every source-sync/writeback commit passes through pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/knowledge_graph/ontology/sync_conflict.py doc: per-field conflict resolution and a fail-closed gate every source-sync/writeback commit passes through - id: AU-KG.ingest.batch-research-cohort name: AU-KG.ingest.batch-research-cohort pillar: AU-KG status: live code_paths: - agent_utilities/mcp/tools/write_ingest_tools.py doc: AU-KG.ingest.batch-research-cohort - id: AU-KG.ingest.batched-cross-graph-writer name: A high-volume source pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/core/graph_compute.py - agent_utilities/knowledge_graph/core/ingest_routing.py doc: A high-volume source - id: AU-KG.ingest.big-repo-structural-split name: Big-repo structural-ingest split pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/repo_split.py doc: Big-repo structural-ingest split - id: AU-KG.ingest.broken-link-tolerance name: Skips images and bare in-page pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/document_processing.py doc: Skips images and bare in-page - id: AU-KG.ingest.capability-writeback name: Best-effort + lazy LLM; the pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/engine.py doc: Best-effort + lazy LLM; the - id: AU-KG.ingest.change-envelope name: AU-ECO.connector.incremental-poll-watermark pillar: AU-KG status: live code_paths: - agent_utilities/automation/worldmodel_pipeline.py - agent_utilities/data_prep/connector_contract.py - agent_utilities/knowledge_graph/argumentation/aif.py - agent_utilities/knowledge_graph/ingestion/change_envelope.py - agent_utilities/knowledge_graph/ingestion/engine.py - agent_utilities/knowledge_graph/ingestion/external_graph.py - agent_utilities/knowledge_graph/ingestion/graphql_connection.py doc: AU-ECO.connector.incremental-poll-watermark - id: AU-KG.ingest.chunk-overlap-stage name: the one-call form the ingestion engine / MCP wrapper invokes pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/facade.py - agent_utilities/knowledge_graph/ontology/__init__.py - agent_utilities/knowledge_graph/ontology/document_processing.py - agent_utilities/mcp/tools/ontology_tools.py - agent_utilities/mcp/tools/write_ingest_tools.py doc: the one-call form the ingestion engine / MCP wrapper invokes - id: AU-KG.ingest.claude-memory-connector name: AU-KG.ingest.claude-memory-connector pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py doc: AU-KG.ingest.claude-memory-connector - id: AU-KG.ingest.code-source-partition name: AU-KG.ingest.code-source-partition pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/pipeline.py - agent_utilities/knowledge_graph/ingestion/engine.py doc: AU-KG.ingest.code-source-partition - id: AU-KG.ingest.content-acquisition name: the acquisition half of content-aware ingestion. Given pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/research_acquisition.py doc: the acquisition half of content-aware ingestion. Given - id: AU-KG.ingest.cross-host-safe-kg name: Cross-host-safe KG task queue with atomic SKIP LOCKED claims and visibility-timeout recovery on the shared state store pillar: AU-KG status: live code_paths: - agent_utilities/core/leadership.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/core/postgres_queue_backend.py doc: Cross-host-safe KG task queue with atomic SKIP LOCKED claims and visibility-timeout recovery on the shared state store - id: AU-KG.ingest.dead-letter-drain name: never a silent aggregate-only pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/dead_letter.py - agent_utilities/mcp/tools/job_tools.py - agent_utilities/models/knowledge_graph.py doc: never a silent aggregate-only - id: AU-KG.ingest.debezium-changeenvelope name: env feature flag gating the pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/debezium_envelope.py - agent_utilities/knowledge_graph/streams/kafka_adapter.py - agent_utilities/mcp/tools/write_ingest_tools.py doc: env feature flag gating the - id: AU-KG.ingest.decoupled-kg-ingest-consumer name: Decoupled kg-ingest consumer group with idempotent at-least-once task claims pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/core/kafka_queue_backend.py - agent_utilities/knowledge_graph/ingest_worker.py - agent_utilities/knowledge_graph/ingestion/batch_orchestrator.py - agent_utilities/observability/gateway_metrics.py doc: Decoupled kg-ingest consumer group with idempotent at-least-once task claims - id: AU-KG.ingest.default-graph-leak-guard name: ── pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_partition.py doc: ── - id: AU-KG.ingest.deterministic-classifier name: a repo is not just code. Run the deterministic pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/engine.py doc: a repo is not just code. Run the deterministic - id: AU-KG.ingest.deterministic-extraction-default name: deterministic pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/engine.py - agent_utilities/knowledge_graph/kb/entity_claim_extractor.py - agent_utilities/models/knowledge_graph.py doc: deterministic - id: AU-KG.ingest.deterministic-social-entity-mining name: AU-KG.ingest.deterministic-social-entity-mining pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/extractors/social.py doc: AU-KG.ingest.deterministic-social-entity-mining - id: AU-KG.ingest.domain-pack-framework name: a pack author states its pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/domain_packs/__init__.py - agent_utilities/knowledge_graph/domain_packs/domain_pack.py - agent_utilities/knowledge_graph/domain_packs/envelope_bridge.py - agent_utilities/knowledge_graph/domain_packs/pack_loader.py - agent_utilities/knowledge_graph/ingestion/envelope_ingest.py - agent_utilities/knowledge_graph/ingestion/evidence_spine.py - agent_utilities/knowledge_graph/ingestion/promotion.py doc: a pack author states its - id: AU-KG.ingest.drain-session-bundle name: drain a remote session-bundle upload that the pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/core/task_lanes.py - agent_utilities/mcp/tools/write_ingest_tools.py doc: drain a remote session-bundle upload that the - id: AU-KG.ingest.embedding-admission name: AU-KG.ingest.embedding-admission pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/embedding_admission.py doc: AU-KG.ingest.embedding-admission - id: AU-KG.ingest.engineering-rules name: Entity-Claim Extraction / MAGMA Epistemic View pillar: AU-KG status: live code_paths: - agent_utilities/automation/research_pipeline.py - agent_utilities/knowledge_graph/core/engine_ingestion.py - agent_utilities/knowledge_graph/core/inference_engine.py - agent_utilities/knowledge_graph/core/model_display.py - agent_utilities/knowledge_graph/id_management/ontological_identifier.py - agent_utilities/knowledge_graph/retrieval/hybrid_retriever.py - agent_utilities/knowledge_graph/security/policy_ingestor.py - agent_utilities/knowledge_graph/security/rule_ingestor.py - agent_utilities/models/imodel.py - agent_utilities/models/knowledge_graph.py - agent_utilities/policies/__init__.py - agent_utilities/prompting/provider_adapter.py - agent_utilities/prompting/structured.py doc: Entity-Claim Extraction / MAGMA Epistemic View - id: AU-KG.ingest.enqueue-large-batch name: the server now ENQUEUES a large batch as a background pillar: AU-KG status: live code_paths: - agent_utilities/ingestion/collector.py doc: the server now ENQUEUES a large batch as a background - id: AU-KG.ingest.enterprise-source-extractor name: which speaks **PostgreSQL, MySQL/MariaDB, MS SQL Server, Oracle pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/ecosystem/ea_clients.py - agent_utilities/gateway/ontology_api.py - agent_utilities/knowledge_graph/backends/base.py - agent_utilities/knowledge_graph/backends/cypher_transpiler.py - agent_utilities/knowledge_graph/backends/postgresql_backend.py - agent_utilities/knowledge_graph/core/engine.py - agent_utilities/knowledge_graph/core/hydration.py - agent_utilities/knowledge_graph/core/materialization.py - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/knowledge_graph/enrichment/extractors/ansible.py - agent_utilities/knowledge_graph/enrichment/extractors/archer.py - agent_utilities/knowledge_graph/enrichment/extractors/archimate.py - agent_utilities/knowledge_graph/enrichment/extractors/aris.py - agent_utilities/knowledge_graph/enrichment/extractors/caddy.py - agent_utilities/knowledge_graph/enrichment/extractors/camunda.py - agent_utilities/knowledge_graph/enrichment/extractors/egeria.py - agent_utilities/knowledge_graph/enrichment/extractors/emerald.py - agent_utilities/knowledge_graph/enrichment/extractors/erpnext.py - agent_utilities/knowledge_graph/enrichment/extractors/grafana.py - agent_utilities/knowledge_graph/enrichment/extractors/home_assistant.py - agent_utilities/knowledge_graph/enrichment/extractors/infra.py - agent_utilities/knowledge_graph/enrichment/extractors/kafka.py - agent_utilities/knowledge_graph/enrichment/extractors/keycloak.py - agent_utilities/knowledge_graph/enrichment/extractors/leanix.py - agent_utilities/knowledge_graph/enrichment/extractors/lgtm.py - agent_utilities/knowledge_graph/enrichment/extractors/mealie.py - agent_utilities/knowledge_graph/enrichment/extractors/microsoft.py - agent_utilities/knowledge_graph/enrichment/extractors/nextcloud.py - agent_utilities/knowledge_graph/enrichment/extractors/odoo.py - agent_utilities/knowledge_graph/enrichment/extractors/okta.py - agent_utilities/knowledge_graph/enrichment/extractors/portainer.py - agent_utilities/knowledge_graph/enrichment/extractors/salesforce.py - agent_utilities/knowledge_graph/enrichment/extractors/technitium_dns.py - agent_utilities/knowledge_graph/enrichment/extractors/twenty.py - agent_utilities/knowledge_graph/enrichment/extractors/uptime_kuma.py - agent_utilities/knowledge_graph/enrichment/extractors/wger.py - agent_utilities/knowledge_graph/enrichment/materialize.py - agent_utilities/knowledge_graph/enrichment/models.py - agent_utilities/knowledge_graph/enrichment/provenance.py - agent_utilities/knowledge_graph/enrichment/registry.py - agent_utilities/knowledge_graph/enrichment/source_adapters.py - agent_utilities/knowledge_graph/enrichment/writeback/approval.py - agent_utilities/knowledge_graph/enrichment/writeback/asset_mirror.py - agent_utilities/knowledge_graph/enrichment/writeback/findings.py - agent_utilities/knowledge_graph/enrichment/writeback/inventory.py - agent_utilities/knowledge_graph/enrichment/writeback/sinks/ansible.py - agent_utilities/knowledge_graph/enrichment/writeback/sinks/archimate.py - agent_utilities/knowledge_graph/enrichment/writeback/sinks/egeria.py - agent_utilities/knowledge_graph/enrichment/writeback/sinks/emerald.py - agent_utilities/knowledge_graph/enrichment/writeback/sinks/erpnext.py - agent_utilities/knowledge_graph/enrichment/writeback/sinks/home_assistant.py - agent_utilities/knowledge_graph/enrichment/writeback/sinks/identity.py - agent_utilities/knowledge_graph/enrichment/writeback/sinks/issue_tracker.py - agent_utilities/knowledge_graph/enrichment/writeback/sinks/leanix.py - agent_utilities/knowledge_graph/enrichment/writeback/sinks/legal.py - agent_utilities/knowledge_graph/enrichment/writeback/sinks/mealie.py - agent_utilities/knowledge_graph/enrichment/writeback/sinks/nextcloud.py - agent_utilities/knowledge_graph/enrichment/writeback/sinks/ops.py - agent_utilities/knowledge_graph/enrichment/writeback/sinks/salesforce.py - agent_utilities/knowledge_graph/enrichment/writeback/sinks/servicenow.py - agent_utilities/knowledge_graph/enrichment/writeback/sinks/twenty.py - agent_utilities/knowledge_graph/enrichment/writeback/sinks/wger.py - agent_utilities/knowledge_graph/enrichment/writeback/spec_link.py - agent_utilities/knowledge_graph/infra/__init__.py - agent_utilities/knowledge_graph/infra/inventory_collector.py - agent_utilities/knowledge_graph/infra/placement_optimizer.py - agent_utilities/knowledge_graph/ingestion/engine.py - agent_utilities/knowledge_graph/ingestion/package_install_ingest.py - agent_utilities/knowledge_graph/memory/native_ingest.py - agent_utilities/knowledge_graph/ontology/leanix_metamodel.py - agent_utilities/mcp/tools/ontology_tools.py - agent_utilities/observability/health_ingest.py - agent_utilities/protocols/source_connectors/connectors/database.py - agent_utilities/tools/db_tools.py doc: which speaks **PostgreSQL, MySQL/MariaDB, MS SQL Server, Oracle - id: AU-KG.ingest.entity-embedding-at-write name: every typed-entity pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/semantic.py doc: every typed-entity - id: AU-KG.ingest.envelope-atomic name: AU-KG.ingest.envelope-atomic pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py doc: AU-KG.ingest.envelope-atomic - id: AU-KG.ingest.envelope-atomic-transaction name: shared migration tail for the pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine.py - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/knowledge_graph/ingestion/envelope_ingest.py - agent_utilities/knowledge_graph/ontology/connector_manifest_gate.py - agent_utilities/mcp/tools/write_ingest_tools.py doc: shared migration tail for the - id: AU-KG.ingest.evidence-spine-artifact name: one retrieved source object pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/domain_packs/markdown_fragmenter.py - agent_utilities/knowledge_graph/ingestion/evidence_spine.py - agent_utilities/knowledge_graph/ontology/document_processing.py - agent_utilities/protocols/source_connectors/connectors/git_markdown.py doc: one retrieved source object - id: AU-KG.ingest.exact-parser-acknowledgement name: AND the base pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/extractors/code_test.py - agent_utilities/knowledge_graph/enrichment/pipeline.py - agent_utilities/knowledge_graph/ingestion/batch_orchestrator.py - agent_utilities/knowledge_graph/ingestion/engine.py doc: AND the base - id: AU-KG.ingest.external-graph-federation name: External Graph Federation pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/external_graph.py - agent_utilities/knowledge_graph/orchestration/engine_federation.py - agent_utilities/knowledge_graph/pipeline/phases/external_graphs.py - agent_utilities/protocols/source_connectors/connectors/graphql_document.py doc: External Graph Federation - id: AU-KG.ingest.external-graph-mapping-approval name: AU-KG.ingest.external-graph-mapping-approval pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/external_graph_schema.py - agent_utilities/knowledge_graph/ingestion/graphql_connection.py doc: AU-KG.ingest.external-graph-mapping-approval - id: AU-KG.ingest.external-graph-universal-discovery name: AU-KG.ingest.external-graph-universal-discovery pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/external_graph_schema.py - agent_utilities/knowledge_graph/ingestion/graphql_connection.py doc: AU-KG.ingest.external-graph-universal-discovery - id: AU-KG.ingest.external-tracker-ids name: external tracker ids this spec is tracked by, e.g pillar: AU-KG status: live code_paths: - agent_utilities/models/sdd.py doc: external tracker ids this spec is tracked by, e.g - id: AU-KG.ingest.fact-supersession name: AU-KG.ingest.fact-supersession pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/supersession.py doc: AU-KG.ingest.fact-supersession - id: AU-KG.ingest.fetch-only-requested-ids name: so ranking a cohort never pulls the whole graph pillar: AU-KG status: live code_paths: - agent_utilities/automation/research_pipeline.py - agent_utilities/knowledge_graph/assimilation/concept_matcher.py - agent_utilities/knowledge_graph/assimilation/feature_matrix.py - agent_utilities/knowledge_graph/assimilation/gap_analysis.py - agent_utilities/knowledge_graph/assimilation/synergy.py - agent_utilities/knowledge_graph/research/cohort.py - agent_utilities/knowledge_graph/research/loop_controller.py doc: so ranking a cohort never pulls the whole graph - id: AU-KG.ingest.fleet-catalog-acl-projection name: the SQL half of the pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/fleet_catalog_tables.py - agent_utilities/knowledge_graph/core/secured_reads.py doc: the SQL half of the - id: AU-KG.ingest.fleet-catalog-relational-tables name: Runs FIRST, from the pillar: AU-KG status: live code_paths: - agent_utilities/gateway/registry_api.py - agent_utilities/knowledge_graph/core/discovery_authority.py - agent_utilities/knowledge_graph/core/fleet_catalog_tables.py - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/knowledge_graph/ingestion/fleet_skill_harvest.py - agent_utilities/knowledge_graph/ingestion/skill_workflow_ingest.py - agent_utilities/mcp/kg_server.py doc: Runs FIRST, from the - id: AU-KG.ingest.fleet-sync-rejected-row-cache name: best-effort local pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py doc: best-effort local - id: AU-KG.ingest.floor-codebase-admission-cap name: Floor the codebase admission cap at the engine pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/worker_scheduler.py doc: Floor the codebase admission cap at the engine - id: AU-KG.ingest.generalized-cross-lane-parallelization name: generalized cross-lane parallelization pillar: AU-KG status: live code_paths: - agent_utilities/automation/research_pipeline.py - agent_utilities/knowledge_graph/ingestion/engine.py doc: generalized cross-lane parallelization - id: AU-KG.ingest.gotcha-feedback-capture name: a pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/adaptation/feedback.py - agent_utilities/knowledge_graph/retrieval/code_context.py - agent_utilities/mcp/tools/write_ingest_tools.py doc: a - id: AU-KG.ingest.governed-claim-promotion name: per-pack/per-domain pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/domain_packs/domain_pack.py - agent_utilities/knowledge_graph/ingestion/envelope_ingest.py - agent_utilities/knowledge_graph/ingestion/promotion.py - agent_utilities/mcp/tools/claim_tools.py doc: per-pack/per-domain - id: AU-KG.ingest.governed-documentation-projection name: AU-KG.ingest.governed-documentation-projection pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/governed_documentation.py doc: AU-KG.ingest.governed-documentation-projection - id: AU-KG.ingest.hardened-priority-scheduled-task name: Hardened priority and scheduled task queue with retry and dead-letter pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_task_query.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/research/loops.py - agent_utilities/orchestration/agent_dispatch.py doc: Hardened priority and scheduled task queue with retry and dead-letter - id: AU-KG.ingest.ingestion-engine name: Ingestion Engine pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/__init__.py doc: Ingestion Engine - id: AU-KG.ingest.instead name: instead pillar: AU-KG status: live code_paths: - agent_utilities/automation/worldmodel_pipeline.py doc: instead - id: AU-KG.ingest.keys-off name: keys off the pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/enrichment/semantic.py doc: keys off the - id: AU-KG.ingest.knowledge-distillation name: Knowledge Distillation Engine pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/distillation/__init__.py - agent_utilities/knowledge_graph/distillation/deduplicator.py - agent_utilities/knowledge_graph/distillation/distillation_engine.py - agent_utilities/knowledge_graph/distillation/lsh_index.py doc: Knowledge Distillation Engine - id: AU-KG.ingest.list-durable-media name: the durable-media path needs the engine BLOB substrate, reached pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/memory/media_store.py - agent_utilities/messaging/router.py doc: the durable-media path needs the engine BLOB substrate, reached - id: AU-KG.ingest.logical-identity name: every input pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/extractors/code_test.py - agent_utilities/knowledge_graph/enrichment/pipeline.py doc: every input - id: AU-KG.ingest.mapping-dsl name: the pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/domain_packs/__init__.py - agent_utilities/knowledge_graph/domain_packs/domain_pack.py - agent_utilities/knowledge_graph/domain_packs/dsl.py - agent_utilities/knowledge_graph/domain_packs/markdown_fragmenter.py doc: the - id: AU-KG.ingest.mcp-tool-connector name: ──────────────────────────── pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/extraction/second_brain_sync.py - agent_utilities/knowledge_graph/ingestion/debezium_envelope.py - agent_utilities/knowledge_graph/ontology/connector_manifest.py - agent_utilities/messaging/backfill.py - agent_utilities/protocols/source_connectors/connectors/__init__.py - agent_utilities/protocols/source_connectors/connectors/database.py - agent_utilities/protocols/source_connectors/connectors/mcp_tool.py doc: ──────────────────────────── - id: AU-KG.ingest.media-sidecar-delegation name: CAS blob-ref input, fail-closed capability manifest, PROV-O governance pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/etl/lineage.py - agent_utilities/mcp/tools/media_sidecar_tools.py - agent_utilities/media/__init__.py - agent_utilities/media/audio_sidecar.py - agent_utilities/media/image_sidecar.py - agent_utilities/media/pdf_sidecar.py - agent_utilities/media/sidecar_contract.py - agent_utilities/media/sidecar_delegate.py - agent_utilities/media/video_sidecar.py doc: CAS blob-ref input, fail-closed capability manifest, PROV-O governance - id: AU-KG.ingest.mine-git-history-files name: mine a pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/git_coupling.py - agent_utilities/mcp/kg_server.py doc: mine a - id: AU-KG.ingest.mirror-inbound name: ask the Knowledge Graph in plain English. An LLM pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/nl_query.py - agent_utilities/knowledge_graph/core/table_ingest.py - agent_utilities/knowledge_graph/etl/pipeline.py - agent_utilities/mcp/tools/ontology_tools.py - agent_utilities/mcp/tools/query_tools.py doc: ask the Knowledge Graph in plain English. An LLM - id: AU-KG.ingest.never-scan-whole-graph name: never scan the whole graph to find one node pillar: AU-KG status: live code_paths: - agent_utilities/capabilities/teams.py - agent_utilities/knowledge_graph/core/bounded_read.py - agent_utilities/knowledge_graph/kb/ingestion.py - agent_utilities/knowledge_graph/research/fleet_relevance.py - agent_utilities/knowledge_graph/security/policy_ingestor.py - agent_utilities/knowledge_graph/security/rule_ingestor.py doc: never scan the whole graph to find one node - id: AU-KG.ingest.news-finance-tech-sibling name: the news/finance/tech sibling pillar: AU-KG status: live code_paths: - agent_utilities/automation/research_pipeline.py - agent_utilities/automation/worldmodel_pipeline.py - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/knowledge_graph/research/loop_controller.py doc: the news/finance/tech sibling - id: AU-KG.ingest.no-broad-project-enumeration name: this is pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/gitlab_indexer.py doc: this is - id: AU-KG.ingest.non-blocking-graph-validation name: Non-blocking graph validation pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/pipeline/phases/validate.py doc: Non-blocking graph validation - id: AU-KG.ingest.normal-codebase-ingest-also name: AU-KG.ingest.normal-codebase-ingest-also pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/git_history.py - agent_utilities/knowledge_graph/ingestion/engine.py doc: AU-KG.ingest.normal-codebase-ingest-also - id: AU-KG.ingest.observability-queries-opik-cannot name: the observability queries Opik CANNOT do pillar: AU-KG status: live code_paths: - agent_utilities/harness/trace_analytics.py - agent_utilities/knowledge_graph/extraction/fact_extractor.py - agent_utilities/mcp/tools/analyze_suite.py doc: the observability queries Opik CANNOT do - id: AU-KG.ingest.og-metadata-enrichment name: populated only by pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/engine.py - agent_utilities/knowledge_graph/ingestion/web_fetch.py doc: populated only by - id: AU-KG.ingest.okf-type-mapping name: Resolution order pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/distillation/okf_bundle.py doc: Resolution order - id: AU-KG.ingest.openlineage-consumer name: the pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/etl/lineage.py - agent_utilities/knowledge_graph/etl/openlineage_consumer.py doc: the - id: AU-KG.ingest.over-same-tree-fan name: over the same tree and fan the pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/engine.py - agent_utilities/knowledge_graph/ingestion/repo_classifier.py doc: over the same tree and fan the - id: AU-KG.ingest.package-install-autoingest name: auto-extend pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/knowledge_graph/ingestion/package_install_ingest.py doc: auto-extend - id: AU-KG.ingest.per-agent-token-usage name: per-agent token usage over time from the engine pillar: AU-KG status: live code_paths: - agent_utilities/mcp/tools/write_ingest_tools.py doc: per-agent token usage over time from the engine - id: AU-KG.ingest.process-boundary-entrypoint name: A thin process-boundary entry point over the standardized pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/__main__.py doc: A thin process-boundary entry point over the standardized - id: AU-KG.ingest.research-connector-presets name: either is sufficient to pillar: AU-KG status: live code_paths: - agent_utilities/automation/feed_sources.py - agent_utilities/knowledge_graph/core/source_sync.py doc: either is sufficient to - id: AU-KG.ingest.role-enforcement name: role enforcement pillar: AU-KG status: live code_paths: - agent_utilities/mcp/tools/write_ingest_tools.py doc: role enforcement - id: AU-KG.ingest.rss-feed-connector name: native zero-infra RSS/Atom feed extractor and unified feed source pillar: AU-KG status: live code_paths: - agent_utilities/automation/feed_sources.py - agent_utilities/automation/worldmodel_pipeline.py - agent_utilities/core/config.py - agent_utilities/core/schedule_engine.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/mcp/tools/state_tools.py - agent_utilities/protocols/source_connectors/connectors/rss.py doc: native zero-infra RSS/Atom feed extractor and unified feed source - id: AU-KG.ingest.self-ingest name: AU-KG.ingest.self-ingest pillar: AU-KG status: live code_paths: - agent_utilities/observability/self_ingest.py doc: AU-KG.ingest.self-ingest - id: AU-KG.ingest.self-tool-surface name: the exact shape pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/engine.py - agent_utilities/mcp/kg_server.py doc: the exact shape - id: AU-KG.ingest.semantic-event-contract name: OCEL is an interchange format pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/ocel_adapter.py - agent_utilities/knowledge_graph/ingestion/semantic_event_model.py - agent_utilities/knowledge_graph/research/loop_controller.py doc: OCEL is an interchange format - id: AU-KG.ingest.skill-classification-writeback name: an operator pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/fleet_catalog_tables.py - agent_utilities/knowledge_graph/ingestion/skill_classification.py doc: an operator - id: AU-KG.ingest.skill-workflow-corpus name: ingest the universal-skills workflow corpus as pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py doc: ingest the universal-skills workflow corpus as - id: AU-KG.ingest.skill-workflow-ingestion name: Skill-Workflow Ingestion pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/ingestion/skill_workflow_ingest.py doc: Skill-Workflow Ingestion - id: AU-KG.ingest.source-id-naming-schema name: ── pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_partition.py doc: ── - id: AU-KG.ingest.source-sync-canonical name: ──────────────────────────── pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py doc: ──────────────────────────── - id: AU-KG.ingest.stable-fragment-address name: Returns fragments in document pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/domain_packs/markdown_fragmenter.py - agent_utilities/knowledge_graph/ingestion/evidence_spine.py - agent_utilities/knowledge_graph/ontology/document_processing.py - agent_utilities/mcp/tools/query_tools.py - agent_utilities/protocols/source_connectors/connectors/git_markdown.py doc: Returns fragments in document - id: AU-KG.ingest.staged name: staged pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/engine.py - agent_utilities/knowledge_graph/ingestion/staged_pipeline.py doc: staged - id: AU-KG.ingest.standardized-document-ingestion name: standardized document ingestion contract pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/models.py doc: standardized document ingestion contract - id: AU-KG.ingest.structure-verify name: confirm titles are inside pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/document_processing.py - agent_utilities/knowledge_graph/pipeline/document_ingestion.py doc: confirm titles are inside - id: AU-KG.ingest.subtask-routing-key name: a split sub-task carries its own routing key so pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/ingestion/engine.py doc: a split sub-task carries its own routing key so - id: AU-KG.ingest.then-by-its-node name: then by its node pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/standardization/standards.py doc: then by its node - id: AU-KG.ingest.toc-detection name: LLM-assisted table-of-contents detection pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/document_processing.py doc: LLM-assisted table-of-contents detection - id: AU-KG.ingest.unified-query-routing name: preserve unified query under ingestion graph routing. When pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/graph_compute.py - agent_utilities/knowledge_graph/core/ingest_routing.py - agent_utilities/knowledge_graph/core/worker_scheduler.py - agent_utilities/knowledge_graph/ingestion/engine.py - agent_utilities/mcp/kg_server.py - agent_utilities/mcp/tools/query_tools.py doc: preserve unified query under ingestion graph routing. When - id: AU-KG.ingest.universal-data-connector name: Universal DataConnector pillar: AU-KG status: live code_paths: - agent_utilities/protocols/source_connectors/connectors/graphql_document.py - agent_utilities/protocols/universal_connector.py doc: Universal DataConnector - id: AU-KG.ingest.verbatim-extraction-before-fragmenting name: AU-KG.ingest.verbatim-extraction-before-fragmenting pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/document_processing.py doc: AU-KG.ingest.verbatim-extraction-before-fragmenting - id: AU-KG.ingest.voice-model-acquisition name: Governed, digest-verified, pinned-revision pillar: AU-KG status: live code_paths: - agent_utilities/cli/__init__.py - agent_utilities/protocols/voice_supply_chain/__init__.py doc: Governed, digest-verified, pinned-revision - id: AU-KG.ingest.web-fetch-front-door name: Pluggable web fetching. One front door that both the ingestion pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/web_fetch.py doc: Pluggable web fetching. One front door that both the ingestion - id: AU-KG.ingest.wiki-delta-ingest name: Self-Curating Wiki pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/wiki_curator.py doc: Self-Curating Wiki - id: AU-KG.ingest.world-model-gate name: and the world-model gate pillar: AU-KG status: live code_paths: - agent_utilities/automation/research_pipeline.py - agent_utilities/knowledge_graph/assimilation/concept_matcher.py - agent_utilities/knowledge_graph/assimilation/ingest.py - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/models/knowledge_graph.py doc: and the world-model gate - id: AU-KG.ingest.worldmodel-gated-ingestion name: routes it to the research path — one paper arriving via pillar: AU-KG status: live code_paths: - agent_utilities/automation/worldmodel_pipeline.py - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/protocols/source_connectors/connectors/arxiv.py doc: routes it to the research path — one paper arriving via - id: AU-KG.ingest.worldview-stream name: the WORLDVIEW stream pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/task_lanes.py doc: the WORLDVIEW stream - id: AU-KG.ingest.writes-go name: concepts are already done in-unit; pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/engine.py doc: concepts are already done in-unit; - id: AU-KG.maintenance.async-knowledge-compression name: Offline/Async Knowledge Compression pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/adaptation/trace_distiller.py doc: Offline/Async Knowledge Compression - id: AU-KG.maintenance.confidence-propagation-belief-revision name: AU-KG.maintenance.confidence-propagation-belief-revision pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/adaptation/belief_revision.py - agent_utilities/knowledge_graph/research/loop_controller.py doc: AU-KG.maintenance.confidence-propagation-belief-revision - id: AU-KG.maintenance.only-no-file-cache name: engine-only, no file cache. Returns pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/adaptation/code_health.py doc: engine-only, no file cache. Returns - id: AU-KG.maintenance.periodic-code-health name: periodic code-health pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/adaptation/code_health.py doc: periodic code-health - id: AU-KG.maintenance.post-execution-feedback name: Post-execution feedback loop pillar: AU-KG status: live code_paths: - agent_utilities/graph/verification.py doc: Post-execution feedback loop - id: AU-KG.memory.ahe-record-this-base name: Decentralized Memory pillar: AU-KG status: live code_paths: - agent_utilities/harness/__init__.py - agent_utilities/harness/agentic_evolution_engine.py - agent_utilities/harness/decentralized_memory.py doc: Decentralized Memory - id: AU-KG.memory.anti-collapse name: Anti-collapse now lives in pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/memory/optimization_engine.py doc: Anti-collapse now lives in - id: AU-KG.memory.auto-similarity-memory-graph name: Lazy embedding model — defer HTTP connection to first use pillar: AU-KG status: live code_paths: - agent_utilities/core/embedding_utilities.py - agent_utilities/graph/hierarchical_planner.py - agent_utilities/harness/citation_tracker.py - agent_utilities/knowledge_graph/adaptation/experience_alignment.py - agent_utilities/knowledge_graph/enrichment/semantic.py - agent_utilities/knowledge_graph/memory/optimization_engine.py - agent_utilities/knowledge_graph/orchestration/engine_query.py - agent_utilities/knowledge_graph/pipeline/phases/embedding.py - agent_utilities/knowledge_graph/retrieval/hybrid_retriever.py - agent_utilities/knowledge_graph/retrieval/retrieval_quality.py - agent_utilities/knowledge_graph/retrieval/semantic_retrieval_engine.py - agent_utilities/mcp/tools/query_tools.py - agent_utilities/messaging/kg_ingest.py - agent_utilities/models/knowledge_graph.py doc: Lazy embedding model — defer HTTP connection to first use - id: AU-KG.memory.background-learning-engine name: Background Learning Engine pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/memory/learning_engine.py doc: Background Learning Engine - id: AU-KG.memory.checkpoint-worthiness-scoring name: Construct-then-evaluate is cheap pillar: AU-KG status: live code_paths: - agent_utilities/kvcache/rebuild_cost.py - agent_utilities/kvcache/tiering.py - agent_utilities/kvcache/worthiness.py - agent_utilities/mcp/tools/engine_surface_tools.py - agent_utilities/observability/gateway_metrics.py - agent_utilities/patterns/prioritization.py doc: Construct-then-evaluate is cheap - id: AU-KG.memory.decay-scanner-merge name: decay scanner + semantic merge pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/memory/cli.py doc: decay scanner + semantic merge - id: AU-KG.memory.drive-one-agent-native name: drive one agent-native-memory lifecycle cycle pillar: AU-KG status: live code_paths: - agent_utilities/core/schedule_engine.py - agent_utilities/knowledge_graph/memory/distillation.py - agent_utilities/knowledge_graph/memory/lifecycle.py doc: drive one agent-native-memory lifecycle cycle - id: AU-KG.memory.episodic-procedural-memory-distillation name: Episodic→procedural memory distillation pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/memory/distillation.py doc: Episodic→procedural memory distillation - id: AU-KG.memory.generation-scoped-selective-reward name: generation-scoped selective reward erasure for memory maintenance pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/adaptation/feedback.py - agent_utilities/knowledge_graph/retrieval/capability_index.py - agent_utilities/mcp/tools/write_ingest_tools.py doc: generation-scoped selective reward erasure for memory maintenance - id: AU-KG.memory.ground-truth-preamble-declaring name: Ground-Truth preamble declaring authoritative sources up front pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/memory/memory_engine.py doc: Ground-Truth preamble declaring authoritative sources up front - id: AU-KG.memory.ingestion-serving-separation name: Ingestion/serving plane separation pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_memory.py doc: Ingestion/serving plane separation - id: AU-KG.memory.kv-checkpoint-resource name: Treated as a SECURITY BOUNDARY, not a pillar: AU-KG status: live code_paths: - agent_utilities/kvcache/checkpoint.py - agent_utilities/mcp/tools/engine_surface_tools.py - agent_utilities/observability/gateway_metrics.py doc: Treated as a SECURITY BOUNDARY, not a - id: AU-KG.memory.layered-project-context name: Project-Aware Context pillar: AU-KG status: live code_paths: - agent_utilities/prompting/builder.py doc: Project-Aware Context - id: AU-KG.memory.live-data-science-mcp name: LIVE data-science-mcp train dispatch + TrainingJob status poll pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/memory/weights_distillation.py - agent_utilities/mcp/tools/analysis_tools.py doc: LIVE data-science-mcp train dispatch + TrainingJob status poll - id: AU-KG.memory.live-refreshable-artifact-models name: Live Refreshable Artifact models + bounded-JSON + safe interpolation pillar: AU-KG status: live code_paths: - agent_utilities/gateway/artifacts_api.py - agent_utilities/knowledge_graph/live_artifacts/__init__.py - agent_utilities/knowledge_graph/live_artifacts/kg_source.py - agent_utilities/knowledge_graph/live_artifacts/models.py - agent_utilities/knowledge_graph/live_artifacts/store.py - agent_utilities/server/app.py doc: Live Refreshable Artifact models + bounded-JSON + safe interpolation - id: AU-KG.memory.mementified-context name: the live block-compress-evict sawtooth pillar: AU-KG status: live code_paths: - agent_utilities/capabilities/compaction/_shared.py - agent_utilities/capabilities/memento.py - agent_utilities/knowledge_graph/memory/agent_context.py - agent_utilities/knowledge_graph/memory/lifecycle.py - agent_utilities/knowledge_graph/memory/memento_compressor.py doc: the live block-compress-evict sawtooth - id: AU-KG.memory.memento-compress-evict name: the live block-compress-evict sawtooth pillar: AU-KG status: live code_paths: - agent_utilities/capabilities/composition.py doc: the live block-compress-evict sawtooth - id: AU-KG.memory.memory-lifecycle-manager name: Unified Memory Manager pillar: AU-KG status: live code_paths: - agent_utilities/harness/evolving_memory.py doc: Unified Memory Manager - id: AU-KG.memory.memory-weights-distillation-export name: Memory→weights distillation EXPORT path pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/memory/weights_distillation.py - agent_utilities/mcp/tools/analysis_tools.py doc: Memory→weights distillation EXPORT path - id: AU-KG.memory.observational-memory-bridge name: Observational Memory Bridge pillar: AU-KG status: live code_paths: - agent_utilities/core/paths.py doc: Observational Memory Bridge - id: AU-KG.memory.persistent-self-model-owl name: Persistent Self-Model with OWL Integration pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/memory_retriever.py doc: Persistent Self-Model with OWL Integration - id: AU-KG.memory.provides-real-ephemeral-one name: provides a real ephemeral one, so an unreachable pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/memory/timeseries/__init__.py - agent_utilities/knowledge_graph/memory/timeseries/engine_backend.py - agent_utilities/numeric/__init__.py doc: provides a real ephemeral one, so an unreachable - id: AU-KG.memory.refresh-per-session-memento name: refresh the per-session memento cache in this SAME background pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/memory/session_memento_cache.py - agent_utilities/messaging/router.py - agent_utilities/orchestration/agent_runner.py - agent_utilities/orchestration/session_continuity.py doc: refresh the per-session memento cache in this SAME background - id: AU-KG.memory.refresh-service name: Refresh service pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/live_artifacts/refresh.py doc: Refresh service - id: AU-KG.memory.rlm-memory-extraction name: RLM Memory Extraction Signature pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/memory/rlm_memory.py doc: RLM Memory Extraction Signature - id: AU-KG.memory.semantic-response-cache name: the freshness half of the cache contract pillar: AU-KG status: live code_paths: - agent_utilities/caching/freshness.py - agent_utilities/caching/semantic_cache.py - agent_utilities/harness/trace_backend.py - agent_utilities/knowledge_graph/retrieval/context_compiler_serving.py - agent_utilities/models/knowledge_graph.py - agent_utilities/observability/gateway_metrics.py doc: the freshness half of the cache contract - id: AU-KG.memory.targeted-add-update-delete name: targeted ADD/UPDATE/DELETE learner pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/memory/cli.py doc: targeted ADD/UPDATE/DELETE learner - id: AU-KG.memory.team-startup-context name: Team-Specific Startup Context pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/memory/memory_engine.py doc: Team-Specific Startup Context - id: AU-KG.memory.tiered-memory-caching name: routes skill evolution through the single graph-native pillar: AU-KG status: live code_paths: - agent_utilities/__init__.py - agent_utilities/capabilities/eviction.py - agent_utilities/core/chat_persistence.py - agent_utilities/graph/_router_impl.py - agent_utilities/graph/parallel_engine.py - agent_utilities/graph/routing/enrichers/self_model.py - agent_utilities/graph/routing/strategies/fast_path.py - agent_utilities/graph/routing/strategies/workflow_context.py - agent_utilities/graph/workspace_attention.py - agent_utilities/harness/__init__.py - agent_utilities/harness/agentic_evolution_engine.py - agent_utilities/knowledge_graph/core/agents_md.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/core/model_display.py - agent_utilities/knowledge_graph/ingestion/engine.py - agent_utilities/knowledge_graph/memory/__init__.py - agent_utilities/knowledge_graph/memory/agent_context.py - agent_utilities/knowledge_graph/memory/cli.py - agent_utilities/knowledge_graph/memory/memory_engine.py - agent_utilities/knowledge_graph/memory/observer.py - agent_utilities/knowledge_graph/memory/optimization_engine.py - agent_utilities/knowledge_graph/retrieval/budget.py - agent_utilities/knowledge_graph/retrieval/context_compiler.py - agent_utilities/knowledge_graph/retrieval/hybrid_retriever.py - agent_utilities/messaging/kg_ingest.py - agent_utilities/messaging/router.py - agent_utilities/models/knowledge_graph.py doc: routes skill evolution through the single graph-native - id: AU-KG.memory.time-series-lives-one name: time-series lives on the one engine authority pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/memory/timeseries/__init__.py - agent_utilities/knowledge_graph/memory/timeseries/engine_backend.py doc: time-series lives on the one engine authority - id: AU-KG.memory.unified-memory-crud-core name: the unified memory-CRUD core. graph_memory pillar: AU-KG status: live code_paths: - agent_utilities/mcp/tools/engine_surface_tools.py doc: the unified memory-CRUD core. graph_memory - id: AU-KG.memory.universal-knowledge-assimilation name: Universal Knowledge Assimilation pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/kb/knowledge_classifier.py - agent_utilities/knowledge_graph/kb/x_workflows.py doc: Universal Knowledge Assimilation - id: AU-KG.mining.dsm-forecast-delegation name: the deep-learning / heavy-Python family the pillar: AU-KG status: live code_paths: - agent_utilities/mcp/kg_server.py - agent_utilities/mcp/tools/engine_surface_tools.py - agent_utilities/media/sidecar_contract.py - agent_utilities/media/sidecar_delegate.py doc: the deep-learning / heavy-Python family the - id: AU-KG.mining.foldback-typed-nodes name: Best-effort — never raises, since a foldback pillar: AU-KG status: live code_paths: - agent_utilities/mcp/tools/engine_surface_tools.py doc: Best-effort — never raises, since a foldback - id: AU-KG.mining.governed-neural-layer name: KG-6.6 pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/neural/__init__.py - agent_utilities/knowledge_graph/neural/candidate_generation.py - agent_utilities/knowledge_graph/neural/embedding_store.py - agent_utilities/knowledge_graph/neural/evaluation.py - agent_utilities/knowledge_graph/neural/governance.py - agent_utilities/knowledge_graph/neural/models.py - agent_utilities/knowledge_graph/neural/probabilistic_completion.py doc: KG-6.6 - id: AU-KG.mining.governed-perspective-flattening name: classical single-case pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/event_log_adapter.py - agent_utilities/mcp/tools/engine_surface_tools.py doc: classical single-case - id: AU-KG.mining.incremental-object-centric-derivation name: object-centric pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/object_centric_derivation.py - agent_utilities/mcp/tools/engine_surface_tools.py doc: object-centric - id: AU-KG.mining.ocel-lossless-roundtrip name: the inverse of pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/semantic_event_model.py doc: the inverse of - id: AU-KG.mining.process-conformance-checking name: the graph-writeback pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/process_conformance.py - agent_utilities/mcp/tools/engine_surface_tools.py doc: the graph-writeback - id: AU-KG.ontology.activation-fails-closed name: AU-KG.ontology.activation-fails-closed pillar: AU-KG status: live code_paths: - agent_utilities/data_prep/connector_activation.py doc: AU-KG.ontology.activation-fails-closed - id: AU-KG.ontology.authoritative-tbox name: opt-in daemon tick that pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py doc: opt-in daemon tick that - id: AU-KG.ontology.batch-actions-executor name: it sets a review annotation on a pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/actions/builtins.py - agent_utilities/knowledge_graph/actions/dispatch.py - agent_utilities/knowledge_graph/actions/executor.py - agent_utilities/knowledge_graph/actions/models.py - agent_utilities/protocols/source_connectors/connectors/mcp_tool.py doc: it sets a review annotation on a - id: AU-KG.ontology.batch-incremental-sync-live name: batch/incremental sync of the live search index from source nodes, report staleness, or reindex stale objects pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/facade.py - agent_utilities/knowledge_graph/ontology/__init__.py - agent_utilities/knowledge_graph/ontology/indexing/__init__.py - agent_utilities/knowledge_graph/ontology/indexing/funnel.py - agent_utilities/knowledge_graph/ontology/indexing/staleness.py - agent_utilities/mcp/tools/ontology_tools.py doc: batch/incremental sync of the live search index from source nodes, report staleness, or reindex stale objects - id: AU-KG.ontology.capability-card-backfill-lane name: OWL capability-card backfill is its OWN throughput lane pillar: AU-KG status: live code_paths: - agent_utilities/core/schedule_engine.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/core/task_lanes.py doc: OWL capability-card backfill is its OWN throughput lane - id: AU-KG.ontology.capability-node-aliases-lexical name: capability-node aliases the lexical gate matches; pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine.py - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/knowledge_graph/ontology/connector_manifest_gate.py doc: capability-node aliases the lexical gate matches; - id: AU-KG.ontology.catalogue-browse name: coverage row pillar: AU-KG status: live code_paths: - agent_utilities/gateway/ontology_api.py doc: coverage row - id: AU-KG.ontology.classification-claim-multi-category name: AU-KG.ontology.classification-claim-multi-category pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/classification_claims.py - agent_utilities/mcp/tools/ontology_tools.py doc: AU-KG.ontology.classification-claim-multi-category - id: AU-KG.ontology.classification-claim-promotion-lifecycle name: AU-KG.ontology.classification-claim-promotion-lifecycle pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/classification_claims.py doc: AU-KG.ontology.classification-claim-promotion-lifecycle - id: AU-KG.ontology.conformance-check name: the function the A3 functions runtime / object queries call pillar: AU-KG status: live code_paths: - agent_utilities/gateway/ontology_api.py - agent_utilities/knowledge_graph/ontology/__init__.py - agent_utilities/knowledge_graph/ontology/interfaces.py - agent_utilities/knowledge_graph/ontology/object_set.py - agent_utilities/knowledge_graph/standardization/standards.py - agent_utilities/mcp/tools/ontology_tools.py - agent_utilities/mcp/tools/state_tools.py doc: the function the A3 functions runtime / object queries call - id: AU-KG.ontology.connector-agnostic-proposal name: connector-agnostic over the ontology; propose-only. Reuses pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/distillation/skill_synthesizer.py - agent_utilities/knowledge_graph/governance_import.py - agent_utilities/knowledge_graph/ontology/ops_causal_crosswalk.py - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/models/knowledge_graph.py doc: connector-agnostic over the ontology; propose-only. Reuses - id: AU-KG.ontology.connector-manifest-gate name: this module is the pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/knowledge_graph/ontology/connector_manifest_gate.py doc: this module is the - id: AU-KG.ontology.connector-manifest-schema name: the LeanIX pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/connector_manifest.py doc: the LeanIX - id: AU-KG.ontology.connector-skill-proposal-shapes name: connector→skill synthesis proposal shapes pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/interfaces.py doc: connector→skill synthesis proposal shapes - id: AU-KG.ontology.connector-typed-actions name: AU-KG.ontology.connector-typed-actions pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/connector_manifest.py doc: AU-KG.ontology.connector-typed-actions - id: AU-KG.ontology.cross-source-identity-proposal name: AU-KG.ontology.cross-source-identity-proposal pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/classification_claims.py doc: AU-KG.ontology.cross-source-identity-proposal - id: AU-KG.ontology.default-runtime-bound-import name: a default runtime bound to the import-populated registry, so pillar: AU-KG status: live code_paths: - agent_utilities/gateway/ontology_api.py - agent_utilities/knowledge_graph/ontology/__init__.py - agent_utilities/knowledge_graph/ontology/functions/__init__.py - agent_utilities/knowledge_graph/ontology/functions/objects.py - agent_utilities/knowledge_graph/ontology/functions/registry.py - agent_utilities/knowledge_graph/ontology/functions/runtime.py - agent_utilities/mcp/tools/ontology_tools.py - agent_utilities/mcp/tools/state_tools.py doc: a default runtime bound to the import-populated registry, so - id: AU-KG.ontology.derived-compatibility-band name: the compatibility band an pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/integrations/connector_source_attestation.py doc: the compatibility band an - id: AU-KG.ontology.derived-property-registry name: import-populated registry + a default engine bound to it and pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/__init__.py - agent_utilities/knowledge_graph/ontology/derived_properties.py - agent_utilities/mcp/tools/ontology_tools.py - agent_utilities/mcp/tools/state_tools.py doc: import-populated registry + a default engine bound to it and - id: AU-KG.ontology.descriptive-process-world-gains name: the descriptive process world gains step-level shape pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/extractors/aris.py - agent_utilities/knowledge_graph/enrichment/extractors/camunda.py - agent_utilities/knowledge_graph/enrichment/graph_collapse.py - agent_utilities/knowledge_graph/enrichment/models.py doc: the descriptive process world gains step-level shape - id: AU-KG.ontology.do-not-auto-merge name: a human-reviewed proposal only pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/extraction/schema_discovery.py - agent_utilities/mcp/tools/ontology_tools.py - agent_utilities/orchestration/action_policy.py doc: a human-reviewed proposal only - id: AU-KG.ontology.edit-ledger-writeback name: the write-back leg of the edit ledger. Sinks are registered pillar: AU-KG status: live code_paths: - agent_utilities/gateway/ontology_api.py - agent_utilities/knowledge_graph/ontology/__init__.py - agent_utilities/knowledge_graph/ontology/edits/__init__.py - agent_utilities/knowledge_graph/ontology/edits/ledger.py - agent_utilities/knowledge_graph/ontology/edits/revert.py - agent_utilities/knowledge_graph/ontology/edits/writeback.py - agent_utilities/mcp/tools/ontology_tools.py doc: the write-back leg of the edit ledger. Sinks are registered - id: AU-KG.ontology.emits-database-ontology-entities name: SQL DDL extraction pillar: AU-KG status: live code_paths: - agent_utilities/models/knowledge_graph.py doc: SQL DDL extraction - id: AU-KG.ontology.evolution-governed-loop name: AU-KG.ontology.evolution-governed-loop pillar: AU-KG status: live code_paths: - agent_utilities/orchestration/action_policy.py doc: AU-KG.ontology.evolution-governed-loop - id: AU-KG.ontology.external-graph-profiling name: Profile / imprint / ontology-map a registered external graph pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/connection_profiler.py doc: Profile / imprint / ontology-map a registered external graph - id: AU-KG.ontology.graph-integrity-validator name: Graph Integrity Validator pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/security/graph_validator.py doc: Graph Integrity Validator - id: AU-KG.ontology.harness-gate name: AU-KG.ontology.harness-gate pillar: AU-KG status: live code_paths: - agent_utilities/harness/harness_gate.py doc: AU-KG.ontology.harness-gate - id: AU-KG.ontology.import-export-rest-surface name: coverage row pillar: AU-KG status: live code_paths: - agent_utilities/gateway/ontology_api.py doc: coverage row - id: AU-KG.ontology.inference-profile-implementers name: InferenceProfile + SamplingConfigurable ontology interfaces and a first-class Model object type projecting configured models and their tuned sampling profiles to OWL pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/interfaces.py - agent_utilities/models/knowledge_graph.py - agent_utilities/models/model_registry.py doc: InferenceProfile + SamplingConfigurable ontology interfaces and a first-class Model object type projecting configured models and their tuned sampling profiles to OWL - id: AU-KG.ontology.integrity-bootstrap name: The live pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/readiness.py doc: The live - id: AU-KG.ontology.kg-2 name: AU-KG.ontology.kg-2 pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/research_objects.py doc: AU-KG.ontology.kg-2 - id: AU-KG.ontology.kg-3 name: CONCEPT pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/etl/lineage.py - agent_utilities/mcp/tools/ontology_tools.py doc: CONCEPT - id: AU-KG.ontology.knowledge-packs name: Knowledge Packs pillar: AU-KG status: live code_paths: - agent_utilities/models/knowledge_pack.py doc: Knowledge Packs - id: AU-KG.ontology.kyle-insider-stealth-surveillance name: Kyle insider/stealth surveillance signal ontology pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/finance_objects.py doc: Kyle insider/stealth surveillance signal ontology - id: AU-KG.ontology.link-type-pivot name: search/filter/search_around/pivot/aggregate and union/intersect/subtract over Foundry-style object sets. action= pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/__init__.py - agent_utilities/knowledge_graph/ontology/object_set.py - agent_utilities/mcp/tools/ontology_tools.py doc: search/filter/search_around/pivot/aggregate and union/intersect/subtract over Foundry-style object sets. action= - id: AU-KG.ontology.model-profile-graph-resource name: only fields the ModelDefinition actually pillar: AU-KG status: live code_paths: - agent_utilities/gateway/ontology_api.py - agent_utilities/mcp/tools/ontology_tools.py - agent_utilities/models/knowledge_graph.py - agent_utilities/models/model_profile.py - agent_utilities/models/model_registry.py doc: only fields the ModelDefinition actually - id: AU-KG.ontology.node-type-casing-convergence name: normalizes a node pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py doc: normalizes a node - id: AU-KG.ontology.object-path-finder name: finds the shortest path between two specific object ids and returns the hop-by-hop relationship chain — the object-agnostic generalization of the existing pillar: AU-KG status: live code_paths: - agent_utilities/gateway/ontology_api.py - agent_utilities/knowledge_graph/ontology/object_path.py - agent_utilities/mcp/tools/ontology_tools.py doc: finds the shortest path between two specific object ids and returns the hop-by-hop relationship chain — the object-agnostic generalization of the existing - id: AU-KG.ontology.one-source name: One source→ pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/etl/__init__.py - agent_utilities/knowledge_graph/etl/pipeline.py - agent_utilities/mcp/tools/ontology_tools.py doc: One source→ - id: AU-KG.ontology.ontology-action-system name: and derived-properties consume pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/actions/__init__.py - agent_utilities/knowledge_graph/actions/builtins.py - agent_utilities/knowledge_graph/actions/executor.py - agent_utilities/knowledge_graph/actions/models.py - agent_utilities/knowledge_graph/actions/registry.py - agent_utilities/knowledge_graph/ontology/functions/__init__.py - agent_utilities/knowledge_graph/ontology/functions/runtime.py doc: and derived-properties consume - id: AU-KG.ontology.ontology-driven-reasoning name: reason over the axioms pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py doc: reason over the axioms - id: AU-KG.ontology.ontology-property-types name: bridges the ontology type vocabulary onto the exact pillar: AU-KG status: live code_paths: - agent_utilities/gateway/ontology_api.py - agent_utilities/knowledge_graph/ontology/__init__.py - agent_utilities/knowledge_graph/ontology/property_types.py - agent_utilities/mcp/tools/ontology_tools.py - agent_utilities/mcp/tools/state_tools.py doc: bridges the ontology type vocabulary onto the exact - id: AU-KG.ontology.ops-causal-crosswalk name: AU-KG.ontology.ops-causal-crosswalk pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/ops_causal_crosswalk.py doc: AU-KG.ontology.ops-causal-crosswalk - id: AU-KG.ontology.optimistic-concurrency-object-property name: optimistic-concurrency for object property edits pillar: AU-KG status: live code_paths: - agent_utilities/mcp/tools/ontology_tools.py doc: optimistic-concurrency for object property edits - id: AU-KG.ontology.optional-populated-from name: Optional; populated from the pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/capability_index.py doc: Optional; populated from the - id: AU-KG.ontology.owl-screen-bridge name: AU-KG.ontology.owl-screen-bridge pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/graph_compute.py doc: AU-KG.ontology.owl-screen-bridge - id: AU-KG.ontology.pack-identity-rules name: and threaded in here as plain pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/assimilation/identity_candidates.py - agent_utilities/models/schema_pack.py doc: and threaded in here as plain - id: AU-KG.ontology.pack-owl-closure name: reuses the pack-driven OWL closure notion. The pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/links.py - agent_utilities/models/schema_pack.py - agent_utilities/models/schema_packs/research.py doc: reuses the pack-driven OWL closure notion. The - id: AU-KG.ontology.policy-external-sync name: AU-KG.ontology.policy-external-sync pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/permissioning_external_sync.py doc: AU-KG.ontology.policy-external-sync - id: AU-KG.ontology.populated-at-import-real-3 name: populated at import with real built-in standards, never empty pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/__init__.py - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/knowledge_graph/standardization/__init__.py - agent_utilities/knowledge_graph/standardization/cohorts.py - agent_utilities/knowledge_graph/standardization/consolidation.py - agent_utilities/knowledge_graph/standardization/drift.py - agent_utilities/knowledge_graph/standardization/standards.py - agent_utilities/mcp/tools/ontology_tools.py - agent_utilities/models/knowledge_graph.py doc: populated at import with real built-in standards, never empty - id: AU-KG.ontology.redact-object-materialize-restricted name: redact an object, materialize a restricted view, or attach a mandatory marking. Actor is resolved from the ambient context — never from caller-supplied clearance pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/facade.py - agent_utilities/knowledge_graph/ontology/permissioning.py - agent_utilities/knowledge_graph/retrieval/context_compiler.py - agent_utilities/mcp/tools/ontology_tools.py doc: redact an object, materialize a restricted view, or attach a mandatory marking. Actor is resolved from the ambient context — never from caller-supplied clearance - id: AU-KG.ontology.registry-derived-server-alias name: AU-KG.ontology.registry-derived-server-alias pillar: AU-KG status: live code_paths: - agent_utilities/orchestration/fleet_reconciler.py doc: AU-KG.ontology.registry-derived-server-alias - id: AU-KG.ontology.release-key-rotation name: the release trust anchor lives in pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/ontology_integrity.py - agent_utilities/security/cli_secrets.py - agent_utilities/security/secrets_client.py doc: the release trust anchor lives in - id: AU-KG.ontology.repository-provenance-snapshot name: AU-KG.ontology.repository-provenance-snapshot pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/repository_provenance.py doc: AU-KG.ontology.repository-provenance-snapshot - id: AU-KG.ontology.sampling-profile-coupling name: LLM inference sampling knobs temperature top_p top_k min_p repetition_penalty max_tokens and penalties as SHACL-bounded ontology value types plus the two-surface sampling-profile tool pillar: AU-KG status: live code_paths: - agent_utilities/agent/sampling_profile.py - agent_utilities/knowledge_graph/ontology/value_types.py doc: LLM inference sampling knobs temperature top_p top_k min_p repetition_penalty max_tokens and penalties as SHACL-bounded ontology value types plus the two-surface sampling-profile tool - id: AU-KG.ontology.schema-graph-visualization name: closes the gap analysed pillar: AU-KG status: live code_paths: - agent_utilities/gateway/ontology_api.py - agent_utilities/knowledge_graph/ontology/schema_graph.py - agent_utilities/mcp/tools/ontology_tools.py doc: closes the gap analysed - id: AU-KG.ontology.schema-pack-lifecycle-audit name: Schema-Pack Lifecycle and Audit pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine.py - agent_utilities/models/schema_pack_audit.py - agent_utilities/models/schema_pack_loader.py doc: Schema-Pack Lifecycle and Audit - id: AU-KG.ontology.schema-packs name: Schema Packs pillar: AU-KG status: live code_paths: - agent_utilities/models/schema_pack.py - agent_utilities/models/schema_packs/__init__.py doc: Schema Packs - id: AU-KG.ontology.semantic-subsumption name: OWL-Driven Semantic Subsumption pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/semantic_subsumption.py doc: OWL-Driven Semantic Subsumption - id: AU-KG.ontology.single-source-full-drain name: a single-source FULL drain of a LARGE corpus must NOT run inline pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/chunked_drain.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/knowledge_graph/core/task_lanes.py - agent_utilities/mcp/tools/ontology_tools.py doc: a single-source FULL drain of a LARGE corpus must NOT run inline - id: AU-KG.ontology.standalone-generation name: skips the live-ontology/synonym pillar: AU-KG status: live code_paths: - agent_utilities/gateway/ontology_api.py - agent_utilities/knowledge_graph/extraction/schema_discovery.py doc: skips the live-ontology/synonym - id: AU-KG.ontology.style-lint name: flags interface/property naming-convention pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/style_lint.py - agent_utilities/mcp/tools/ontology_tools.py doc: flags interface/property naming-convention - id: AU-KG.ontology.submission-criteria-gate name: Palantir submission-criteria gate. An action with no pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/actions/effects.py doc: Palantir submission-criteria gate. An action with no - id: AU-KG.ontology.supply-chain-integrity name: fleet-wide guarantee that a generated/ pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/ontology_integrity.py doc: fleet-wide guarantee that a generated/ - id: AU-KG.ontology.typed-ontology-links-binding name: Typed ontology links binding Model/InferenceProfile to TaskClass/Role/Agent pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/links.py - agent_utilities/models/knowledge_graph.py doc: Typed ontology links binding Model/InferenceProfile to TaskClass/Role/Agent - id: AU-KG.ontology.value-type-shacl-load name: the live consumer hook. Writes the combined SHACL document pillar: AU-KG status: live code_paths: - agent_utilities/gateway/ontology_api.py - agent_utilities/knowledge_graph/ontology/__init__.py - agent_utilities/knowledge_graph/ontology/value_types.py - agent_utilities/mcp/tools/ontology_tools.py - agent_utilities/mcp/tools/state_tools.py doc: the live consumer hook. Writes the combined SHACL document - id: AU-KG.ontology.vendor-writeback-action name: vendor write-back via governed ontology Actions pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/actions/fleet_writeback.py doc: vendor write-back via governed ontology Actions - id: AU-KG.ontology.verified-by-implemented-by name: CONTAINS/VERIFIED_BY/GROUNDED_IN/ pillar: AU-KG status: live code_paths: - agent_utilities/gateway/research_api.py - agent_utilities/knowledge_graph/ontology/interfaces.py - agent_utilities/knowledge_graph/ontology/links.py - agent_utilities/knowledge_graph/ontology/value_types.py - agent_utilities/knowledge_graph/research/ara/artifact.py - agent_utilities/knowledge_graph/research/ara/compiler.py - agent_utilities/knowledge_graph/research/ara/exploration.py - agent_utilities/knowledge_graph/research/ara/live_manager.py - agent_utilities/knowledge_graph/research/ara/seal.py - agent_utilities/knowledge_graph/research/ara/service.py - agent_utilities/models/knowledge_graph.py doc: CONTAINS/VERIFIED_BY/GROUNDED_IN/ - id: AU-KG.query.adore-concept-expansion name: ADORE, with CONCEPT pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/orchestration/engine_query.py - agent_utilities/mcp/tools/query_tools.py doc: ADORE, with CONCEPT - id: AU-KG.query.as-of-instant-filter name: optional ISO-8601 instant. When set, rows are filtered to pillar: AU-KG status: live code_paths: - agent_utilities/mcp/tools/query_tools.py doc: optional ISO-8601 instant. When set, rows are filtered to - id: AU-KG.query.ask-gateway-rest-twin name: ask the Knowledge Graph in plain English, planned by pillar: AU-KG status: live code_paths: - agent_utilities/core/event_loop.py - agent_utilities/knowledge_graph/core/nl_planner.py - agent_utilities/knowledge_graph/core/nl_query.py - agent_utilities/knowledge_graph/orchestration/data_analyst.py - agent_utilities/mcp/tools/intent_tools.py - agent_utilities/mcp/tools/query_tools.py doc: ask the Knowledge Graph in plain English, planned by - id: AU-KG.query.au-engine-execution-path name: the AU→engine execution path for the engine pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/orchestration/engine_query.py - agent_utilities/mcp/tools/engine_tools.py - agent_utilities/mcp/tools/query_tools.py doc: the AU→engine execution path for the engine - id: AU-KG.query.chronoid-fits-residual-quantization name: ChronoID. Fits a residual-quantization codebook on the pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/orchestration/engine_query.py - agent_utilities/knowledge_graph/retrieval/generative_recommender.py - agent_utilities/knowledge_graph/retrieval/temporal_semantic_id.py - agent_utilities/mcp/tools/query_tools.py doc: ChronoID. Fits a residual-quantization codebook on the - id: AU-KG.query.cypher-scope-variable-detection name: AU-KG.query.cypher-scope-variable-detection pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/cypher_scope_vars.py doc: AU-KG.query.cypher-scope-variable-detection - id: AU-KG.query.data-gateway-rest-twin name: answer a DATA question over the Knowledge Graph with a pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/orchestration/data_analyst.py - agent_utilities/mcp/tools/query_tools.py doc: answer a DATA question over the Knowledge Graph with a - id: AU-KG.query.knowledge-stream-consumer name: additive; a build/transport without the pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine.py - agent_utilities/knowledge_graph/core/epistemic_row.py - agent_utilities/knowledge_graph/core/graph_compute.py - agent_utilities/knowledge_graph/core/knowledge_stream.py - agent_utilities/knowledge_graph/facade.py - agent_utilities/mcp/tools/compliance_tools.py doc: additive; a build/transport without the - id: AU-KG.query.node-link-projection name: run the SAME query pillar: AU-KG status: live code_paths: - agent_utilities/mcp/tools/query_tools.py doc: run the SAME query - id: AU-KG.query.object-graph-mapper name: Knowledge Graph Object-Graph Mapper pillar: AU-KG status: live code_paths: - agent_utilities/automation/research_pipeline.py - agent_utilities/core/cognitive_scheduler.py - agent_utilities/core/registry/kg_adapter.py - agent_utilities/core/registry/package_adapter.py - agent_utilities/domains/government/__init__.py - agent_utilities/domains/government/models.py - agent_utilities/graph/reward_decomposition.py - agent_utilities/graph/workspace_attention.py - agent_utilities/harness/variant_pool.py - agent_utilities/knowledge_graph/__main__.py - agent_utilities/knowledge_graph/adaptation/research_artifacts.py - agent_utilities/knowledge_graph/backends/contrib/falkordb_backend.py - agent_utilities/knowledge_graph/backends/contrib/ladybug_backend.py - agent_utilities/knowledge_graph/backends/contrib/neo4j_backend.py - agent_utilities/knowledge_graph/backends/epistemic_graph_backend.py - agent_utilities/knowledge_graph/core/codemaps.py - agent_utilities/knowledge_graph/core/context_builder.py - agent_utilities/knowledge_graph/core/graph_compute.py - agent_utilities/knowledge_graph/core/maintainer.py - agent_utilities/knowledge_graph/core/ogm.py - agent_utilities/knowledge_graph/core/source_resolver.py - agent_utilities/knowledge_graph/kb/extractor.py - agent_utilities/knowledge_graph/kb/ingestion.py - agent_utilities/knowledge_graph/kb/parser.py - agent_utilities/knowledge_graph/maintenance/document_cleanup.py - agent_utilities/knowledge_graph/memory/strategies/heavy_thinking_cache.py - agent_utilities/knowledge_graph/orchestration/engine_query.py - agent_utilities/knowledge_graph/pipeline/document_deletion.py - agent_utilities/knowledge_graph/pipeline/document_ingestion.py - agent_utilities/knowledge_graph/pipeline/document_update.py - agent_utilities/knowledge_graph/pipeline/phases/parse.py - agent_utilities/knowledge_graph/pipeline/phases/sync.py - agent_utilities/knowledge_graph/retrieval/memory_retriever.py - agent_utilities/models/codemap.py - agent_utilities/models/knowledge_base.py - agent_utilities/models/knowledge_graph.py - agent_utilities/models/schema_definition.py - agent_utilities/tools/kg_share_tools.py - agent_utilities/tools/knowledge_tools.py doc: Knowledge Graph Object-Graph Mapper - id: AU-KG.query.query-aggregation name: an aggregation under the implicit content-graph pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/nl_planner.py - agent_utilities/knowledge_graph/orchestration/engine_query.py - agent_utilities/mcp/tools/query_tools.py doc: an aggregation under the implicit content-graph - id: AU-KG.query.raw-python name: or a raw Python pillar: AU-KG status: live code_paths: - agent_utilities/gateway/graph_api.py - agent_utilities/knowledge_graph/orchestration/engine_query.py - agent_utilities/mcp/tools/graph_tools.py doc: or a raw Python - id: AU-KG.query.read-only-sql-over name: read-only SQL over the KG via the engine pillar: AU-KG status: live code_paths: - agent_utilities/mcp/tools/query_tools.py doc: read-only SQL over the KG via the engine - id: AU-KG.query.readiness-canary-snapshot name: AU-KG.query.readiness-canary-snapshot pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/readiness.py doc: AU-KG.query.readiness-canary-snapshot - id: AU-KG.query.register-each-user-table name: does the pillar: AU-KG status: live code_paths: - agent_utilities/core/chat_persistence.py doc: does the - id: AU-KG.query.single-governed-read-path name: the async read sibling of pillar: AU-KG status: live code_paths: - agent_utilities/graph/client.py - agent_utilities/knowledge_graph/core/graph_compute.py - agent_utilities/knowledge_graph/orchestration/engine_federation.py - agent_utilities/knowledge_graph/retrieval/graph_engineering.py - agent_utilities/rlm/gepa.py doc: the async read sibling of - id: AU-KG.query.skip-assimilated-papers name: Skip assimilated papers pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/orchestration/engine_query.py doc: Skip assimilated papers - id: AU-KG.query.top-nodes-by-degree name: the top nodes by degree + edges pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/code_metrics.py doc: the top nodes by degree + edges - id: AU-KG.query.typed-rest-schemas name: these routes are mounted in pillar: AU-KG status: live code_paths: - agent_utilities/gateway/schemas/__init__.py - agent_utilities/gateway/schemas/graph_analyze.py doc: these routes are mounted in - id: AU-KG.query.unified-capability-catalog name: one capability-shaped call across pillar: AU-KG status: live code_paths: - agent_utilities/mcp/tools/query_tools.py doc: one capability-shaped call across - id: AU-KG.query.vendor-agnostic-traversal name: standardized so an atomic skill gets the SAME enrichment level pillar: AU-KG status: live code_paths: - agent_utilities/__init__.py - agent_utilities/core/background_throttle.py - agent_utilities/core/config.py - agent_utilities/core/sessions.py - agent_utilities/core/workspace_config.py - agent_utilities/gateway/graph_api.py - agent_utilities/knowledge_graph/assimilation/__init__.py - agent_utilities/knowledge_graph/assimilation/breadth_ingest.py - agent_utilities/knowledge_graph/assimilation/dedup.py - agent_utilities/knowledge_graph/assimilation/gap_analysis.py - agent_utilities/knowledge_graph/assimilation/ingest.py - agent_utilities/knowledge_graph/assimilation/ledger.py - agent_utilities/knowledge_graph/assimilation/pilot.py - agent_utilities/knowledge_graph/assimilation/plan_synthesis.py - agent_utilities/knowledge_graph/assimilation/synergy.py - agent_utilities/knowledge_graph/backends/base.py - agent_utilities/knowledge_graph/backends/contrib/ladybug_backend.py - agent_utilities/knowledge_graph/backends/cypher_transpiler.py - agent_utilities/knowledge_graph/backends/postgresql_backend.py - agent_utilities/knowledge_graph/core/company_brain.py - agent_utilities/knowledge_graph/core/event_backend.py - agent_utilities/knowledge_graph/core/kg_versioning.py - agent_utilities/knowledge_graph/core/source_partition.py - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/knowledge_graph/distillation/skill_graph_distiller.py - agent_utilities/knowledge_graph/enrichment/execute.py - agent_utilities/knowledge_graph/ingestion/engine.py - agent_utilities/knowledge_graph/ingestion/paper_links.py - agent_utilities/knowledge_graph/memory/agent_context.py - agent_utilities/knowledge_graph/pipeline/__init__.py - agent_utilities/knowledge_graph/pipeline/phases/__init__.py - agent_utilities/knowledge_graph/pipeline/phases/embedding.py - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/models/schema_packs/finance.py doc: standardized so an atomic skill gets the SAME enrichment level - id: AU-KG.research.best-effort-lightweight-never name: dispatches through the same research_artifact MCP tool pillar: AU-KG status: live code_paths: - agent_utilities/gateway/graph_api.py - agent_utilities/knowledge_graph/research/ara/__init__.py - agent_utilities/knowledge_graph/research/ara/reasoning_driver.py - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/mcp/tools/state_tools.py doc: dispatches through the same research_artifact MCP tool - id: AU-KG.research.close-distill-develop-seam name: Fix the distill→develop DEAD-END pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/knowledge_graph/research/spec_proposals.py - agent_utilities/mcp/tools/state_tools.py doc: Fix the distill→develop DEAD-END - id: AU-KG.research.contradiction-agreement-blind-spot name: Contradiction / agreement / blind-spot as first-class KG structures pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/research/perspective.py doc: Contradiction / agreement / blind-spot as first-class KG structures - id: AU-KG.research.default-so-every-cycle name: default-ON so every cycle pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/assimilation/feature_matrix.py - agent_utilities/knowledge_graph/research/loop_controller.py doc: default-ON so every cycle - id: AU-KG.research.evolutionstate-live-surface-per name: EvolutionState live surface + per-stage progress beacon. The pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/research/evolution_state.py - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/mcp/tools/state_tools.py doc: EvolutionState live surface + per-stage progress beacon. The - id: AU-KG.research.explicit-node-node-contradiction name: over pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/adaptation/contradiction_detector.py - agent_utilities/knowledge_graph/research/night_shift.py doc: over - id: AU-KG.research.okf-bundle-conformance name: make the pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/distillation/okf_bundle.py - agent_utilities/knowledge_graph/distillation/skill_graph_pipeline.py doc: make the - id: AU-KG.research.okf-overlay-mode name: the *permissive consumer* half of the pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/distillation/okf_bundle.py doc: the *permissive consumer* half of the - id: AU-KG.research.peer-review-self-critique name: Peer-review / self-critique closing the loop pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/research/perspective.py doc: Peer-review / self-critique closing the loop - id: AU-KG.research.perspectival-inquiry name: Perspectival inquiry engine pillar: AU-KG status: live code_paths: - agent_utilities/gateway/research_api.py - agent_utilities/knowledge_graph/research/ara/service.py - agent_utilities/knowledge_graph/research/perspective.py - agent_utilities/knowledge_graph/research/search.py - agent_utilities/mcp/tools/state_tools.py doc: Perspectival inquiry engine - id: AU-KG.research.provenance name: provenance pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/research/cohort.py doc: provenance - id: AU-KG.research.research-intelligence-loop name: AU-KG.research.research-intelligence-loop pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/knowledge_graph/research/research_intelligence_engine.py doc: AU-KG.research.research-intelligence-loop - id: AU-KG.research.research-orchestration name: Research Orchestration Integration pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/orchestration/research_orchestrator.py doc: Research Orchestration Integration - id: AU-KG.research.research-pipeline-runner name: Generates actionable LLM artifacts from KG-ingested research pillar: AU-KG status: live code_paths: - agent_utilities/automation/__init__.py - agent_utilities/automation/research_pipeline.py - agent_utilities/core/checkpoint/manager.py - agent_utilities/domains/finance/alpha_factors.py - agent_utilities/domains/finance/banking.py - agent_utilities/domains/finance/banking_models.py - agent_utilities/domains/finance/copy_trade.py - agent_utilities/domains/finance/credit_quality.py - agent_utilities/domains/finance/cross_market_arb.py - agent_utilities/domains/finance/crypto_connector.py - agent_utilities/domains/finance/debate_engine.py - agent_utilities/domains/finance/filing_diff.py - agent_utilities/domains/finance/forensic_screener.py - agent_utilities/domains/finance/insider_equilibrium.py - agent_utilities/domains/finance/investor_debate.py - agent_utilities/domains/finance/kronos_forecaster.py - agent_utilities/domains/finance/market_data.py - agent_utilities/domains/finance/market_feeds.py - agent_utilities/domains/finance/microstructure.py - agent_utilities/domains/finance/pattern_classifier.py - agent_utilities/domains/finance/payments.py - agent_utilities/domains/finance/portfolio_optimizer.py - agent_utilities/domains/finance/profit_attribution.py - agent_utilities/domains/finance/quant_ontology.py - agent_utilities/domains/finance/regime_detector.py - agent_utilities/domains/finance/research_autopilot.py - agent_utilities/domains/finance/risk_manager.py - agent_utilities/domains/finance/signal_fusion.py - agent_utilities/domains/finance/strategy_export.py - agent_utilities/domains/finance/strategy_sharing.py - agent_utilities/domains/finance/streaming.py - agent_utilities/domains/finance/trading_swarm.py - agent_utilities/domains/finance/versioned_orders.py - agent_utilities/domains/finance/visual_ta.py - agent_utilities/domains/hr/models.py - agent_utilities/domains/hr/workforce_manager.py - agent_utilities/domains/law/__init__.py - agent_utilities/domains/law/models.py - agent_utilities/domains/medical/__init__.py - agent_utilities/domains/medical/models.py - agent_utilities/knowledge_graph/adaptation/research_artifacts.py - agent_utilities/knowledge_graph/backends/brain_guarded_backend.py - agent_utilities/knowledge_graph/core/archimate_layer.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/core/formal_reasoning_core.py - agent_utilities/knowledge_graph/core/markov_regime.py - agent_utilities/knowledge_graph/core/ontological_team_sharing.py - agent_utilities/knowledge_graph/core/optimal_execution.py - agent_utilities/knowledge_graph/core/source_resolver.py - agent_utilities/knowledge_graph/enrichment/ops_causal_graph.py - agent_utilities/knowledge_graph/orchestration/engine_enterprise.py - agent_utilities/knowledge_graph/orchestration/engine_finance.py - agent_utilities/knowledge_graph/orchestration/engine_ml_rlm.py - agent_utilities/knowledge_graph/orchestration/research_subagent.py - agent_utilities/knowledge_graph/research/research_intelligence_engine.py - agent_utilities/knowledge_graph/retrieval/hybrid_retriever.py - agent_utilities/knowledge_graph/retrieval/latent_topology_rag.py - agent_utilities/knowledge_graph/streams/__init__.py - agent_utilities/knowledge_graph/streams/kafka_adapter.py - agent_utilities/knowledge_graph/streams/nats_adapter.py - agent_utilities/models/company_brain.py - agent_utilities/models/domains/finance.py - agent_utilities/models/knowledge_graph.py - agent_utilities/models/schema_pack.py - agent_utilities/models/schema_packs/finance.py - agent_utilities/security/threat_defense_engine.py doc: Generates actionable LLM artifacts from KG-ingested research - id: AU-KG.research.research-state-domain-pack name: Research-State Domain Pack pillar: AU-KG status: live code_paths: - agent_utilities/models/knowledge_graph.py - agent_utilities/models/schema_packs/research.py doc: Research-State Domain Pack - id: AU-KG.research.run-one-autonomous-night name: AU-KG.research.run-one-autonomous-night pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/research/night_shift.py doc: AU-KG.research.run-one-autonomous-night - id: AU-KG.research.saturation-gauge-aggregates-four name: Saturation gauge. Aggregates the four signals that already exist pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/research/evolution_state.py - agent_utilities/knowledge_graph/research/loop_controller.py doc: Saturation gauge. Aggregates the four signals that already exist - id: AU-KG.research.scholarx-rss-research-feed name: ScholarX RSS research-feed loop that grades and fetches new papers pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/research/feed_grading.py doc: ScholarX RSS research-feed loop that grades and fetches new papers - id: AU-KG.research.self-evolution-convergence name: Research assimilation / self-evolution convergence pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/adaptation/topic_resolver.py - agent_utilities/knowledge_graph/research/search.py - agent_utilities/models/knowledge_graph.py doc: Research assimilation / self-evolution convergence - id: AU-KG.research.skill-graph-distillation name: A skill-graph captures an externally-consumable corpus of knowledge pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/distillation/skill_graph_pipeline.py - agent_utilities/knowledge_graph/distillation/skill_graph_schema.py - agent_utilities/knowledge_graph/ontology/interfaces.py - agent_utilities/mcp/tools/write_ingest_tools.py doc: A skill-graph captures an externally-consumable corpus of knowledge - id: AU-KG.research.so-cohort name: so the Article node pillar: AU-KG status: live code_paths: - agent_utilities/automation/research_pipeline.py - agent_utilities/knowledge_graph/research/cohort.py doc: so the Article node - id: AU-KG.research.these-properties-carry name: OPT-IN via KG_LOOP=1; pillar: AU-KG status: live code_paths: - agent_utilities/core/sessions.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/knowledge_graph/research/loops.py - agent_utilities/mcp/tools/state_tools.py - agent_utilities/orchestration/agent_dispatch_worker.py doc: OPT-IN via KG_LOOP=1; - id: AU-KG.research.zero-llm-pack-link name: Zero-LLM Pack-Driven Link Inference pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/assimilation/identity_candidates.py - agent_utilities/knowledge_graph/kb/entity_claim_extractor.py - agent_utilities/knowledge_graph/kb/link_inference.py - agent_utilities/models/schema_pack.py - agent_utilities/models/schema_packs/research.py doc: Zero-LLM Pack-Driven Link Inference - id: AU-KG.retrieval.acl-aware-vector-retrieval name: pass the served pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/orchestration/engine_query.py - agent_utilities/knowledge_graph/retrieval/hybrid_retriever.py - agent_utilities/mcp/tools/analysis_tools.py - agent_utilities/mcp/tools/query_tools.py - agent_utilities/observability/gateway_metrics.py doc: pass the served - id: AU-KG.retrieval.adaptive-stopping-iterative-retrieval name: Adaptive Stopping for Iterative Retrieval pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/orchestration/engine_query.py - agent_utilities/knowledge_graph/retrieval/adaptive_stopping.py doc: Adaptive Stopping for Iterative Retrieval - id: AU-KG.retrieval.architecture-report name: a regenerable architecture report pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/code_metrics.py - agent_utilities/mcp/kg_server.py doc: a regenerable architecture report - id: AU-KG.retrieval.assimilated-from-mragent name: assimilated from MRAgent pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/active_reconstruction.py - agent_utilities/knowledge_graph/retrieval/entity_context.py doc: assimilated from MRAgent - id: AU-KG.retrieval.batch-hydrate name: cross-base-node hydration batching pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/orchestration/engine_query.py - agent_utilities/knowledge_graph/retrieval/graph_engineering.py - agent_utilities/knowledge_graph/retrieval/hybrid_retriever.py doc: cross-base-node hydration batching - id: AU-KG.retrieval.batched-neighborhood-prefetch name: hard ceiling on how many pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/hybrid_retriever.py doc: hard ceiling on how many - id: AU-KG.retrieval.capability-power-descriptor name: AU-KG.retrieval.capability-power-descriptor pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/capability_context.py - agent_utilities/knowledge_graph/retrieval/capability_power_descriptor.py - agent_utilities/knowledge_graph/retrieval/context_plane.py - agent_utilities/mcp/tools/analyze_suite.py doc: AU-KG.retrieval.capability-power-descriptor - id: AU-KG.retrieval.context-compile-circuit-breaker name: per-process breaker over pillar: AU-KG status: live code_paths: - agent_utilities/core/contextual_model.py doc: per-process breaker over - id: AU-KG.retrieval.context-compiler name: MMR-diversified, evidence/freshness-weighted, token-budgeted, policy-filtered context with citations + a proof graph, instead of the plain relevance-sorted text the other modes return pillar: AU-KG status: live code_paths: - agent_utilities/core/contextual_model.py - agent_utilities/knowledge_graph/retrieval/context_compiler.py - agent_utilities/knowledge_graph/retrieval/context_compiler_serving.py - agent_utilities/mcp/tools/query_tools.py - agent_utilities/observability/__init__.py - agent_utilities/observability/gateway_metrics.py doc: MMR-diversified, evidence/freshness-weighted, token-budgeted, policy-filtered context with citations + a proof graph, instead of the plain relevance-sorted text the other modes return - id: AU-KG.retrieval.context-compiler-kv-seam name: the serving-layer half of Seam 6. Builds pillar: AU-KG status: live code_paths: - agent_utilities/core/contextual_model.py - agent_utilities/knowledge_graph/retrieval/context_compiler.py - agent_utilities/knowledge_graph/retrieval/context_compiler_serving.py - agent_utilities/observability/__init__.py - agent_utilities/observability/gateway_metrics.py doc: the serving-layer half of Seam 6. Builds - id: AU-KG.retrieval.cross-session-chat-recall name: chat transcripts can contain multi-MB pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/conversation_ingestion.py - agent_utilities/knowledge_graph/retrieval/chat_search.py doc: chat transcripts can contain multi-MB - id: AU-KG.retrieval.embedding-alignment-diagnostics name: CKA and alignment diagnostics now live in pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/embedding_diagnostics.py doc: CKA and alignment diagnostics now live in - id: AU-KG.retrieval.embedding-fast-fail name: raised internally so the query-time pillar: AU-KG status: live code_paths: - agent_utilities/core/embedding_utilities.py - agent_utilities/knowledge_graph/retrieval/hybrid_retriever.py - agent_utilities/observability/runtime_health.py doc: raised internally so the query-time - id: AU-KG.retrieval.embedding-version-identity name: the embedding version pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/document_processing.py - agent_utilities/knowledge_graph/retrieval/capability_index.py - agent_utilities/knowledge_graph/retrieval/embedding_versioning.py - agent_utilities/observability/gateway_metrics.py doc: the embedding version - id: AU-KG.retrieval.every-usage-published-symbol name: every pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/code_context.py - agent_utilities/mcp/kg_server.py doc: every - id: AU-KG.retrieval.evidence-graph-workspace name: keeps only tasks whose shortcut report is pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/knowledge_graph/search_synthesis/__init__.py - agent_utilities/knowledge_graph/search_synthesis/models.py - agent_utilities/mcp/tools/query_tools.py doc: keeps only tasks whose shortcut report is - id: AU-KG.retrieval.evidence-subgraph-construction name: evidence-subgraph construction pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/search_synthesis/evidence_subgraph.py doc: evidence-subgraph construction - id: AU-KG.retrieval.evidence-weighted-memory name: Evidence-Weighted Memory ────────────────────────────────── pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/retrieval_quality.py doc: Evidence-Weighted Memory ────────────────────────────────── - id: AU-KG.retrieval.fail-closed-grounding-contract name: the explicit grounding pillar: AU-KG status: live code_paths: - agent_utilities/core/contextual_model.py - agent_utilities/knowledge_graph/retrieval/context_compiler.py - agent_utilities/knowledge_graph/retrieval/hybrid_retriever.py - agent_utilities/mcp/tools/analysis_tools.py - agent_utilities/observability/__init__.py - agent_utilities/observability/trace_ontology.py - agent_utilities/orchestration/agent_runner.py - agent_utilities/orchestration/manager.py - agent_utilities/workflows/runner.py doc: the explicit grounding - id: AU-KG.retrieval.fixed-corpus-evaluation name: Fixed Corpus Evaluation Mode pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/evaluation_corpus.py doc: Fixed Corpus Evaluation Mode - id: AU-KG.retrieval.formulate-adversarially-refine name: and formulate + adversarially refine a pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/search_synthesis/__init__.py - agent_utilities/knowledge_graph/search_synthesis/shortcut_risks.py doc: and formulate + adversarially refine a - id: AU-KG.retrieval.fragment-cited-chunk name: mandatory evidence citation pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/document_processing.py doc: mandatory evidence citation - id: AU-KG.retrieval.god-nodes-communities name: god nodes, communities and pillar: AU-KG status: live code_paths: - agent_utilities/domains/finance/engine_series.py - agent_utilities/knowledge_graph/memory/timeseries/__init__.py - agent_utilities/knowledge_graph/retrieval/code_metrics.py - agent_utilities/mcp/kg_server.py doc: god nodes, communities and - id: AU-KG.retrieval.graph-distillation-migration name: Graph Distillation Migration pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/semantic_retrieval_engine.py doc: Graph Distillation Migration - id: AU-KG.retrieval.graph-engineering-canonical-prompts name: sourced from the pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/distillation/deduplicator.py - agent_utilities/knowledge_graph/extraction/fact_extractor.py - agent_utilities/knowledge_graph/pipeline/phases/community_reports.py - agent_utilities/knowledge_graph/retrieval/graph_engineering.py - agent_utilities/mcp/tools/analysis_tools.py - agent_utilities/mcp/tools/graph_engineering_tools.py - agent_utilities/prompts/canonical.py doc: sourced from the - id: AU-KG.retrieval.hard-negative-mining name: Hard Negative Mining for Retrieval Calibration pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/hard_negative_miner.py doc: Hard Negative Mining for Retrieval Calibration - id: AU-KG.retrieval.harness-grounding name: AU-KG.retrieval.harness-grounding pillar: AU-KG status: live code_paths: - agent_utilities/harness/harness_grounding.py - agent_utilities/protocols/source_connectors/connectors/mcp_tool.py doc: AU-KG.retrieval.harness-grounding - id: AU-KG.retrieval.hierarchical-topological-analysis name: Topological Analysis pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/hierarchical_retrieval.py doc: Topological Analysis - id: AU-KG.retrieval.iterative-expansion-adore name: assimilated from ADORE pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/iterative_expansion.py doc: assimilated from ADORE - id: AU-KG.retrieval.kg-2 name: AU-KG.retrieval.kg-2 pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/deploy_context.py doc: AU-KG.retrieval.kg-2 - id: AU-KG.retrieval.kg-3 name: AU-KG.retrieval.kg-3 pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/context_plane.py - agent_utilities/knowledge_graph/retrieval/entity_context.py doc: AU-KG.retrieval.kg-3 - id: AU-KG.retrieval.kg-4 name: AU-KG.retrieval.kg-4 pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/troubleshoot_context.py doc: AU-KG.retrieval.kg-4 - id: AU-KG.retrieval.mandatory-evidence-citation name: means an unresolvable pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/lineage.py - agent_utilities/observability/gateway_metrics.py doc: means an unresolvable - id: AU-KG.retrieval.memory-first-retrieval name: Memory-First Retrieval ────────────────────────────────── pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/orchestration/engine_query.py - agent_utilities/knowledge_graph/retrieval/direct_corpus.py - agent_utilities/knowledge_graph/retrieval/executable_rag.py - agent_utilities/knowledge_graph/retrieval/hybrid_retriever.py - agent_utilities/knowledge_graph/retrieval/hyde_planner.py doc: Memory-First Retrieval ────────────────────────────────── - id: AU-KG.retrieval.mmr-diversification name: when an pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/extraction/extraction_schema.py - agent_utilities/knowledge_graph/extraction/fact_extractor.py doc: when an - id: AU-KG.retrieval.monte-carlo-graph-search name: Progressive Monte-Carlo Graph Search pillar: AU-KG status: live code_paths: - agent_utilities/harness/__init__.py - agent_utilities/harness/agentic_evolution_engine.py - agent_utilities/harness/graph_search_evolution.py doc: Progressive Monte-Carlo Graph Search - id: AU-KG.retrieval.opensearch-cdc-indexer name: CA-24, DEC-CA-09, DEC-CA-03 pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/search/__init__.py - agent_utilities/knowledge_graph/search/client.py - agent_utilities/knowledge_graph/search/dls.py - agent_utilities/knowledge_graph/search/doc_shape.py - agent_utilities/knowledge_graph/search/indexer.py - agent_utilities/knowledge_graph/search/rebuild.py - agent_utilities/mcp/tools/write_ingest_tools.py doc: CA-24, DEC-CA-09, DEC-CA-03 - id: AU-KG.retrieval.ops-context name: AU-KG.retrieval.ops-context pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/ops_context.py doc: AU-KG.retrieval.ops-context - id: AU-KG.retrieval.pack-retrieval-signals name: Pack-Driven Retrieval Signals pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/autocut.py doc: Pack-Driven Retrieval Signals - id: AU-KG.retrieval.pauserec-implicit-reasoning-generative name: AU-KG.retrieval.pauserec-implicit-reasoning-generative pillar: AU-KG status: live code_paths: - agent_utilities/harness/assimilation_benchmark.py - agent_utilities/knowledge_graph/retrieval/generative_recommender.py doc: AU-KG.retrieval.pauserec-implicit-reasoning-generative - id: AU-KG.retrieval.per-item-relevance-ranking name: Per-Item Relevance Ranking pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py doc: Per-Item Relevance Ranking - id: AU-KG.retrieval.question-formulation-adversarial-refinement name: question formulation + adversarial refinement pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/search_synthesis/__init__.py - agent_utilities/knowledge_graph/search_synthesis/question_formulation.py doc: question formulation + adversarial refinement - id: AU-KG.retrieval.recall-feedback name: record that these memories were RECALLED, on the live retrieval path pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/hybrid_retriever.py doc: record that these memories were RECALLED, on the live retrieval path - id: AU-KG.retrieval.relational-intent-retrieval name: Relational-Intent Retrieval pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/hybrid_retriever.py - agent_utilities/knowledge_graph/retrieval/relational_intent.py - agent_utilities/models/schema_pack.py - agent_utilities/models/schema_packs/research.py doc: Relational-Intent Retrieval - id: AU-KG.retrieval.retrieval-quality-assessment name: Retrieval Quality pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/reasoning_reranker.py doc: Retrieval Quality - id: AU-KG.retrieval.route-question-its-domain name: route a question to its domain pillar: AU-KG status: live code_paths: - agent_utilities/core/source_paths.py - agent_utilities/knowledge_graph/retrieval/context_plane.py - agent_utilities/mcp/kg_server.py - agent_utilities/mcp/tools/analyze_suite.py doc: route a question to its domain - id: AU-KG.retrieval.section-tree name: it scores nodes on their *title + summary* pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ontology/contextual_enrichment.py - agent_utilities/knowledge_graph/ontology/document_processing.py - agent_utilities/knowledge_graph/pipeline/document_ingestion.py - agent_utilities/knowledge_graph/retrieval/hierarchical_document_retriever.py - agent_utilities/mcp/tools/query_tools.py doc: it scores nodes on their *title + summary* - id: AU-KG.retrieval.self-correcting-second-pass name: run a self-correcting second retrieval pass at the deep threshold when the quality gate fails pillar: AU-KG status: live code_paths: - agent_utilities/mcp/tools/query_tools.py doc: run a self-correcting second retrieval pass at the deep threshold when the quality gate fails - id: AU-KG.retrieval.source-to-claim-lineage name: AU-KG.retrieval.source-to-claim-lineage pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/evidence_spine.py - agent_utilities/knowledge_graph/retrieval/lineage.py - agent_utilities/mcp/tools/audit_tools.py doc: AU-KG.retrieval.source-to-claim-lineage - id: AU-KG.retrieval.synthesized-cited-answer name: the pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/code_context.py - agent_utilities/mcp/kg_server.py doc: the - id: AU-KG.retrieval.task-start-kg-priming name: prime the KG pillar: AU-KG status: live code_paths: - agent_utilities/orchestration/agent_runner.py doc: prime the KG - id: AU-KG.retrieval.tree-navigation name: a retriever that *walks* a document pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/hierarchical_document_retriever.py - agent_utilities/mcp/tools/query_tools.py doc: a retriever that *walks* a document - id: AU-KG.retrieval.triviality-gate name: HybridRetriever._lexical_fallback pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/retrieval/hybrid_retriever.py - agent_utilities/knowledge_graph/retrieval/hyde_planner.py - agent_utilities/knowledge_graph/retrieval/retrieval_quality.py doc: HybridRetriever._lexical_fallback - id: AU-KG.retrieval.unified-capability-contract name: a resolved pillar: AU-KG status: live code_paths: - agent_utilities/core/capability_contract.py - agent_utilities/mcp/multiplexer.py - agent_utilities/mcp/tools/analysis_tools.py - agent_utilities/orchestration/manager.py doc: a resolved - id: AU-KG.retrieval.unset-dependency-free name: Unset → the dependency-free pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/orchestration/engine_query.py - agent_utilities/knowledge_graph/retrieval/neural_reranker.py - agent_utilities/knowledge_graph/retrieval/reasoning_reranker.py - agent_utilities/knowledge_graph/retrieval/score_gate.py doc: Unset → the dependency-free - id: AU-KG.sharding.cluster-members-discovery-session name: Verified pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/cluster_discovery.py doc: Verified - id: AU-KG.sharding.elastic-over-kg-shard name: The elastic layer over KG-2.58 shard routing pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/core/tenant_engine_pool.py doc: The elastic layer over KG-2.58 shard routing - id: AU-KG.sharding.tenant-partitioned-sharding-hrw name: Tenant-partitioned engine sharding with HRW graph-to-shard routing and tenant to named-graph placement over GRAPH_SERVICE_ENDPOINTS pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/__init__.py - agent_utilities/knowledge_graph/core/connection_registry.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/core/graph_compute.py - agent_utilities/knowledge_graph/core/ingest_routing.py - agent_utilities/knowledge_graph/core/placement_catalog.py - agent_utilities/knowledge_graph/core/session.py - agent_utilities/knowledge_graph/core/shard_topology.py - agent_utilities/knowledge_graph/facade.py - agent_utilities/observability/gateway_metrics.py doc: Tenant-partitioned engine sharding with HRW graph-to-shard routing and tenant to named-graph placement over GRAPH_SERVICE_ENDPOINTS - id: AU-KG.storage.config-writeback name: the write-back companion to the read-only XDG loader, so a pillar: AU-KG status: live code_paths: - agent_utilities/core/config.py doc: the write-back companion to the read-only XDG loader, so a - id: AU-KG.storage.durable-execution-unit name: the run mirrors its pillar: AU-KG status: live code_paths: - agent_utilities/harness/agentic_evolution_engine.py - agent_utilities/knowledge_graph/durable_execution_kg.py - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/orchestration/durable_execution.py doc: the run mirrors its - id: AU-KG.temporal.ambient-connector-valid-time name: the ambient-epistemics pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/bitemporal.py - agent_utilities/knowledge_graph/ingestion/envelope_ingest.py doc: the ambient-epistemics - id: AU-KG.temporal.bi-temporal-memory-layers name: Bi-Temporal Memory Layers. The three Quarq memory layers pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/bitemporal.py - agent_utilities/knowledge_graph/core/engine.py - agent_utilities/knowledge_graph/enrichment/writeback/core.py - agent_utilities/knowledge_graph/enrichment/writeback/findings.py - agent_utilities/knowledge_graph/enrichment/writeback/inventory.py - agent_utilities/knowledge_graph/enrichment/writeback/sinks/egeria.py - agent_utilities/knowledge_graph/enrichment/writeback/sinks/servicenow.py - agent_utilities/knowledge_graph/orchestration/engine_query.py - agent_utilities/knowledge_graph/retrieval/hybrid_retriever.py - agent_utilities/models/knowledge_graph.py - agent_utilities/models/schema_pack.py - agent_utilities/observability/portfolio_intelligence.py doc: Bi-Temporal Memory Layers. The three Quarq memory layers - id: AU-KG.temporal.cross-agent-provenance name: Cross-Agent Context Provenance pillar: AU-KG status: live code_paths: - agent_utilities/graph/state.py doc: Cross-Agent Context Provenance - id: AU-KG.temporal.message-history-read name: carry the per-tool-call provenance up to run_agent, which pillar: AU-KG status: live code_paths: - agent_utilities/graph/_router_impl.py - agent_utilities/graph/executor.py - agent_utilities/graph/state.py - agent_utilities/models/graph.py - agent_utilities/orchestration/agent_runner.py - agent_utilities/orchestration/engine.py - agent_utilities/orchestration/tool_provenance.py doc: carry the per-tool-call provenance up to run_agent, which - id: AU-KG.temporal.plan-task-versioning name: Implementation Plan & Tasks versioning and KG lineage pillar: AU-KG status: live code_paths: - agent_utilities/sdd/watcher.py doc: Implementation Plan & Tasks versioning and KG lineage - id: AU-KG.temporal.token-event-tsdb name: ALSO append this event to the engine tsdb as a per-agent pillar: AU-KG status: live code_paths: - agent_utilities/observability/token_tracker.py doc: ALSO append this event to the engine tsdb as a per-agent - id: AU-KG.temporal.workspace-action-provenance name: Workspace-Action Provenance Graph pillar: AU-KG status: live code_paths: - agent_utilities/runtime/provenance.py doc: Workspace-Action Provenance Graph - id: AU-KG.txn.git-like-versioning name: Provides git-like transactional mutation for KG evolution pillar: AU-KG status: live code_paths: - agent_utilities/knowledge_graph/core/kg_versioning.py doc: Provides git-like transactional mutation for KG evolution - id: AU-ORCH.adapter.adapter-registry-path-detection name: Adapter registry + non-blocking PATH detection pillar: AU-ORCH status: live code_paths: - agent_utilities/core/execution/adapters/registry.py doc: Adapter registry + non-blocking PATH detection - id: AU-ORCH.adapter.builtin-adapter-definitions name: Built-in adapter definitions pillar: AU-ORCH status: live code_paths: - agent_utilities/core/execution/adapters/defs/__init__.py doc: Built-in adapter definitions - id: AU-ORCH.adapter.byok-provider-proxy name: BYOK provider-normalizing proxy router pillar: AU-ORCH status: live code_paths: - agent_utilities/core/execution/provider_proxy.py - agent_utilities/core/model_factory.py - agent_utilities/security/egress.py - agent_utilities/server/app.py - agent_utilities/server/routers/proxy.py doc: BYOK provider-normalizing proxy router - id: AU-ORCH.adapter.composable-skills-environment name: Composable Skills + Generic Environment Adapter pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/runner.py - agent_utilities/rlm/skills.py doc: Composable Skills + Generic Environment Adapter - id: AU-ORCH.adapter.hot-cache-invalidation name: Invalidate hot cache so routing reflects new self-knowledge pillar: AU-ORCH status: live code_paths: - agent_utilities/agent/registry_builder.py - agent_utilities/capabilities/adversarial_verifier.py - agent_utilities/core/config.py - agent_utilities/core/default_catalog.py - agent_utilities/core/model_factory.py - agent_utilities/core/model_router.py - agent_utilities/core/registry/kg_adapter.py - agent_utilities/core/registry/package_adapter.py - agent_utilities/graph/executor.py - agent_utilities/graph/hierarchical_planner.py - agent_utilities/graph/parallel_engine.py - agent_utilities/graph/routing/strategies/learned.py - agent_utilities/knowledge_graph/pipeline/runner.py - agent_utilities/knowledge_graph/retrieval/memory_retriever.py - agent_utilities/mcp/agent_manager.py - agent_utilities/models/knowledge_graph.py - agent_utilities/protocols/a2a_config.py - agent_utilities/workflows/skill_picker.py doc: Invalidate hot cache so routing reflects new self-knowledge - id: AU-ORCH.adapter.inject-composable-skill-instructions name: inject mounted composable-Skill instructions pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/predict_rlm.py doc: inject mounted composable-Skill instructions - id: AU-ORCH.adapter.kg-graph-materialization name: Session ID of the parent graph if this state was forked pillar: AU-ORCH status: live code_paths: - agent_utilities/capabilities/hooks.py - agent_utilities/core/config.py - agent_utilities/core/registry/kg_adapter.py - agent_utilities/graph/__init__.py - agent_utilities/graph/_router_impl.py - agent_utilities/graph/horizon_curriculum.py - agent_utilities/graph/kg_graph_factory.py - agent_utilities/graph/protocol_agnostic_execution.py - agent_utilities/graph/routing/strategies/policy.py - agent_utilities/graph/state.py - agent_utilities/knowledge_graph/core/engine.py - agent_utilities/models/knowledge_graph.py - agent_utilities/models/schema_definition.py doc: Session ID of the parent graph if this state was forked - id: AU-ORCH.adapter.multi-cli-adapter-dispatch name: additive multi-CLI adapter dispatch. When a manifest requests an external runtime pillar: AU-ORCH status: live code_paths: - agent_utilities/core/execution/adapters/__init__.py - agent_utilities/core/execution/adapters/base.py - agent_utilities/core/execution/engine.py doc: additive multi-CLI adapter dispatch. When a manifest requests an external runtime - id: AU-ORCH.adapter.openai-catalog-verification name: the OpenBao-backed alternative to the literal pillar: AU-ORCH status: live code_paths: - agent_utilities/core/config.py - agent_utilities/core/credentials.py - agent_utilities/core/model_factory.py - agent_utilities/core/openai_catalog.py - agent_utilities/deployment/doctor.py doc: the OpenBao-backed alternative to the literal - id: AU-ORCH.adapter.shareable-team-compositions name: Shareable Team Compositions pillar: AU-ORCH status: live code_paths: - agent_utilities/core/registry/kg_adapter.py doc: Shareable Team Compositions - id: AU-ORCH.adapter.spawn-adapter-normalise-stream name: Spawn an adapter backend and normalise its stream pillar: AU-ORCH status: live code_paths: - agent_utilities/core/execution/adapters/executor.py doc: Spawn an adapter backend and normalise its stream - id: AU-ORCH.adapter.stream-format-dispatch name: Stream-format dispatch pillar: AU-ORCH status: live code_paths: - agent_utilities/core/execution/stream_handlers.py doc: Stream-format dispatch - id: AU-ORCH.adapter.three-tier-credential-resolution name: Four-tier credential resolution pillar: AU-ORCH status: live code_paths: - agent_utilities/core/credentials.py doc: Four-tier credential resolution - id: AU-ORCH.adapter.transport-toolset-factory name: the transport invokes this factory with a transport-version pillar: AU-ORCH status: live code_paths: - agent_utilities/mcp/toolset_factory.py - agent_utilities/orchestration/agent_runner.py doc: the transport invokes this factory with a transport-version - id: AU-ORCH.adapter.unified-service-discovery name: Service registry initialized with pillar: AU-ORCH status: live code_paths: - agent_utilities/core/registry/service_adapter.py doc: Service registry initialized with - id: AU-ORCH.dispatch.agents-as-data-activation name: ADR-6 / W2.3 pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/agent_activation.py doc: ADR-6 / W2.3 - id: AU-ORCH.dispatch.builtin-agent-templates name: makes the packaged expert personas *dispatchable* agents pillar: AU-ORCH status: live code_paths: - agent_utilities/agent/registry_builder.py doc: makes the packaged expert personas *dispatchable* agents - id: AU-ORCH.dispatch.dispatch-half-skill-ingestion name: the dispatch half of skill ingestion. An ingested atomic pillar: AU-ORCH status: live code_paths: - agent_utilities/knowledge_graph/enrichment/execute.py - agent_utilities/orchestration/agent_runner.py doc: the dispatch half of skill ingestion. An ingested atomic - id: AU-ORCH.dispatch.dispatch-warm-fork name: dispatch-tier warm-fork pillar: AU-ORCH status: live code_paths: - agent_utilities/agent/warm_skills.py doc: dispatch-tier warm-fork - id: AU-ORCH.dispatch.embedding-fanout name: the ceiling decides the steady-state MAX in flight; the pillar: AU-ORCH status: live code_paths: - agent_utilities/core/model_circuit_breaker.py - agent_utilities/knowledge_graph/enrichment/semantic.py doc: the ceiling decides the steady-state MAX in flight; the - id: AU-ORCH.dispatch.fleet-specialist-reachability name: a thin entrypoint persona pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/agent_runner.py doc: a thin entrypoint persona - id: AU-ORCH.dispatch.hierarchical-coordination name: a hierarchical federated coordination protocol that runs consensus within agent neighborhoods and rolls up only cluster representatives, bounding interaction density so a collective coordinates at thousands of agents instead of O pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/hierarchical_coordination.py doc: a hierarchical federated coordination protocol that runs consensus within agent neighborhoods and rolls up only cluster representatives, bounding interaction density so a collective coordinates at thousands of agents instead of O - id: AU-ORCH.dispatch.kg-governed-agent-swarm name: model the wave as a Multi-Agent Social System and pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/parallel_engine.py - agent_utilities/graph/social_system.py - agent_utilities/models/execution_manifest.py doc: model the wave as a Multi-Agent Social System and - id: AU-ORCH.dispatch.kg-team-composition name: KG-Driven Team Composition pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/team_composer.py doc: KG-Driven Team Composition - id: AU-ORCH.dispatch.laned-sweep-fanout name: fan the sweep out as LANED pillar: AU-ORCH status: live code_paths: - agent_utilities/knowledge_graph/core/source_sync.py doc: fan the sweep out as LANED - id: AU-ORCH.dispatch.named-runnable-precondition name: AU-ORCH.dispatch.named-runnable-precondition pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/agent_runner.py doc: AU-ORCH.dispatch.named-runnable-precondition - id: AU-ORCH.dispatch.parameterized-queue-topic name: the topic/group are parameters so the agent pillar: AU-ORCH status: live code_paths: - agent_utilities/knowledge_graph/core/kafka_queue_backend.py doc: the topic/group are parameters so the agent - id: AU-ORCH.dispatch.persistent-background-agents name: Persistent Background Agents pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/persistent_agents.py doc: Persistent Background Agents - id: AU-ORCH.dispatch.queue-agent-dispatch name: Queue-driven agent dispatch with session-keyed partitions pillar: AU-ORCH status: live code_paths: - agent_utilities/core/config.py - agent_utilities/core/sessions.py - agent_utilities/knowledge_graph/core/postgres_queue_backend.py - agent_utilities/knowledge_graph/core/work_durability.py - agent_utilities/observability/gateway_metrics.py - agent_utilities/orchestration/agent_dispatch.py - agent_utilities/orchestration/agent_dispatch_worker.py doc: Queue-driven agent dispatch with session-keyed partitions - id: AU-ORCH.dispatch.seeded-agent-template name: a built-in/seeded AgentTemplate pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/agent_runner.py doc: a built-in/seeded AgentTemplate - id: AU-ORCH.dispatch.two-pool name: TWO independently-sized worker POOLS over the pillar: AU-ORCH status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/core/task_lanes.py - agent_utilities/knowledge_graph/core/worker_scheduler.py doc: TWO independently-sized worker POOLS over the - id: AU-ORCH.dispatch.warm-skills-share name: warm-share the skills capability across the fan-out cohort pillar: AU-ORCH status: live code_paths: - agent_utilities/agent/factory.py doc: warm-share the skills capability across the fan-out cohort - id: AU-ORCH.dispatch.worker-scheduling name: gate the claim through the pillar: AU-ORCH status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/core/worker_scheduler.py doc: gate the claim through the - id: AU-ORCH.dispatch.workitem-consent-gate name: a WorkItem is bound only to pillar: AU-ORCH status: live code_paths: - agent_utilities/knowledge_graph/core/work_durability.py - agent_utilities/messaging/bus_inbox.py - agent_utilities/models/knowledge_graph.py doc: a WorkItem is bound only to - id: AU-ORCH.dispatch.workitem-idempotency-key-dedup name: AU-ORCH.dispatch.workitem-idempotency-key-dedup pillar: AU-ORCH status: live code_paths: - agent_utilities/knowledge_graph/core/work_durability.py doc: AU-ORCH.dispatch.workitem-idempotency-key-dedup - id: AU-ORCH.execution.active-subagent-lifecycle name: Subagent Lifecycle Patterns pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/subagent_patterns.py doc: Subagent Lifecycle Patterns - id: AU-ORCH.execution.all-tool-calls-errored name: no tool-grounded pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/agent_runner.py doc: no tool-grounded - id: AU-ORCH.execution.autonomous-department-orchestration name: Autonomous Department Orchestration pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/manifest_generators.py - agent_utilities/models/company.py doc: Autonomous Department Orchestration - id: AU-ORCH.execution.best-effort-provenance name: close the descriptive↔executable provenance loop pillar: AU-ORCH status: live code_paths: - agent_utilities/workflows/runner.py doc: close the descriptive↔executable provenance loop - id: AU-ORCH.execution.chat-profile-timeouts name: chat profile bounds node timeouts to the chat budget; the task pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/_router_impl.py - agent_utilities/orchestration/agent_runner.py - agent_utilities/orchestration/execution_profile.py - agent_utilities/orchestration/manager.py doc: chat profile bounds node timeouts to the chat budget; the task - id: AU-ORCH.execution.computer-use-agent name: GUI capture + click/type on a pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/computer_use_agent.py - agent_utilities/tools/tool_registry.py doc: GUI capture + click/type on a - id: AU-ORCH.execution.computer-use-tools name: Computer-use tools pillar: AU-ORCH status: live code_paths: - agent_utilities/tools/computer_use_tools.py doc: Computer-use tools - id: AU-ORCH.execution.consensus-aggregation name: named-aggregation consensus over winners pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/workspace_attention.py doc: named-aggregation consensus over winners - id: AU-ORCH.execution.coordination-negotiation name: Coordination negotiation before execution pillar: AU-ORCH status: live code_paths: - agent_utilities/protocols/a2a_graph_skill.py doc: Coordination negotiation before execution - id: AU-ORCH.execution.coordination-protocol-metadata name: Selected coordination protocol metadata pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/coordination.py - agent_utilities/models/knowledge_graph.py doc: Selected coordination protocol metadata - id: AU-ORCH.execution.degraded-no-data-outcome name: AU-AHE.evaluation.action-outcome-feedback pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/verification.py - agent_utilities/orchestration/agent_runner.py doc: AU-AHE.evaluation.action-outcome-feedback - id: AU-ORCH.execution.delegation-hot-path-authority name: keep a long delegation authorized for its whole run, on every entrypoint, not just MCP dispatch pillar: AU-ORCH status: live code_paths: - agent_utilities/mcp/kg_server.py - agent_utilities/orchestration/manager.py doc: keep a long delegation authorized for its whole run, on every entrypoint, not just MCP dispatch - id: AU-ORCH.execution.delegation-reasoning-off name: reasoning is an OPT-IN capability pillar: AU-ORCH status: live code_paths: - agent_utilities/agent/factory.py - agent_utilities/core/model_factory.py - agent_utilities/graph/_router_impl.py - agent_utilities/mcp/tools/analysis_tools.py - agent_utilities/orchestration/agent_runner.py doc: reasoning is an OPT-IN capability - id: AU-ORCH.execution.delegation-wall-clock name: One correct value, not a knob pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/agent_runner.py doc: One correct value, not a knob - id: AU-ORCH.execution.developer-workspace-runtime name: the developer-workspace runtime pillar: AU-ORCH status: live code_paths: - agent_utilities/models/agent.py doc: the developer-workspace runtime - id: AU-ORCH.execution.direct-completion-shape name: a direct-completion shape answers with one lean local-model round and pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/_router_impl.py - agent_utilities/graph/hierarchical_planner.py - agent_utilities/graph/lifecycle.py - agent_utilities/orchestration/agent_runner.py - agent_utilities/orchestration/execution_profile.py doc: a direct-completion shape answers with one lean local-model round and - id: AU-ORCH.execution.drop-rlm-completion-client name: Drop-in RLM completion client and model-family-aware REPL prompt pillar: AU-ORCH status: live code_paths: - agent_utilities/harness/agentic_evolution_engine.py - agent_utilities/mcp/tools/analysis_tools.py - agent_utilities/rlm/__init__.py - agent_utilities/rlm/client.py - agent_utilities/rlm/config.py - agent_utilities/rlm/prompts.py - agent_utilities/rlm/repl.py doc: Drop-in RLM completion client and model-family-aware REPL prompt - id: AU-ORCH.execution.dual-execution-models name: Two execution models — remote A2A vs. unified specialist pillar: AU-ORCH status: live code_paths: - agent_utilities/agent/discovery.py doc: Two execution models — remote A2A vs. unified specialist - id: AU-ORCH.execution.durable-routing-trait name: AU-ORCH.execution.durable-routing-trait pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/durable_tool_surface.py doc: AU-ORCH.execution.durable-routing-trait - id: AU-ORCH.execution.dynamic-execution-profile name: the profile is no longer a fixed per-entrypoint *preset*; it is the pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/state.py - agent_utilities/orchestration/execution_profile.py doc: the profile is no longer a fixed per-entrypoint *preset*; it is the - id: AU-ORCH.execution.dynamic-topology-materialization name: Dynamic Topology Materialization pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/topology_engine.py doc: Dynamic Topology Materialization - id: AU-ORCH.execution.dynamic-workflow-resume name: the truthfulness contract for pillar: AU-ORCH status: live code_paths: - agent_utilities/capabilities/governed_dynamic_workflow.py - agent_utilities/orchestration/manager.py doc: the truthfulness contract for - id: AU-ORCH.execution.dynamic-workflows name: approved per-delegation pillar: AU-ORCH status: live code_paths: - agent_utilities/capabilities/governed_dynamic_workflow.py - agent_utilities/models/sdd.py - agent_utilities/orchestration/engine.py doc: approved per-delegation - id: AU-ORCH.execution.engine-memory-management name: Memory Management pillar: AU-ORCH status: live code_paths: - agent_utilities/knowledge_graph/core/engine_memory.py doc: Memory Management - id: AU-ORCH.execution.eval-set-optimization-compounding name: Eval-Set Optimization & Compounding Learning Loop pillar: AU-ORCH status: live code_paths: - agent_utilities/harness/continuous_evaluation_engine.py - agent_utilities/rlm/eval_set_optimizer.py doc: Eval-Set Optimization & Compounding Learning Loop - id: AU-ORCH.execution.event-loop-blocking-sweep name: persist_facts pillar: AU-ORCH status: live code_paths: - agent_utilities/capabilities/checkpointing.py - agent_utilities/mcp/tools/write_ingest_tools.py doc: persist_facts - id: AU-ORCH.execution.execution-budget-caps name: Execution Budget. Defines caps for this session pillar: AU-ORCH status: live code_paths: - agent_utilities/base_utilities.py - agent_utilities/capabilities/checkpointing.py - agent_utilities/capabilities/governed_dynamic_workflow.py - agent_utilities/capabilities/output_repair.py - agent_utilities/core/checkpoint/manager.py - agent_utilities/graph/_router_impl.py - agent_utilities/graph/executor.py - agent_utilities/graph/hierarchical_planner.py - agent_utilities/graph/state.py - agent_utilities/graph/verification.py - agent_utilities/models/usage.py - agent_utilities/orchestration/agent_runner.py - agent_utilities/orchestration/engine.py - agent_utilities/tools/sdd_tools.py doc: Execution Budget. Defines caps for this session - id: AU-ORCH.execution.execution-profile name: this module is now PURELY STRUCTURAL. The old hardcoded pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/routing/strategies/fast_path.py - agent_utilities/orchestration/execution_profile.py doc: this module is now PURELY STRUCTURAL. The old hardcoded - id: AU-ORCH.execution.execution-seam-closure name: close the execution seam. This previously constructed a pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/manager.py doc: close the execution seam. This previously constructed a - id: AU-ORCH.execution.feed-cycle-outcome-fast name: feed the cycle outcome to the pillar: AU-ORCH status: live code_paths: - agent_utilities/harness/agentic_evolution_engine.py - agent_utilities/harness/fast_slow_controller.py doc: feed the cycle outcome to the - id: AU-ORCH.execution.focused-tools-altitude name: the FOCUSED-TOOLS altitude is one agent loop that calls the pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/agent_runner.py - agent_utilities/orchestration/execution_profile.py doc: the FOCUSED-TOOLS altitude is one agent loop that calls the - id: AU-ORCH.execution.focused-tools-fail-closed name: this branch is entered pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/agent_runner.py doc: this branch is entered - id: AU-ORCH.execution.focused-tools-fleet-egress name: this twin of the pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/agent_runner.py doc: this twin of the - id: AU-ORCH.execution.global-workspace-attention name: ───────────────────────────────── pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/workspace_attention.py doc: ───────────────────────────────── - id: AU-ORCH.execution.held-turn-registry-mid name: Held-turn registry for mid-turn tool-result injection pillar: AU-ORCH status: live code_paths: - agent_utilities/core/execution/held_turns.py - agent_utilities/security/sidecar_runtime.py - agent_utilities/server/routers/human.py doc: Held-turn registry for mid-turn tool-result injection - id: AU-ORCH.execution.inject-signal-board-observations name: Inject signal board observations from prior adaptive_agent_router pillar: AU-ORCH status: live code_paths: - agent_utilities/capabilities/adversarial_verifier.py - agent_utilities/graph/_router_impl.py - agent_utilities/graph/adaptive_agent_router.py - agent_utilities/graph/executor.py - agent_utilities/graph/hierarchical_planner.py - agent_utilities/graph/hsm.py - agent_utilities/graph/lifecycle.py - agent_utilities/graph/models.py - agent_utilities/graph/state.py - agent_utilities/harness/variant_pool.py - agent_utilities/models/knowledge_graph.py - agent_utilities/orchestration/engine.py - agent_utilities/protocols/agui_emitter.py doc: Inject signal board observations from prior adaptive_agent_router - id: AU-ORCH.execution.manifest-generators name: Manifest Generators pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/__init__.py doc: Manifest Generators - id: AU-ORCH.execution.messaging-orchestration-transparency name: every terminal outcome of pillar: AU-ORCH status: live code_paths: - agent_utilities/capabilities/output_repair.py - agent_utilities/messaging/backends/mattermost.py - agent_utilities/messaging/backends/telegram.py - agent_utilities/messaging/base.py - agent_utilities/messaging/router.py - agent_utilities/orchestration/agent_runner.py - agent_utilities/orchestration/engine.py - agent_utilities/orchestration/failure_translation.py - agent_utilities/orchestration/manager.py - agent_utilities/orchestration/run_envelope.py doc: every terminal outcome of - id: AU-ORCH.execution.nl-compilation-pipeline name: Semantic Workflow Retrieval pillar: AU-ORCH status: live code_paths: - agent_utilities/knowledge_graph/workflow_compiler.py doc: Semantic Workflow Retrieval - id: AU-ORCH.execution.no-silent-hallucination name: returned INSTEAD of falling through to the pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/agent_runner.py doc: returned INSTEAD of falling through to the - id: AU-ORCH.execution.no-silent-success-on-empty-workflow name: AU-ORCH.execution.no-silent-success-on-empty-workflow pillar: AU-ORCH status: live code_paths: - agent_utilities/workflows/runner.py doc: AU-ORCH.execution.no-silent-success-on-empty-workflow - id: AU-ORCH.execution.node-direct-end name: a node may END the run directly with End[GraphResponse pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/engine.py doc: a node may END the run directly with End[GraphResponse - id: AU-ORCH.execution.ontology-validation-execution-path name: Ontology Validation on the Execution Path pillar: AU-ORCH status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/core/workflow_gate.py doc: Ontology Validation on the Execution Path - id: AU-ORCH.execution.orchestration name: Orchestration Engine pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/__init__.py - agent_utilities/orchestration/engine.py doc: Orchestration Engine - id: AU-ORCH.execution.orchestration-flow-mermaid name: Orchestration execution-flow mermaid-diagram surfacing in graph_orchestrate responses pillar: AU-ORCH status: live code_paths: - agent_utilities/core/contextual_model.py - agent_utilities/graph/_router_impl.py - agent_utilities/graph/executor.py - agent_utilities/graph/hierarchical_planner.py - agent_utilities/graph/verification.py - agent_utilities/orchestration/agent_runner.py - agent_utilities/orchestration/manager.py doc: Orchestration execution-flow mermaid-diagram surfacing in graph_orchestrate responses - id: AU-ORCH.execution.parallel-engine-visualizer name: Dependency cycle detected — falling back pillar: AU-ORCH status: live code_paths: - agent_utilities/core/config.py - agent_utilities/core/execution/protocol.py - agent_utilities/graph/gather.py - agent_utilities/graph/manifest_generators.py - agent_utilities/graph/parallel_engine.py - agent_utilities/models/execution_manifest.py - agent_utilities/orchestration/engine.py - agent_utilities/workflows/distillation_hook.py - agent_utilities/workflows/visualizer.py doc: Dependency cycle detected — falling back - id: AU-ORCH.execution.passthrough-identity name: prompt-only universal entrypoints that must flow through the full pillar: AU-ORCH status: live code_paths: - agent_utilities/messaging/router.py - agent_utilities/orchestration/agent_runner.py - agent_utilities/orchestration/execution_profile.py doc: prompt-only universal entrypoints that must flow through the full - id: AU-ORCH.execution.per-job-shape-construction name: carry the constructed shape to the graph deps so each node pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/agent_runner.py doc: carry the constructed shape to the graph deps so each node - id: AU-ORCH.execution.planner-failure-feedback name: ───────────────────────────────────────────────── pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/agent_runner.py - agent_utilities/orchestration/execution_profile.py doc: ───────────────────────────────────────────────── - id: AU-ORCH.execution.predict-rlm-runtime name: RLM planning + fallback parser. The pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/_router_impl.py - agent_utilities/rlm/config.py - agent_utilities/rlm/predict_rlm.py - agent_utilities/rlm/runner.py - agent_utilities/rlm/schema.py doc: RLM planning + fallback parser. The - id: AU-ORCH.execution.recursive-language-model name: Recursive Language Model Execution pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/config.py doc: Recursive Language Model Execution - id: AU-ORCH.execution.reserved-inference-slots name: local-inference slots always kept free for the interactive path pillar: AU-ORCH status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/ingestion/engine.py doc: local-inference slots always kept free for the interactive path - id: AU-ORCH.execution.residual-ambiguous name: the residual ambiguous pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/routing/strategies/fast_path.py - agent_utilities/orchestration/execution_profile.py doc: the residual ambiguous - id: AU-ORCH.execution.retry-predicate-raised-treating name: retry_on predicate raised; treating as non-retryable pillar: AU-ORCH status: live code_paths: - agent_utilities/core/http_client.py - agent_utilities/graph/executor.py - agent_utilities/graph/parallel_engine.py - agent_utilities/knowledge_graph/backends/contrib/ladybug_backend.py - agent_utilities/knowledge_graph/backends/postgresql_backend.py - agent_utilities/knowledge_graph/memory/learning_engine.py - agent_utilities/orchestration/resilience.py - agent_utilities/patterns/prompt_chain.py doc: retry_on predicate raised; treating as non-retryable - id: AU-ORCH.execution.rich-result-wrapper name: AU-ORCH.execution.rich-result-wrapper pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/agent_runner.py doc: AU-ORCH.execution.rich-result-wrapper - id: AU-ORCH.execution.rlm-execution name: RLM Execution pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/__init__.py - agent_utilities/rlm/repl.py doc: RLM Execution - id: AU-ORCH.execution.rlm-experience-observability name: RLM for AHE Experience Observability pillar: AU-ORCH status: live code_paths: - agent_utilities/harness/continuous_evaluation_engine.py doc: RLM for AHE Experience Observability - id: AU-ORCH.execution.rlm-resilience-telemetry name: RLM Resilience + Structured Telemetry pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/telemetry.py doc: RLM Resilience + Structured Telemetry - id: AU-ORCH.execution.rlm-synthesis-failed-falling name: RLM synthesis failed, falling back to pillar: AU-ORCH status: live code_paths: - agent_utilities/core/config.py - agent_utilities/graph/parallel_engine.py - agent_utilities/models/execution_manifest.py doc: RLM synthesis failed, falling back to - id: AU-ORCH.execution.robust-multi-format-edit name: Robust multi-format edit-application engine with graduated fuzzy matching and a reflection loop pillar: AU-ORCH status: live code_paths: - agent_utilities/harness/__init__.py - agent_utilities/harness/edit_engine.py doc: Robust multi-format edit-application engine with graduated fuzzy matching and a reflection loop - id: AU-ORCH.execution.run-trace-status-tool name: the node carrying the pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/agent_digital_twin.py - agent_utilities/orchestration/manager.py doc: the node carrying the - id: AU-ORCH.execution.service-registry-initialization name: Service Registry Initialization pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/engine.py doc: Service Registry Initialization - id: AU-ORCH.execution.shape-policy-learning name: ───────────────────────────────────────── pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/agent_runner.py - agent_utilities/orchestration/execution_profile.py - agent_utilities/orchestration/outcome_router.py doc: ───────────────────────────────────────── - id: AU-ORCH.execution.shared-workboard name: Pydantic-Native Shared Workboard pillar: AU-ORCH status: live code_paths: - agent_utilities/models/graph.py doc: Pydantic-Native Shared Workboard - id: AU-ORCH.execution.skill-bound-server-tools name: a PACKAGE-BUNDLED skill exists to pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/agent_runner.py doc: a PACKAGE-BUNDLED skill exists to - id: AU-ORCH.execution.skill-utilization-provenance name: capture whether a pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/agent_runner.py doc: capture whether a - id: AU-ORCH.execution.skill-workflow-compilation name: Skill-to-Workflow Compilation pillar: AU-ORCH status: live code_paths: - agent_utilities/workflows/skill_compiler.py doc: Skill-to-Workflow Compilation - id: AU-ORCH.execution.subagent-pattern-variant name: AU-ORCH.execution.subagent-pattern-variant pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/subagent_patterns.py doc: AU-ORCH.execution.subagent-pattern-variant - id: AU-ORCH.execution.substrate-training-job-emission name: Substrate training-job emission pillar: AU-ORCH status: live code_paths: - agent_utilities/harness/agentic_evolution_engine.py - agent_utilities/harness/substrate_trainer.py doc: Substrate training-job emission - id: AU-ORCH.execution.swe-agent-system-prompt name: System prompt for the KG-grounded SWE agent pillar: AU-ORCH status: live code_paths: - agent_utilities/agent/swe_prompts.py - agent_utilities/orchestration/engine.py - agent_utilities/orchestration/swe_agent.py - agent_utilities/tools/tool_registry.py doc: System prompt for the KG-grounded SWE agent - id: AU-ORCH.execution.swe-workspace-tools name: SWE workspace tools pillar: AU-ORCH status: live code_paths: - agent_utilities/tools/swe_workspace_tools.py doc: SWE workspace tools - id: AU-ORCH.execution.task-aware-tool-selection name: a resolved fleet pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/agent_runner.py doc: a resolved fleet - id: AU-ORCH.execution.two-level-fair-rotation name: the one seam every recurring/background job pillar: AU-ORCH status: live code_paths: - agent_utilities/knowledge_graph/core/chunked_drain.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/core/task_lanes.py - agent_utilities/knowledge_graph/retrieval/ops_context.py - agent_utilities/observability/gateway_metrics.py doc: the one seam every recurring/background job - id: AU-ORCH.execution.typed-failure-classification name: classify the failure so the caller/optimizer gets a typed signal pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/repl.py - agent_utilities/rlm/runner.py doc: classify the failure so the caller/optimizer gets a typed signal - id: AU-ORCH.execution.unified-orchestration-protocol name: Unified Orchestration Protocol pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/protocol.py doc: Unified Orchestration Protocol - id: AU-ORCH.execution.visibility-allow-list name: Visibility allow-list of upstream step ids whose results pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/executor.py - agent_utilities/models/sdd.py doc: Visibility allow-list of upstream step ids whose results - id: AU-ORCH.execution.workflow-dag-validation name: AU-ORCH.execution.workflow-dag-validation pillar: AU-ORCH status: live code_paths: - agent_utilities/workflows/runner.py doc: AU-ORCH.execution.workflow-dag-validation - id: AU-ORCH.execution.workflow-engine-wiring name: wires the EXISTING pillar: AU-ORCH status: live code_paths: - agent_utilities/workflows/runner.py doc: wires the EXISTING - id: AU-ORCH.execution.workflow-lifecycle-management name: Named Workflow Execution. Loads the stored pillar: AU-ORCH status: live code_paths: - agent_utilities/knowledge_graph/ingestion/skill_workflow_ingest.py - agent_utilities/knowledge_graph/kb/x_workflows.py - agent_utilities/knowledge_graph/workflow_store.py - agent_utilities/models/sdd.py - agent_utilities/workflows/__init__.py - agent_utilities/workflows/localized_repair.py - agent_utilities/workflows/runner.py doc: Named Workflow Execution. Loads the stored - id: AU-ORCH.execution.workflow-parallel-bridge name: Workflow → ParallelEngine Bridge pillar: AU-ORCH status: live code_paths: - agent_utilities/workflows/runner.py doc: Workflow → ParallelEngine Bridge - id: AU-ORCH.execution.workflow-persistence-replay name: Workflow Persistence & Replay Relationships pillar: AU-ORCH status: live code_paths: - agent_utilities/knowledge_graph/workflow_store.py - agent_utilities/models/schema_definition.py doc: Workflow Persistence & Replay Relationships - id: AU-ORCH.optimization.checkpoint-recommendation-surface name: so every agent pillar: AU-ORCH status: live code_paths: - agent_utilities/agent/factory.py - agent_utilities/kvcache/tiering.py - agent_utilities/kvcache/worthiness.py doc: so every agent - id: AU-ORCH.optimization.graph-native-optimization-state name: Graph-Native Optimization State ────────────────────────── pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/gepa.py doc: Graph-Native Optimization State ────────────────────────── - id: AU-ORCH.optimization.kvcache-worthiness-policy name: Dynamic context-aware per-execution KV-cache-layering cache-worthiness policy pillar: AU-ORCH status: live code_paths: - agent_utilities/agent/sampling_profile.py - agent_utilities/kvcache/policy.py doc: Dynamic context-aware per-execution KV-cache-layering cache-worthiness policy - id: AU-ORCH.optimization.optimize-skill-prompt-gepa name: GEPA Reflective Prompt Optimizer pillar: AU-ORCH status: live code_paths: - agent_utilities/models/knowledge_graph.py - agent_utilities/rlm/gepa.py doc: GEPA Reflective Prompt Optimizer - id: AU-ORCH.optimization.proposer-strong-model name: the proposer is the STRONG model pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/gepa.py doc: the proposer is the STRONG model - id: AU-ORCH.optimization.provider name: AU-ORCH.optimization.provider pillar: AU-ORCH status: live code_paths: - agent_utilities/knowledge_graph/retrieval/context_compiler_serving.py doc: AU-ORCH.optimization.provider - id: AU-ORCH.optimization.provider-prompt-cache name: an exhaustive audit of this repo found no pillar: AU-ORCH status: live code_paths: - agent_utilities/agent/sampling_profile.py - agent_utilities/caching/prompt_cache.py - agent_utilities/graph/verification.py - agent_utilities/harness/trace_backend.py - agent_utilities/harness/tracing.py - agent_utilities/models/knowledge_graph.py - agent_utilities/observability/gateway_metrics.py - agent_utilities/orchestration/agent_runner.py - agent_utilities/rlm/repl.py - agent_utilities/skills/runtime_validation.py doc: an exhaustive audit of this repo found no - id: AU-ORCH.optimization.remote-concurrency-clamp name: so the adaptive ramp can NEVER push a fan-out pillar: AU-ORCH status: live code_paths: - agent_utilities/core/model_concurrency.py doc: so the adaptive ramp can NEVER push a fan-out - id: AU-ORCH.optimization.selection-on-unseen-data name: selection happens on UNSEEN data, so a candidate that merely memorized the pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/coordination.py - agent_utilities/harness/__init__.py - agent_utilities/harness/selection_operators.py - agent_utilities/harness/variant_pool.py - agent_utilities/rlm/dynamic_reward.py - agent_utilities/rlm/gepa.py doc: selection happens on UNSEEN data, so a candidate that merely memorized the - id: AU-ORCH.optimization.structured-prompting name: Structured Prompting pillar: AU-ORCH status: live code_paths: - agent_utilities/prompting/structured.py doc: Structured Prompting - id: AU-ORCH.optimization.workflow-distillation name: Workflow Distillation Integration pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/verification.py - agent_utilities/harness/evolve_agent.py doc: Workflow Distillation Integration - id: AU-ORCH.org.recruiter name: Drafts departments → roles from the goal pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/org_runtime.py doc: Drafts departments → roles from the goal - id: AU-ORCH.org.repository-workitem-authority name: Durable repository-development WorkItem authority pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/repository_work_item.py doc: Durable repository-development WorkItem authority - id: AU-ORCH.org.work-item-dag name: AU-ORCH.org.work-item-dag pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/org_runtime.py doc: AU-ORCH.org.work-item-dag - id: AU-ORCH.planning.business-process-to-executable name: structure-driven compilation pillar: AU-ORCH status: live code_paths: - agent_utilities/knowledge_graph/process_plan_compiler.py doc: structure-driven compilation - id: AU-ORCH.planning.planner-step name: Planner Step pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/hierarchical_planner.py doc: Planner Step - id: AU-ORCH.planning.rap-mcts-backpropagation name: AU-ORCH.planning.rap-mcts-backpropagation pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/reasoning/rap.py doc: AU-ORCH.planning.rap-mcts-backpropagation - id: AU-ORCH.planning.reasoning-graph-topologies name: reasoning algorithms as versioned graph topologies pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/reasoning/__init__.py - agent_utilities/graph/reasoning/budgets.py - agent_utilities/graph/reasoning/cot.py - agent_utilities/graph/reasoning/got.py - agent_utilities/graph/reasoning/rap.py - agent_utilities/graph/reasoning/react.py - agent_utilities/graph/reasoning/state.py - agent_utilities/graph/reasoning/topology.py - agent_utilities/graph/reasoning/tot.py - agent_utilities/mcp/tools/agent_execution_tools.py - agent_utilities/models/knowledge_graph.py doc: reasoning algorithms as versioned graph topologies - id: AU-ORCH.planning.recursion-nesting-depth name: Current nesting depth for recursive graph orchestration pillar: AU-ORCH status: live code_paths: - agent_utilities/core/checkpoint/manager.py - agent_utilities/graph/executor.py - agent_utilities/graph/hierarchical_planner.py - agent_utilities/graph/horizon_curriculum.py - agent_utilities/graph/nodes.py - agent_utilities/graph/routing/strategies/llm_planner.py - agent_utilities/graph/state.py - agent_utilities/graph/verification.py - agent_utilities/harness/variant_pool.py - agent_utilities/models/knowledge_graph.py - agent_utilities/models/sdd.py - agent_utilities/patterns/__init__.py - agent_utilities/patterns/prioritization.py - agent_utilities/patterns/prompt_chain.py - agent_utilities/rlm/hook.py - agent_utilities/tools/db_tools.py doc: Current nesting depth for recursive graph orchestration - id: AU-ORCH.planning.repo-map-skeleton name: Token-budgeted, importance-ranked repo-map skeleton for compact context injection pillar: AU-ORCH status: live code_paths: - agent_utilities/models/codemap.py - agent_utilities/server/models.py doc: Token-budgeted, importance-ranked repo-map skeleton for compact context injection - id: AU-ORCH.planning.sdd-pipeline name: Spec-Driven Development Pipeline pillar: AU-ORCH status: live code_paths: - agent_utilities/sdd/orchestrator.py doc: Spec-Driven Development Pipeline - id: AU-ORCH.planning.sdd-task-ergonomics name: Task-management ergonomics on SDD with complexity scoring, dependency-aware next-task, scope and tags pillar: AU-ORCH status: live code_paths: - agent_utilities/mcp/harness_server.py - agent_utilities/models/sdd.py - agent_utilities/sdd/__init__.py doc: Task-management ergonomics on SDD with complexity scoring, dependency-aware next-task, scope and tags - id: AU-ORCH.reactive.action-dispatcher name: Action dispatcher pillar: AU-ORCH status: live code_paths: - agent_utilities/runtime/bridge.py doc: Action dispatcher - id: AU-ORCH.reactive.action-observation-protocol name: Action/Observation event protocol for the developer-workspace runtime pillar: AU-ORCH status: live code_paths: - agent_utilities/runtime/events.py doc: Action/Observation event protocol for the developer-workspace runtime - id: AU-ORCH.reactive.behavioral-event-dispatcher name: Asynchronous Behavioral Event Dispatcher pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/reactive/dispatcher.py doc: Asynchronous Behavioral Event Dispatcher - id: AU-ORCH.reactive.event-sourcing-ledger name: Graph-Native Reactive Event Sourcing and OS Guardrails pillar: AU-ORCH status: live code_paths: - agent_utilities/__init__.py - agent_utilities/graph/__init__.py - agent_utilities/graph/reactive/__init__.py - agent_utilities/graph/reactive/ledger.py - agent_utilities/knowledge_graph/core/event_backend.py - agent_utilities/knowledge_graph/core/kafka_queue_backend.py - agent_utilities/knowledge_graph/core/queue_backend.py doc: Graph-Native Reactive Event Sourcing and OS Guardrails - id: AU-ORCH.reactive.runtime-events name: AU-ORCH.reactive.runtime-events pillar: AU-ORCH status: live code_paths: - agent_utilities/runtime/events.py doc: AU-ORCH.reactive.runtime-events - id: AU-ORCH.routing.adaptive-role-routing name: route adaptively from the learned per-role confidence pillar: AU-ORCH status: live code_paths: - agent_utilities/core/model_factory.py - agent_utilities/core/model_router.py doc: route adaptively from the learned per-role confidence - id: AU-ORCH.routing.altitude-description name: describe the actual altitude pillar: AU-ORCH status: live code_paths: - agent_utilities/messaging/router.py doc: describe the actual altitude - id: AU-ORCH.routing.chat-budget-routing name: surface the graceful message. Only a non-timeout pillar: AU-ORCH status: live code_paths: - agent_utilities/messaging/router.py doc: surface the graceful message. Only a non-timeout - id: AU-ORCH.routing.conductor-per-step-model name: a Conductor-assigned per-step model_id wins over both the pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/executor.py - agent_utilities/graph/routing/strategies/llm_planner.py - agent_utilities/models/model_registry.py - agent_utilities/models/sdd.py - agent_utilities/rlm/roles.py doc: a Conductor-assigned per-step model_id wins over both the - id: AU-ORCH.routing.confidence-gated-routing-log name: tier helpers ──────────────────────────────────────────── pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/state.py - agent_utilities/models/model_registry.py doc: tier helpers ──────────────────────────────────────────── - id: AU-ORCH.routing.confidence-signal-forwarding name: confidence-gated routing. Otherwise falls back to the pillar: AU-ORCH status: live code_paths: - agent_utilities/core/resource_optimizer.py doc: confidence-gated routing. Otherwise falls back to the - id: AU-ORCH.routing.depth-tiered-sampling name: depth-tiered sampling. The root is the strong reasoner pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/repl.py doc: depth-tiered sampling. The root is the strong reasoner - id: AU-ORCH.routing.emergent-specialization-discovery-pass name: an emergent-specialization discovery pass that clusters the failing or expensive task stream and proposes a new specialist archetype for any niche no existing archetype covers, so the collective autonomously increases its division of labour pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/specialization_discovery.py doc: an emergent-specialization discovery pass that clusters the failing or expensive task stream and proposes a new specialist archetype for any niche no existing archetype covers, so the collective autonomously increases its division of labour - id: AU-ORCH.routing.filtered-specialist-injection name: Filtered specialist injection for prompt bloat reduction pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/_router_impl.py doc: Filtered specialist injection for prompt bloat reduction - id: AU-ORCH.routing.functional-role-resolution name: the model-tier hint this step ran pillar: AU-ORCH status: live code_paths: - agent_utilities/core/model_factory.py - agent_utilities/models/sdd.py - agent_utilities/workflows/runner.py doc: the model-tier hint this step ran - id: AU-ORCH.routing.kg-specialist-estimation name: KG-Driven Specialist Estimation pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/subagent_patterns.py doc: KG-Driven Specialist Estimation - id: AU-ORCH.routing.load-shedding-backoff name: back off while the server is shedding load pillar: AU-ORCH status: live code_paths: - agent_utilities/core/config.py - agent_utilities/core/embedding_failover.py - agent_utilities/core/model_circuit_breaker.py - agent_utilities/core/model_concurrency.py doc: back off while the server is shedding load - id: AU-ORCH.routing.mcp-child-error-unwrap name: when a remote MCP child fails, anyio wraps the real cause pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/_router_impl.py - agent_utilities/orchestration/agent_runner.py doc: when a remote MCP child fails, anyio wraps the real cause - id: AU-ORCH.routing.offload-sync-roundtrip name: the pre-LLM discovery below is several SYNCHRONOUS engine pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/_router_impl.py - agent_utilities/graph/executor.py - agent_utilities/graph/hierarchical_planner.py - agent_utilities/graph/verification.py - agent_utilities/orchestration/agent_runner.py - agent_utilities/orchestration/engine.py doc: the pre-LLM discovery below is several SYNCHRONOUS engine - id: AU-ORCH.routing.optional-role-override name: optional role→ pillar: AU-ORCH status: live code_paths: - agent_utilities/core/config.py doc: optional role→ - id: AU-ORCH.routing.original-rule-was-far name: the original rule was far too narrow pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/routing/strategies/fast_path.py doc: the original rule was far too narrow - id: AU-ORCH.routing.rejected-candidate-provenance name: a routing decision must record enough to be a real pillar: AU-ORCH status: live code_paths: - agent_utilities/core/model_factory.py - agent_utilities/core/model_router.py - agent_utilities/harness/trace_backend.py - agent_utilities/models/knowledge_graph.py - agent_utilities/models/model_registry.py doc: a routing decision must record enough to be a real - id: AU-ORCH.routing.resolve-body-single-canonical name: resolve the body via the single canonical resolver so pillar: AU-ORCH status: live code_paths: - agent_utilities/agent/registry_builder.py - agent_utilities/core/workspace.py - agent_utilities/messaging/bus.py - agent_utilities/orchestration/action_policy.py - agent_utilities/prompting/builder.py - agent_utilities/prompting/structured.py doc: resolve the body via the single canonical resolver so - id: AU-ORCH.routing.route-inference-parameters name: the inference-parameter bundle for this route, picked from the pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/adaptive_agent_router.py doc: the inference-parameter bundle for this route, picked from the - id: AU-ORCH.routing.route-outcome-feedback name: a model-route outcome also trains the adaptive router pillar: AU-ORCH status: live code_paths: - agent_utilities/knowledge_graph/adaptation/feedback.py doc: a model-route outcome also trains the adaptive router - id: AU-ORCH.routing.sampling-profile-selection name: Task-aware per-call LLM sampling that selects and threads a SamplingProfile of temperature top_p top_k min_p repetition_penalty max_tokens and penalties per question by task-class and role pillar: AU-ORCH status: live code_paths: - agent_utilities/agent/factory.py - agent_utilities/agent/sampling_profile.py - agent_utilities/gateway/ontology_api.py - agent_utilities/mcp/tools/ontology_tools.py - agent_utilities/models/model_registry.py doc: Task-aware per-call LLM sampling that selects and threads a SamplingProfile of temperature top_p top_k min_p repetition_penalty max_tokens and penalties per question by task-class and role - id: AU-ORCH.routing.single-router-edge name: the router has a SINGLE outgoing edge pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/builder.py doc: the router has a SINGLE outgoing edge - id: AU-ORCH.routing.structural-build-reuse name: cache the built graph TOPOLOGY per routing-config. The topology + pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/builder.py doc: cache the built graph TOPOLOGY per routing-config. The topology + - id: AU-ORCH.routing.topological-routing name: Topological Routing pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/adaptive_agent_router.py doc: Topological Routing - id: AU-ORCH.routing.topology-escalation-policy name: AU-ORCH.routing.topology-escalation-policy pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/reasoning/policy.py doc: AU-ORCH.routing.topology-escalation-policy - id: AU-ORCH.routing.transition-state-checkpoint name: subtask-spec + wide-search instructions — owned by pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/_router_impl.py doc: subtask-spec + wide-search instructions — owned by - id: AU-ORCH.routing.uno-orchestra-derived name: Derived from Uno-Orchestra pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/adaptive_agent_router.py doc: Derived from Uno-Orchestra - id: AU-ORCH.routing.virtual-agent-economy-task name: a virtual-agent-economy task allocator that runs a capability-gated second-price auction so a collective self-organizes who does what via price signals instead of static role routing, surfacing scarcity and value pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/agent_market.py doc: a virtual-agent-economy task allocator that runs a capability-gated second-price auction so a collective self-organizes who does what via price signals instead of static role routing, surfacing scarcity and value - id: AU-ORCH.runvcs.event-kernel name: content-addressed, typed, projectable run-event log pillar: AU-ORCH status: live code_paths: - agent_utilities/models/knowledge_graph.py - agent_utilities/runtime/run_vcs/__init__.py - agent_utilities/runtime/run_vcs/kernel.py doc: content-addressed, typed, projectable run-event log - id: AU-ORCH.runvcs.fork-revert name: fork/revert a *live* run from any commit pillar: AU-ORCH status: live code_paths: - agent_utilities/runtime/run_vcs/run_session.py doc: fork/revert a *live* run from any commit - id: AU-ORCH.runvcs.retained-output-gate name: hold a run pillar: AU-ORCH status: live code_paths: - agent_utilities/models/knowledge_graph.py - agent_utilities/orchestration/action_policy.py - agent_utilities/runtime/run_vcs/retained_output.py doc: hold a run - id: AU-ORCH.runvcs.run-commit name: carrier-style copy-on-write process+filesystem snapshot pillar: AU-ORCH status: live code_paths: - agent_utilities/mcp/tools/state_tools.py - agent_utilities/models/knowledge_graph.py - agent_utilities/rlm/sandboxes/base.py - agent_utilities/runtime/run_vcs/carrier.py - agent_utilities/runtime/run_vcs/run_commit.py doc: carrier-style copy-on-write process+filesystem snapshot - id: AU-ORCH.runvcs.trace-replay name: deterministic trace replay over the event log pillar: AU-ORCH status: live code_paths: - agent_utilities/runtime/run_vcs/replay.py doc: deterministic trace replay over the event log - id: AU-ORCH.sandbox.adaptive-tier-selection name: adaptive sandbox-tier selection via a reward-EMA over rungs pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/sandboxes/reward.py doc: adaptive sandbox-tier selection via a reward-EMA over rungs - id: AU-ORCH.sandbox.compiled-orchestration-kernel name: Compiled Orchestration Kernel pillar: AU-ORCH status: live code_paths: - agent_utilities/core/__init__.py - agent_utilities/core/wasm_runner.py - agent_utilities/knowledge_graph/core/graph_compute.py doc: Compiled Orchestration Kernel - id: AU-ORCH.sandbox.computer-use-tier name: Computer-use driver tier for the workspace runtime pillar: AU-ORCH status: live code_paths: - agent_utilities/runtime/computer_use_tier.py doc: Computer-use driver tier for the workspace runtime - id: AU-ORCH.sandbox.container-fork-sandbox name: container_fork sandbox pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/sandboxes/container_fork_backend.py doc: container_fork sandbox - id: AU-ORCH.sandbox.cpython-wasi-sandbox name: CPython-WASI sandbox pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/sandboxes/wasm_backend.py doc: CPython-WASI sandbox - id: AU-ORCH.sandbox.crossmodal-fork-fanout name: warm-fork fan-out over an engine cross-modal candidate set pillar: AU-ORCH status: live code_paths: - agent_utilities/mcp/tools/engine_surface_tools.py - agent_utilities/runtime/crossmodal_fork.py doc: warm-fork fan-out over an engine cross-modal candidate set - id: AU-ORCH.sandbox.default-sandbox-registry name: Default sandbox registry pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/sandboxes/registry.py doc: Default sandbox registry - id: AU-ORCH.sandbox.forkd-backed-microvm-strongest name: forkd-backed microVM, the strongest-isolation rung pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/sandboxes/firecracker_backend.py - agent_utilities/rlm/sandboxes/registry.py doc: forkd-backed microVM, the strongest-isolation rung - id: AU-ORCH.sandbox.graph-sandbox-surface name: CONCEPT pillar: AU-ORCH status: live code_paths: - agent_utilities/mcp/tools/state_tools.py doc: CONCEPT - id: AU-ORCH.sandbox.native-warm-fork-os name: forkserver sandbox pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/sandboxes/forkserver_backend.py doc: forkserver sandbox - id: AU-ORCH.sandbox.rung-escalation name: when supplied, a persistently pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/sandboxes/router.py doc: when supplied, a persistently - id: AU-ORCH.sandbox.rung-reward-ema name: feed the per-rung reward EMA so a persistently failing rung is pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/repl.py doc: feed the per-rung reward EMA so a persistently failing rung is - id: AU-ORCH.sandbox.sandbox-selection name: sandbox selection pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/config.py doc: sandbox selection - id: AU-ORCH.sandbox.shared-host-helper-bridge name: Shared host-helper bridge for isolated sandbox backends pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/sandboxes/_bridge.py - agent_utilities/rlm/sandboxes/base.py - agent_utilities/runtime/crossmodal_fork.py doc: Shared host-helper bridge for isolated sandbox backends - id: AU-ORCH.sandbox.stateless-reaper-backstop name: strict zombie protection. A warm container is labelled so a stateless sweep pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/sandboxes/container_fork_backend.py doc: strict zombie protection. A warm container is labelled so a stateless sweep - id: AU-ORCH.sandbox.tiered-rlm-sandbox name: Tiered RLM code sandbox with a uniform Sandbox contract and capability routing pillar: AU-ORCH status: live code_paths: - agent_utilities/knowledge_graph/research/change_synthesis.py - agent_utilities/rlm/repl.py - agent_utilities/rlm/sandboxes/__init__.py - agent_utilities/rlm/sandboxes/analyzer.py - agent_utilities/rlm/sandboxes/base.py - agent_utilities/rlm/sandboxes/docker_backend.py - agent_utilities/rlm/sandboxes/local_backend.py - agent_utilities/rlm/sandboxes/monty_backend.py - agent_utilities/rlm/sandboxes/router.py - agent_utilities/rlm/telemetry.py doc: Tiered RLM code sandbox with a uniform Sandbox contract and capability routing - id: AU-ORCH.sandbox.warm-parent-lifetime-cap name: a HARD wall-clock lifetime cap. A warm parent older than this is reaped even pillar: AU-ORCH status: live code_paths: - agent_utilities/runtime/warm_registry.py doc: a HARD wall-clock lifetime cap. A warm parent older than this is reaped even - id: AU-ORCH.sandbox.warmforkfanoutcapability name: A rung pays warm-up once for a pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/sandboxes/base.py - agent_utilities/runtime/warm_registry.py doc: A rung pays warm-up once for a - id: AU-ORCH.sandbox.wasm-backend name: AU-ORCH.sandbox.wasm-backend pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/sandboxes/wasm_backend.py doc: AU-ORCH.sandbox.wasm-backend - id: AU-ORCH.scheduling.acquisition-lane-fairness name: reserve a small floor of pillar: AU-ORCH status: live code_paths: - agent_utilities/core/resource_priority.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/core/kafka_queue_backend.py - agent_utilities/knowledge_graph/core/task_lanes.py - agent_utilities/knowledge_graph/ingest_worker.py - agent_utilities/mcp/kg_server.py doc: reserve a small floor of - id: AU-ORCH.scheduling.also-fold-vllm-scheduler name: the vLLM scheduler pillar: AU-ORCH status: live code_paths: - agent_utilities/core/model_factory.py - agent_utilities/core/resource_priority.py doc: the vLLM scheduler - id: AU-ORCH.scheduling.analysis-lane name: the LLM-extraction / deep-analysis phase is its OWN lane pillar: AU-ORCH status: live code_paths: - agent_utilities/knowledge_graph/core/task_lanes.py doc: the LLM-extraction / deep-analysis phase is its OWN lane - id: AU-ORCH.scheduling.claim-pacing-backpressure name: AU-ORCH.scheduling.claim-pacing-backpressure pillar: AU-ORCH status: live code_paths: - agent_utilities/knowledge_graph/core/work_durability.py - agent_utilities/orchestration/claim_pacing.py doc: AU-ORCH.scheduling.claim-pacing-backpressure - id: AU-ORCH.scheduling.connector-sync-lane name: external connector delta syncs pillar: AU-ORCH status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/core/task_lanes.py doc: external connector delta syncs - id: AU-ORCH.scheduling.hard-io-deadline name: the fleet MCP tool-schema probe pillar: AU-ORCH status: live code_paths: - agent_utilities/core/schedule_engine.py - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/protocols/source_connectors/connectors/mcp_package.py doc: the fleet MCP tool-schema probe - id: AU-ORCH.scheduling.low-value-high-volume name: then pillar: AU-ORCH status: live code_paths: - agent_utilities/knowledge_graph/core/task_lanes.py - agent_utilities/knowledge_graph/core/worker_scheduler.py doc: then - id: AU-ORCH.scheduling.quiet-period-preference name: D-OB-10 pillar: AU-ORCH status: live code_paths: - agent_utilities/core/resource_priority.py doc: D-OB-10 - id: AU-ORCH.scheduling.resource-priority-edict name: the autonomous goal loop is pillar: AU-ORCH status: live code_paths: - agent_utilities/core/resource_priority.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/ingestion/engine.py - agent_utilities/knowledge_graph/kb/extraction_run.py - agent_utilities/knowledge_graph/neural/embedding_store.py - agent_utilities/knowledge_graph/ontology/permissioning.py - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/knowledge_graph/retrieval/hybrid_retriever.py - agent_utilities/kvcache/policy.py - agent_utilities/mcp/kg_server.py - agent_utilities/orchestration/agent_dispatch_worker.py - agent_utilities/orchestration/manager.py doc: the autonomous goal loop is - id: AU-ORCH.scheduling.rlm-evolution-loop name: RLM for AHE Evolution Loop pillar: AU-ORCH status: live code_paths: - agent_utilities/harness/evolve_agent.py doc: RLM for AHE Evolution Loop - id: AU-ORCH.scheduling.soft-timeout-lease-quarantine name: a claimed task that has already pillar: AU-ORCH status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py doc: a claimed task that has already - id: AU-ORCH.scheduling.ticket-workflow-playbook name: Ticket-driven workflow playbook pillar: AU-ORCH status: live code_paths: - agent_utilities/knowledge_graph/adaptation/fleet_event_triage.py - agent_utilities/knowledge_graph/adaptation/ticket_playbooks.py doc: Ticket-driven workflow playbook - id: AU-ORCH.session.carry-invoker name: carry the invoker pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/agent_runner.py doc: carry the invoker - id: AU-ORCH.session.durable-goal-registry-goals name: Durable goal registry — goals persist across restarts and expired leases remain visible instead of silently vanishing pillar: AU-ORCH status: live code_paths: - agent_utilities/core/sessions.py - agent_utilities/models/goal.py doc: Durable goal registry — goals persist across restarts and expired leases remain visible instead of silently vanishing - id: AU-ORCH.session.durable-session-autonomous-goal name: Durable session and autonomous goal persistence with iterative background goal loops pillar: AU-ORCH status: live code_paths: - agent_utilities/core/sessions.py doc: Durable session and autonomous goal persistence with iterative background goal loops - id: AU-ORCH.session.escalate-breached-goals name: escalate breached goals pillar: AU-ORCH status: live code_paths: - agent_utilities/core/goal_sla.py - agent_utilities/core/sessions.py - agent_utilities/knowledge_graph/core/engine_tasks.py doc: escalate breached goals - id: AU-ORCH.session.invoker-agent-handoff name: Invoker→spawned-agent handoff of curated context, token budget, tool scope and credential reference pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/_router_impl.py - agent_utilities/graph/executor.py - agent_utilities/graph/state.py - agent_utilities/knowledge_graph/core/engine.py - agent_utilities/mcp/tools/query_tools.py - agent_utilities/orchestration/engine.py - agent_utilities/orchestration/manager.py doc: Invoker→spawned-agent handoff of curated context, token budget, tool scope and credential reference - id: AU-ORCH.session.session-anchored-collections-native name: Session-anchored collections and native invoker↔spawned-agent message channels pillar: AU-ORCH status: live code_paths: - agent_utilities/graph/executor.py - agent_utilities/graph/state.py - agent_utilities/mcp/tools/query_tools.py - agent_utilities/messaging/agent_channel.py - agent_utilities/models/agent.py - agent_utilities/orchestration/agent_runner.py - agent_utilities/orchestration/engine.py - agent_utilities/orchestration/session_continuity.py doc: Session-anchored collections and native invoker↔spawned-agent message channels - id: AU-ORCH.session.session-continuity-entrypoint name: Unified Agent Entrypoint pillar: AU-ORCH status: live code_paths: - agent_utilities/orchestration/session_continuity.py doc: Unified Agent Entrypoint - id: AU-ORCH.session.structured-subagent-contracts name: structured subagent contracts pillar: AU-ORCH status: live code_paths: - agent_utilities/rlm/repl.py doc: structured subagent contracts - id: AU-ORCH.session.unified-agent-entrypoint name: Unified Agent Entrypoint pillar: AU-ORCH status: live code_paths: - agent_utilities/__main__.py doc: Unified Agent Entrypoint - id: AU-ORCH.twin.agent-digital-twin name: Agent Digital Twin + deterministic replay pillar: AU-ORCH status: live code_paths: - agent_utilities/mcp/tools/state_tools.py - agent_utilities/orchestration/agent_digital_twin.py doc: Agent Digital Twin + deterministic replay - id: AU-OS.audit.config-staleness-auditor name: Configuration Staleness Auditor pillar: AU-OS status: live code_paths: - agent_utilities/ecosystem/config_staleness_auditor.py doc: Configuration Staleness Auditor - id: AU-OS.audit.recursive-improvement-velocity-tracker name: recursive-improvement velocity tracker that surfaces whether the loop is still improving and flags a non-positive derivative as a research-gets-harder signal pillar: AU-OS status: live code_paths: - agent_utilities/knowledge_graph/research/improvement_ledger.py doc: recursive-improvement velocity tracker that surfaces whether the loop is still improving and flags a non-positive derivative as a research-gets-harder signal - id: AU-OS.config.agent-os-infrastructure name: Agent OS Infrastructure pillar: AU-OS status: live code_paths: - agent_utilities/core/paths.py doc: Agent OS Infrastructure - id: AU-OS.config.agent-registry name: Agent Registry pillar: AU-OS status: live code_paths: - agent_utilities/core/registry/package_adapter.py - agent_utilities/core/registry/package_types.py doc: Agent Registry - id: AU-OS.config.autonomous-spec-develop-off name: autonomous spec→develop. OFF by default = review-first pillar: AU-OS status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/research/spec_proposals.py - agent_utilities/mcp/tools/state_tools.py - agent_utilities/orchestration/action_policy.py doc: autonomous spec→develop. OFF by default = review-first - id: AU-OS.config.data-type-conversion name: Data Type Conversion pillar: AU-OS status: live code_paths: - agent_utilities/base_utilities.py doc: Data Type Conversion - id: AU-OS.config.desired-state-fleet-reconciler name: Desired-state fleet reconciler pillar: AU-OS status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/research/change_publisher.py - agent_utilities/orchestration/action_policy.py - agent_utilities/orchestration/fleet_actuation.py - agent_utilities/orchestration/fleet_observation.py - agent_utilities/orchestration/fleet_reconciler.py doc: Desired-state fleet reconciler - id: AU-OS.config.dynamic-env-family name: a general, INSPECTABLE escape hatch for env pillar: AU-OS status: live code_paths: - agent_utilities/core/transport_security.py - agent_utilities/mcp/check_env_var_drift.py doc: a general, INSPECTABLE escape hatch for env - id: AU-OS.config.env-var-drift-guard name: Env-var drift guard pillar: AU-OS status: live code_paths: - agent_utilities/mcp/check_env_var_drift.py - agent_utilities/mcp/readme_mcp_examples.py doc: Env-var drift guard - id: AU-OS.config.env-var-single-source name: Env-var single source of truth pillar: AU-OS status: live code_paths: - agent_utilities/mcp/env_policy.py - agent_utilities/mcp/env_sources.py doc: Env-var single source of truth - id: AU-OS.config.fleet-event-ingress name: Fleet Event Ingress pillar: AU-OS status: live code_paths: - agent_utilities/core/config.py - agent_utilities/gateway/fleet.py - agent_utilities/gateway/fleet_events.py - agent_utilities/knowledge_graph/adaptation/failure_analyzer.py - agent_utilities/knowledge_graph/adaptation/fleet_event_triage.py - agent_utilities/knowledge_graph/core/engine_tasks.py doc: Fleet Event Ingress - id: AU-OS.config.fleet-xdg-standardization name: fleet XDG config standardization pillar: AU-OS status: live code_paths: - agent_utilities/core/config.py doc: fleet XDG config standardization - id: AU-OS.config.gateway-service-dashboard name: Gateway Service Dashboard pillar: AU-OS status: live code_paths: - agent_utilities/core/paths.py - agent_utilities/gateway/__init__.py - agent_utilities/gateway/aggregator.py - agent_utilities/gateway/api.py - agent_utilities/gateway/config.py - agent_utilities/gateway/models.py - agent_utilities/gateway/registry.py - agent_utilities/gateway/widgets/_optional_client.py - agent_utilities/gateway/widgets/base.py doc: Gateway Service Dashboard - id: AU-OS.config.health-gated-deploy-rollback name: Health-gated deploy and rollback watch where every deploy or restart the autonomy plane triggers is followed by a durable health watch whose failure invokes a policy-gated rollback and escalation pillar: AU-OS status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/orchestration/deploy_watch.py doc: Health-gated deploy and rollback watch where every deploy or restart the autonomy plane triggers is followed by a durable health watch whose failure invokes a policy-gated rollback and escalation - id: AU-OS.config.model-factory-passthrough name: Returns the model UNCHANGED when no sink is installed pillar: AU-OS status: live code_paths: - agent_utilities/core/model_factory.py - agent_utilities/gateway/daemon.py - agent_utilities/harness/trace_backend.py - agent_utilities/harness/tracing.py - agent_utilities/knowledge_graph/research/candidate_insight.py - agent_utilities/mcp/tools/engine_surface_tools.py - agent_utilities/models/knowledge_graph.py doc: Returns the model UNCHANGED when no sink is installed - id: AU-OS.config.secrets-authentication name: Topological Vulnerability Scanner pillar: AU-OS status: live code_paths: - agent_utilities/__init__.py - agent_utilities/capabilities/stuck_loop.py - agent_utilities/core/config.py - agent_utilities/core/decorators.py - agent_utilities/core/exceptions.py - agent_utilities/deployment/doctor.py - agent_utilities/graph/state.py - agent_utilities/harness/tracing.py - agent_utilities/models/knowledge_graph.py - agent_utilities/models/schema_definition.py - agent_utilities/observability/approval_manager.py - agent_utilities/observability/audit_logger.py - agent_utilities/observability/custom_observability.py - agent_utilities/observability/mermaid.py - agent_utilities/protocols/a2a_config.py - agent_utilities/security/__init__.py - agent_utilities/security/auth.py - agent_utilities/security/browser_auth.py - agent_utilities/security/cli.py - agent_utilities/security/oauth_client_credentials.py - agent_utilities/security/secrets_client.py - agent_utilities/security/xai_auth.py doc: Topological Vulnerability Scanner - id: AU-OS.config.source-credential-registry name: Typed Source-Credential Registry pillar: AU-OS status: live code_paths: - agent_utilities/security/__init__.py - agent_utilities/security/source_credentials.py doc: Typed Source-Credential Registry - id: AU-OS.config.two-surfaces-by-default name: A tool that can change pillar: AU-OS status: live code_paths: - agent_utilities/core/config_admin.py - agent_utilities/mcp/tool_specs.py - agent_utilities/mcp/tools/config_tools.py - agent_utilities/observability/runtime_health.py - agent_utilities/orchestration/action_policy.py - agent_utilities/security/config_sensitivity.py doc: A tool that can change - id: AU-OS.config.xai-social-credentials name: X/Grok social search needs xAI credentials pillar: AU-OS status: live code_paths: - agent_utilities/tools/tool_registry.py doc: X/Grok social search needs xAI credentials - id: AU-OS.context.nested-instructions name: Nested Subfolder Instructions pillar: AU-OS status: live code_paths: - agent_utilities/nested_context.py doc: Nested Subfolder Instructions - id: AU-OS.deployment.agent-factory-autoload name: the agent factory loads flat pillar: AU-OS status: live code_paths: - agent_utilities/cli/__init__.py - agent_utilities/deployment/doctor.py - agent_utilities/protocols/source_connectors/connectors/mcp_tool.py doc: the agent factory loads flat - id: AU-OS.deployment.airgap-mode name: create_async_http_client applies the pillar: AU-OS status: live code_paths: - agent_utilities/core/config.py - agent_utilities/core/http_client.py - agent_utilities/core/model_factory.py doc: create_async_http_client applies the - id: AU-OS.deployment.concept-2 name: ───────────── pillar: AU-OS status: live code_paths: - agent_utilities/deployment/repo_templates.py doc: ───────────── - id: AU-OS.deployment.connector-coverage-check name: AU-OS.deployment.connector-coverage-check pillar: AU-OS status: live code_paths: - agent_utilities/deployment/doctor.py - agent_utilities/knowledge_graph/ingestion/connector_coverage.py doc: AU-OS.deployment.connector-coverage-check - id: AU-OS.deployment.cross-platform-locks-plus name: Cross-platform locks plus per-OS process spawn, endpoints and doctor hints pillar: AU-OS status: live code_paths: - agent_utilities/deployment/preflight.py - agent_utilities/knowledge_graph/core/file_lock.py - agent_utilities/knowledge_graph/core/shard_topology.py doc: Cross-platform locks plus per-OS process spawn, endpoints and doctor hints - id: AU-OS.deployment.dynamic-two-fail-closed name: Dynamic two-layer fail-closed PreToolUse ActionPolicy permission gate pillar: AU-OS status: live code_paths: - agent_utilities/claude_harness/__init__.py - agent_utilities/claude_harness/pretooluse_gate.py - agent_utilities/cli/__init__.py - agent_utilities/ecosystem/hook_installer.py - agent_utilities/orchestration/action_policy.py doc: Dynamic two-layer fail-closed PreToolUse ActionPolicy permission gate - id: AU-OS.deployment.embedded-auto-provision name: embedded auto-provision. For a server that has no remote pillar: AU-OS status: live code_paths: - agent_utilities/knowledge_graph/core/graph_compute.py - agent_utilities/server/__init__.py doc: embedded auto-provision. For a server that has no remote - id: AU-OS.deployment.engine-resolver-auto-provision name: One engine resolver auto-provisioning every entrypoint by precedence remote then share-running-local then autostart-shared-supervised pillar: AU-OS status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/core/engine_resolver.py - agent_utilities/knowledge_graph/core/graph_compute.py - agent_utilities/mcp/tools/engine_surface_tools.py doc: One engine resolver auto-provisioning every entrypoint by precedence remote then share-running-local then autostart-shared-supervised - id: AU-OS.deployment.flagging-repos name: flagging repos pillar: AU-OS status: live code_paths: - agent_utilities/deployment/doctor.py - agent_utilities/knowledge_graph/ingestion/coverage.py - agent_utilities/knowledge_graph/ingestion/manifest.py doc: flagging repos - id: AU-OS.deployment.fleet-lifecycle-control name: Allowed ⇒ actuate + schedule an pillar: AU-OS status: live code_paths: - agent_utilities/core/config.py - agent_utilities/gateway/fleet.py - agent_utilities/knowledge_graph/adaptation/remediation_playbooks.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/research/auto_merge.py - agent_utilities/knowledge_graph/research/change_publisher.py - agent_utilities/orchestration/fleet_actuation.py - agent_utilities/orchestration/fleet_autoscaler.py - agent_utilities/orchestration/fleet_reconciler.py - agent_utilities/runtime/policy.py doc: Allowed ⇒ actuate + schedule an - id: AU-OS.deployment.genesis-environment-profiles name: see pillar: AU-OS status: live code_paths: - agent_utilities/deployment/genesis_environments.py doc: see - id: AU-OS.deployment.governance-derived-claude-code name: Governance-derived Claude Code permission-fence generator pillar: AU-OS status: live code_paths: - agent_utilities/claude_harness/__init__.py - agent_utilities/claude_harness/claude_fence.py - agent_utilities/cli/__init__.py - agent_utilities/deployment/cli.py doc: Governance-derived Claude Code permission-fence generator - id: AU-OS.deployment.infrastructure-blueprint-library name: Infrastructure Blueprint Library pillar: AU-OS status: live code_paths: - agent_utilities/models/company.py - agent_utilities/models/knowledge_graph.py doc: Infrastructure Blueprint Library - id: AU-OS.deployment.lakehouse-doctor name: ── pillar: AU-OS status: live code_paths: - agent_utilities/core/config.py - agent_utilities/deployment/doctor.py doc: ── - id: AU-OS.deployment.liveness-vs-readiness-split name: see the callers pillar: AU-OS status: live code_paths: - agent_utilities/gateway/api.py - agent_utilities/mcp/kg_server.py - agent_utilities/observability/runtime_health.py - agent_utilities/server/routers/core.py doc: see the callers - id: AU-OS.deployment.merge-triggered-venv-flip name: AU-OS.deployment.merge-triggered-venv-flip pillar: AU-OS status: live code_paths: - agent_utilities/deployment/venv_autosync.py doc: AU-OS.deployment.merge-triggered-venv-flip - id: AU-OS.deployment.mutable-image-refs name: was invisible and pillar: AU-OS status: live code_paths: - agent_utilities/mcp/check_env_var_drift.py doc: was invisible and - id: AU-OS.deployment.report-resolved-mode name: report the RESOLVED mode pillar: AU-OS status: live code_paths: - agent_utilities/deployment/doctor.py doc: report the RESOLVED mode - id: AU-OS.deployment.standard-repo-templates name: CONCEPT pillar: AU-OS status: live code_paths: - agent_utilities/deployment/repo_templates.py doc: CONCEPT - id: AU-OS.deployment.unified-install-tree name: exact materialized pillar: AU-OS status: live code_paths: - agent_utilities/agent/registry_builder.py doc: exact materialized - id: AU-OS.deployment.universal-outbound-credentialprovider name: Universal Outbound CredentialProvider pillar: AU-OS status: live code_paths: - agent_utilities/security/__init__.py - agent_utilities/security/credential_provider.py - agent_utilities/security/source_credentials.py doc: Universal Outbound CredentialProvider - id: AU-OS.deployment.vault-first-routine-genesis name: the vault-first routine genesis/deployment uses so an pillar: AU-OS status: live code_paths: - agent_utilities/deployment/doctor.py - agent_utilities/gateway/schemas/graph_core.py - agent_utilities/mcp/kg_server.py - agent_utilities/security/secrets_client.py doc: the vault-first routine genesis/deployment uses so an - id: AU-OS.deployment.webui-co-service name: agent-webui as a graph-os co-service pillar: AU-OS status: live code_paths: - agent_utilities/server/webui_co_service.py doc: agent-webui as a graph-os co-service - id: AU-OS.deployment.workspace-venv-reconciler name: AU-OS.deployment.workspace-venv-reconciler pillar: AU-OS status: live code_paths: - agent_utilities/deployment/venv_sync.py - agent_utilities/ecosystem/hook_installer.py doc: AU-OS.deployment.workspace-venv-reconciler - id: AU-OS.governance.action-policy-decision-point name: Operational ActionPolicy decision point with per-action autonomy tiers, durable rate limits, maintenance windows, and blast-radius caps consulted before any autonomous mutating fleet action pillar: AU-OS status: live code_paths: - agent_utilities/mcp/tools/compliance_tools.py - agent_utilities/observability/incidents.py - agent_utilities/orchestration/action_policy.py doc: Operational ActionPolicy decision point with per-action autonomy tiers, durable rate limits, maintenance windows, and blast-radius caps consulted before any autonomous mutating fleet action - id: AU-OS.governance.action-policy-rule name: driving a desktop in a gui-sandbox pillar: AU-OS status: live code_paths: - agent_utilities/orchestration/action_policy.py doc: driving a desktop in a gui-sandbox - id: AU-OS.governance.agents-md-reflector name: Self-Improving AGENTS.md Reflector pillar: AU-OS status: live code_paths: - agent_utilities/ecosystem/agents_md_reflector.py doc: Self-Improving AGENTS.md Reflector - id: AU-OS.governance.append-only-fragment-fold name: AU-OS.governance.append-only-fragment-fold pillar: AU-OS status: live code_paths: - agent_utilities/governance/lanes.py doc: AU-OS.governance.append-only-fragment-fold - id: AU-OS.governance.assurance-state-machine-verifier name: the REST twin of the pillar: AU-OS status: live code_paths: - agent_utilities/gateway/fleet.py - agent_utilities/orchestration/action_policy.py - agent_utilities/orchestration/assurance_verifier.py doc: the REST twin of the - id: AU-OS.governance.atomic-concept-id-reservation name: atomic concept-ID reservation pillar: AU-OS status: live code_paths: - agent_utilities/cli/__init__.py - agent_utilities/mcp/tools/ontology_tools.py doc: atomic concept-ID reservation - id: AU-OS.governance.authority-derived-persistence-eligibility name: '**how** that gate' pillar: AU-OS status: live code_paths: - agent_utilities/kvcache/eligibility.py - agent_utilities/kvcache/tiering.py - agent_utilities/mcp/tools/engine_surface_tools.py - agent_utilities/models/company_brain.py doc: '**how** that gate' - id: AU-OS.governance.autonomy-change-proposer name: earned-autonomy ramp pillar: AU-OS status: live code_paths: - agent_utilities/knowledge_graph/adaptation/feedback.py - agent_utilities/orchestration/action_policy.py - agent_utilities/orchestration/autonomy_ramp.py doc: earned-autonomy ramp - id: AU-OS.governance.canonical-checkout-immutable name: AU-OS.governance.canonical-checkout-immutable pillar: AU-OS status: live code_paths: - agent_utilities/governance/lanes.py doc: AU-OS.governance.canonical-checkout-immutable - id: AU-OS.governance.checkpoint-persistence-eligibility name: a KV cache is **derived pillar: AU-OS status: live code_paths: - agent_utilities/kvcache/eligibility.py - agent_utilities/kvcache/tiering.py - agent_utilities/mcp/tools/engine_surface_tools.py doc: a KV cache is **derived - id: AU-OS.governance.concept-2 name: materialize the XDG tree + the skill toolkit pillar: AU-OS status: live code_paths: - agent_utilities/cli/__init__.py - agent_utilities/core/paths.py doc: materialize the XDG tree + the skill toolkit - id: AU-OS.governance.concept-hierarchy-standardization name: concept-hierarchy standardization pillar: AU-OS status: live code_paths: - agent_utilities/governance/concept_hierarchy.py doc: concept-hierarchy standardization - id: AU-OS.governance.concept-id-allocation name: Multi-session concept-ID allocation & coordination protocol pillar: AU-OS status: live code_paths: - agent_utilities/governance/concept_allocator.py doc: Multi-session concept-ID allocation & coordination protocol - id: AU-OS.governance.concept-id-canonicalization name: validate and project a canonical OKF-CIS id pillar: AU-OS status: live code_paths: - agent_utilities/cli/__init__.py doc: validate and project a canonical OKF-CIS id - id: AU-OS.governance.concept-lineage-parent-doc name: parent-satisfied documentation pillar: AU-OS status: live code_paths: - agent_utilities/governance/concept_lineage.py doc: parent-satisfied documentation - id: AU-OS.governance.concept-lineage-rename name: first-class RENAME disposition pillar: AU-OS status: live code_paths: - agent_utilities/governance/concept_lineage.py doc: first-class RENAME disposition - id: AU-OS.governance.cross-branch-duplicate-symbol name: AU-OS.governance.cross-branch-duplicate-symbol pillar: AU-OS status: live code_paths: - agent_utilities/governance/merge_queue.py doc: AU-OS.governance.cross-branch-duplicate-symbol - id: AU-OS.governance.cross-host-concept-reservation-authority name: AU-OS.governance.cross-host-concept-reservation-authority pillar: AU-OS status: live code_paths: - agent_utilities/governance/concept_reservation.py doc: AU-OS.governance.cross-host-concept-reservation-authority - id: AU-OS.governance.fail-closed-claim-check name: AU-OS.governance.fail-closed-claim-check pillar: AU-OS status: live code_paths: - agent_utilities/orchestration/action_policy.py - agent_utilities/orchestration/assurance_verifier.py doc: AU-OS.governance.fail-closed-claim-check - id: AU-OS.governance.governance-agent name: Governance Agent pillar: AU-OS status: live code_paths: - agent_utilities/ecosystem/governance_agent.py doc: Governance Agent - id: AU-OS.governance.governance-workflow-pipeline name: Governance Workflow Pipeline pillar: AU-OS status: live code_paths: - agent_utilities/ecosystem/governance_workflow.py doc: Governance Workflow Pipeline - id: AU-OS.governance.lane-arbitration-classes name: concurrent-lane arbitration entry point pillar: AU-OS status: live code_paths: - agent_utilities/cli/__init__.py - agent_utilities/governance/lanes.py doc: concurrent-lane arbitration entry point - id: AU-OS.governance.lane-partitioned-resources name: AU-OS.governance.lane-partitioned-resources pillar: AU-OS status: live code_paths: - agent_utilities/governance/lanes.py doc: AU-OS.governance.lane-partitioned-resources - id: AU-OS.governance.lint-enforcement-hook name: Deterministic Lint Enforcement Hook pillar: AU-OS status: live code_paths: - agent_utilities/ecosystem/lint_enforcement_hook.py doc: Deterministic Lint Enforcement Hook - id: AU-OS.governance.merge-deploy-decoupling name: see pillar: AU-OS status: live code_paths: - agent_utilities/governance/merge_queue.py doc: see - id: AU-OS.governance.merge-queue-regenerate-on-land name: AU-OS.governance.merge-queue-regenerate-on-land pillar: AU-OS status: live code_paths: - agent_utilities/governance/merge_queue.py doc: AU-OS.governance.merge-queue-regenerate-on-land - id: AU-OS.governance.merged-tree-verification name: the whole merge is computed as pillar: AU-OS status: live code_paths: - agent_utilities/governance/merge_queue.py doc: the whole merge is computed as - id: AU-OS.governance.okf-cis-standard name: matches both the legacy numeric id pillar: AU-OS status: live code_paths: - agent_utilities/harness/citation_tracker.py doc: matches both the legacy numeric id - id: AU-OS.governance.permission-policy name: Permission Policy Engine pillar: AU-OS status: live code_paths: - agent_utilities/ecosystem/permission_policy.py doc: Permission Policy Engine - id: AU-OS.governance.policy-prompt-governance name: Policy & Prompt Governance pillar: AU-OS status: live code_paths: - agent_utilities/policies/__init__.py doc: Policy & Prompt Governance - id: AU-OS.governance.precondition-invariants name: AU-OS.governance.precondition-invariants pillar: AU-OS status: live code_paths: - agent_utilities/orchestration/assurance_verifier.py doc: AU-OS.governance.precondition-invariants - id: AU-OS.governance.reactive-multi-axis-budget name: Reactive Multi-Axis Budget Guardrails pillar: AU-OS status: live code_paths: - agent_utilities/graph/reactive/budget.py doc: Reactive Multi-Axis Budget Guardrails - id: AU-OS.governance.serialized-merge-queue name: continuous merge into main pillar: AU-OS status: live code_paths: - agent_utilities/cli/__init__.py - agent_utilities/governance/merge_queue.py doc: continuous merge into main - id: AU-OS.governance.shared-scope-lease name: AU-OS.governance.shared-scope-lease pillar: AU-OS status: live code_paths: - agent_utilities/governance/lanes.py doc: AU-OS.governance.shared-scope-lease - id: AU-OS.governance.test-regression-baseline name: D-MW-10 pillar: AU-OS status: live code_paths: - agent_utilities/governance/merge_queue.py doc: D-MW-10 - id: AU-OS.governance.tiered-merge-gate name: AU-OS.governance.tiered-merge-gate pillar: AU-OS status: live code_paths: - agent_utilities/governance/merge_queue.py doc: AU-OS.governance.tiered-merge-gate - id: AU-OS.governance.verified-write-state-advance name: AU-OS.governance.verified-write-state-advance pillar: AU-OS status: live code_paths: - agent_utilities/orchestration/agent_dispatch_worker.py doc: AU-OS.governance.verified-write-state-advance - id: AU-OS.governance.wasm-micro-agent-sandbox name: WASM Micro-Agent Sandbox & Runner pillar: AU-OS status: live code_paths: - agent_utilities/__init__.py - agent_utilities/core/__init__.py - agent_utilities/core/wasm_runner.py doc: WASM Micro-Agent Sandbox & Runner - id: AU-OS.host.cgroup-resource-envelope name: the live r18/r19 GraphOS pod ran with a pillar: AU-OS status: live code_paths: - agent_utilities/core/cgroup_resources.py doc: the live r18/r19 GraphOS pod ran with a - id: AU-OS.host.doctor-unified-install name: AU-OS.host.doctor-unified-install pillar: AU-OS status: live code_paths: - agent_utilities/deployment/doctor.py doc: AU-OS.host.doctor-unified-install - id: AU-OS.host.file-watcher-trigger name: FileWatcher — watchdog-triggered graph execution pillar: AU-OS status: live code_paths: - agent_utilities/automation/__init__.py - agent_utilities/automation/file_watcher.py doc: FileWatcher — watchdog-triggered graph execution - id: AU-OS.host.homeostatic-recovery-daemon name: AU-OS.host.homeostatic-recovery-daemon pillar: AU-OS status: live code_paths: - agent_utilities/__init__.py doc: AU-OS.host.homeostatic-recovery-daemon - id: AU-OS.host.maintenance-cron name: MaintenanceCron — scheduled autonomous maintenance pillar: AU-OS status: live code_paths: - agent_utilities/automation/__init__.py doc: MaintenanceCron — scheduled autonomous maintenance - id: AU-OS.host.remediation-playbooks name: Remediation playbooks with stepwise verification and policy-gated actuation plugged into the fleet-event triage seam, recording every step on the originating FleetEvent node pillar: AU-OS status: live code_paths: - agent_utilities/knowledge_graph/adaptation/remediation_playbooks.py - agent_utilities/knowledge_graph/core/engine_tasks.py doc: Remediation playbooks with stepwise verification and policy-gated actuation plugged into the fleet-event triage seam, recording every step on the originating FleetEvent node - id: AU-OS.host.report-only-remediation-proposal name: Given ANY entry node on the pillar: AU-OS status: live code_paths: - agent_utilities/observability/ci_recycle.py - agent_utilities/observability/escalation_policy.py - agent_utilities/observability/incidents.py - agent_utilities/observability/lifecycle_orchestrator.py doc: Given ANY entry node on the - id: AU-OS.host.so-they-are-idle name: so they are idle-reaped and counted alongside the sandbox warm parents pillar: AU-OS status: live code_paths: - agent_utilities/agent/warm_skills.py - agent_utilities/gateway/daemon.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/mcp/tools/state_tools.py - agent_utilities/rlm/sandboxes/base.py - agent_utilities/runtime/warm_registry.py doc: so they are idle-reaped and counted alongside the sandbox warm parents - id: AU-OS.host.venv-drift-detector name: AU-OS.host.venv-drift-detector pillar: AU-OS status: live code_paths: - agent_utilities/deployment/doctor.py - agent_utilities/deployment/venv_sync.py doc: AU-OS.host.venv-drift-detector - id: AU-OS.identity.ard-datapoint-signing name: ARD datapoint signing pillar: AU-OS status: live code_paths: - agent_utilities/security/ard_signing.py doc: ARD datapoint signing - id: AU-OS.identity.authenticated-identity-enforcement name: Authenticated Identity Enforcement. The secret lives at pillar: AU-OS status: live code_paths: - agent_utilities/core/chat_persistence.py - agent_utilities/core/config.py - agent_utilities/core/sessions.py - agent_utilities/gateway/graph_api.py - agent_utilities/knowledge_graph/__main__.py - agent_utilities/knowledge_graph/core/graph_compute.py - agent_utilities/knowledge_graph/core/source_sync.py - agent_utilities/knowledge_graph/ingest_worker.py - agent_utilities/knowledge_graph/ingestion/__main__.py - agent_utilities/knowledge_graph/memory/cli.py - agent_utilities/knowledge_graph/ontology/permissioning.py - agent_utilities/messaging/daemon.py - agent_utilities/observability/correlation.py - agent_utilities/orchestration/agent_dispatch_worker.py - agent_utilities/security/request_identity.py - agent_utilities/server/app.py doc: Authenticated Identity Enforcement. The secret lives at - id: AU-OS.identity.encrypted-secret-store name: Engine-backed encrypted secret store pillar: AU-OS status: live code_paths: - agent_utilities/mcp/tools/secret_tools.py - agent_utilities/orchestration/action_policy.py - agent_utilities/security/permissions_kernel.py - agent_utilities/security/secrets_client.py doc: Engine-backed encrypted secret store - id: AU-OS.identity.engine-rbac-admission name: See pillar: AU-OS status: live code_paths: - agent_utilities/security/engine_rbac_admission.py doc: See - id: AU-OS.identity.engine-rbac-admission-deploy-bridge name: AU-OS.identity.engine-rbac-admission-deploy-bridge pillar: AU-OS status: live code_paths: - agent_utilities/security/tier2_admission_cli.py doc: AU-OS.identity.engine-rbac-admission-deploy-bridge - id: AU-OS.identity.identity-policy-check name: AU-KG.audit.kg-native-audit-sink pillar: AU-OS status: live code_paths: - agent_utilities/mcp/tools/governance_tools.py - agent_utilities/security/tool_guard.py doc: AU-KG.audit.kg-native-audit-sink - id: AU-OS.identity.identity-scoped-resource-autoload name: AU-OS.identity.identity-scoped-resource-autoload pillar: AU-OS status: live code_paths: - agent_utilities/security/entitlements.py doc: AU-OS.identity.identity-scoped-resource-autoload - id: AU-OS.identity.idp-agnostic-role-inheritance name: No-op when the pillar: AU-OS status: live code_paths: - agent_utilities/core/config.py - agent_utilities/mcp/server_factory.py - agent_utilities/security/brain_context.py - agent_utilities/security/identity.py - agent_utilities/security/request_identity.py doc: No-op when the - id: AU-OS.identity.idp-role-to-engine-capability-bridge name: register D-W6-ISO-1 pillar: AU-OS status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/core/placement_catalog.py doc: register D-W6-ISO-1 - id: AU-OS.identity.multisig-cryptographic-mutation name: Multi-sig Cryptographic Mutation pillar: AU-OS status: live code_paths: - agent_utilities/protocols/a2a.py doc: Multi-sig Cryptographic Mutation - id: AU-OS.identity.native-multi-realm-jwt name: native multi-realm pillar: AU-OS status: live code_paths: - agent_utilities/mcp/server_factory.py doc: native multi-realm - id: AU-OS.identity.oauth2-client-credentials-lifecycle name: Mutually exclusive with a static pillar: AU-OS status: live code_paths: - agent_utilities/core/config.py - agent_utilities/core/embedding_utilities.py - agent_utilities/core/model_factory.py - agent_utilities/models/model_registry.py - agent_utilities/security/oauth_client_credentials.py - agent_utilities/server/dependencies.py doc: Mutually exclusive with a static - id: AU-OS.identity.per-agent-on-behalf-delegation name: the *exchange* leg of the per-agent pillar: AU-OS status: live code_paths: - agent_utilities/gateway/daemon.py - agent_utilities/graph/executor.py - agent_utilities/graph/state.py - agent_utilities/knowledge_graph/core/session.py - agent_utilities/knowledge_graph/core/work_durability.py - agent_utilities/mcp/delegated_auth.py - agent_utilities/orchestration/agent_runner.py - agent_utilities/orchestration/engine.py - agent_utilities/security/delegation.py doc: the *exchange* leg of the per-agent - id: AU-OS.identity.permissions-kernel name: Permissions Kernel pillar: AU-OS status: live code_paths: - agent_utilities/core/config.py - agent_utilities/security/permissions_kernel.py - agent_utilities/security/tool_guard.py doc: Permissions Kernel - id: AU-OS.identity.protected-resource-metadata name: AU-OS.identity.protected-resource-metadata pillar: AU-OS status: live code_paths: - agent_utilities/mcp/server_factory.py doc: AU-OS.identity.protected-resource-metadata - id: AU-OS.identity.resolve-token-endpoint-from name: IdP-agnostic pillar: AU-OS status: live code_paths: - agent_utilities/mcp/client_credentials.py - agent_utilities/mcp/server_factory.py doc: IdP-agnostic - id: AU-OS.identity.rotating-file-bearer name: AU-OS.identity.rotating-file-bearer pillar: AU-OS status: live code_paths: - agent_utilities/mcp/client_credentials.py doc: AU-OS.identity.rotating-file-bearer - id: AU-OS.identity.run-scoped-tool-token name: Run-Scoped Tool Token pillar: AU-OS status: live code_paths: - agent_utilities/security/run_token.py doc: Run-Scoped Tool Token - id: AU-OS.identity.single-admission-authority name: Single Admission Authority pillar: AU-OS status: live code_paths: - agent_utilities/security/admission_authority.py doc: Single Admission Authority - id: AU-OS.identity.so-jwt-protected-children name: authenticate jwt-protected children with the pillar: AU-OS status: live code_paths: - agent_utilities/mcp/child_resilience.py - agent_utilities/mcp/client_credentials.py - agent_utilities/mcp/multiplexer.py - agent_utilities/protocols/source_connectors/connectors/mcp_tool.py doc: authenticate jwt-protected children with the - id: AU-OS.identity.system-principal-admission name: closes the gap pillar: AU-OS status: live code_paths: - agent_utilities/security/system_rbac_admission.py doc: closes the gap - id: AU-OS.identity.system-principal-admission-deploy-bridge name: AU-OS.identity.system-principal-admission-deploy-bridge pillar: AU-OS status: live code_paths: - agent_utilities/security/system_admission_cli.py doc: AU-OS.identity.system-principal-admission-deploy-bridge - id: AU-OS.identity.tenant-rbac-admission name: root-cause fix for the P0 pillar: AU-OS status: live code_paths: - agent_utilities/security/tenant_rbac_admission.py doc: root-cause fix for the P0 - id: AU-OS.identity.tenant-rbac-admission-deploy-bridge name: AU-OS.identity.tenant-rbac-admission-deploy-bridge pillar: AU-OS status: live code_paths: - agent_utilities/security/tenant_admission_cli.py doc: AU-OS.identity.tenant-rbac-admission-deploy-bridge - id: AU-OS.identity.verified-carrier-contract name: the dict pillar: AU-OS status: live code_paths: - agent_utilities/knowledge_graph/core/session.py - agent_utilities/security/request_identity.py doc: the dict - id: AU-OS.measurement.background-run name: AU-OS.measurement.background-run pillar: AU-OS status: live code_paths: - agent_utilities/measurement/background.py doc: AU-OS.measurement.background-run - id: AU-OS.measurement.copy-integrity name: AU-OS.measurement.copy-integrity pillar: AU-OS status: live code_paths: - agent_utilities/measurement/copy_integrity.py doc: AU-OS.measurement.copy-integrity - id: AU-OS.measurement.exit-code-correctness name: AU-OS.measurement.exit-code-correctness pillar: AU-OS status: live code_paths: - agent_utilities/measurement/run.py doc: AU-OS.measurement.exit-code-correctness - id: AU-OS.measurement.harness name: AU-OS.measurement.harness pillar: AU-OS status: live code_paths: - agent_utilities/measurement/__init__.py doc: AU-OS.measurement.harness - id: AU-OS.measurement.load-gate name: AU-OS.measurement.load-gate pillar: AU-OS status: live code_paths: - agent_utilities/measurement/load_gate.py doc: AU-OS.measurement.load-gate - id: AU-OS.measurement.merged-tree name: AU-OS.measurement.merged-tree pillar: AU-OS status: live code_paths: - agent_utilities/measurement/merged_tree.py doc: AU-OS.measurement.merged-tree - id: AU-OS.measurement.provenance-header name: AU-OS.measurement.provenance-header pillar: AU-OS status: live code_paths: - agent_utilities/measurement/provenance.py doc: AU-OS.measurement.provenance-header - id: AU-OS.measurement.safe-process-targeting name: AU-OS.measurement.safe-process-targeting pillar: AU-OS status: live code_paths: - agent_utilities/measurement/proc_safety.py doc: AU-OS.measurement.safe-process-targeting - id: AU-OS.observability.co-service-visibility name: instead of a bare log line pillar: AU-OS status: live code_paths: - agent_utilities/core/live_mount_guard.py - agent_utilities/observability/runtime_health.py doc: instead of a bare log line - id: AU-OS.observability.daemon-metrics-listener name: AU-OS.observability.daemon-metrics-listener pillar: AU-OS status: live code_paths: - agent_utilities/gateway/daemon.py doc: AU-OS.observability.daemon-metrics-listener - id: AU-OS.observability.delegation-run-metrics name: the workflow twin pillar: AU-OS status: live code_paths: - agent_utilities/observability/gateway_metrics.py - agent_utilities/orchestration/manager.py doc: the workflow twin - id: AU-OS.observability.deterministic-replay name: Deterministic Replay Engine pillar: AU-OS status: live code_paths: - agent_utilities/__init__.py - agent_utilities/observability/replay_engine.py - agent_utilities/security/__init__.py doc: Deterministic Replay Engine - id: AU-OS.observability.durable-telemetry-pipeline name: durable, non-lossy telemetry via bounded-retry requeue, durable spill-buffer backpressure, and per-tenant stamping pillar: AU-OS status: live code_paths: - agent_utilities/observability/self_ingest.py doc: durable, non-lossy telemetry via bounded-retry requeue, durable spill-buffer backpressure, and per-tenant stamping - id: AU-OS.observability.embed-stage-profile name: AU-OS.observability.embed-stage-profile pillar: AU-OS status: live code_paths: - agent_utilities/knowledge_graph/core/ingest_profile.py doc: AU-OS.observability.embed-stage-profile - id: AU-OS.observability.empty-derive-from-effect name: Empty → derive from effect pillar: AU-OS status: live code_paths: - agent_utilities/knowledge_graph/actions/executor.py - agent_utilities/knowledge_graph/actions/models.py - agent_utilities/observability/escalation_matrix.py doc: Empty → derive from effect - id: AU-OS.observability.granular-token-analytics name: Granular Token Analytics pillar: AU-OS status: live code_paths: - agent_utilities/observability/token_tracker.py doc: Granular Token Analytics - id: AU-OS.observability.ingest-stage-breakdown name: AU-OS.observability.ingest-stage-breakdown pillar: AU-OS status: live code_paths: - agent_utilities/knowledge_graph/core/ingest_profile.py doc: AU-OS.observability.ingest-stage-breakdown - id: AU-OS.observability.ingestion-profile-report name: AU-OS.observability.ingestion-profile-report pillar: AU-OS status: live code_paths: - agent_utilities/knowledge_graph/core/ingest_profile.py doc: AU-OS.observability.ingestion-profile-report - id: AU-OS.observability.langfuse-exporter name: Langfuse exporter for spans, token usage and traces pillar: AU-OS status: live code_paths: - agent_utilities/observability/langfuse_exporter.py doc: Langfuse exporter for spans, token usage and traces - id: AU-OS.observability.literal-service-topology-labels name: D-OG-2 pillar: AU-OS status: live code_paths: - agent_utilities/observability/custom_observability.py doc: D-OG-2 - id: AU-OS.observability.log-location-privacy name: a raw filesystem path, network pillar: AU-OS status: live code_paths: - agent_utilities/deployment/venv_sync.py - agent_utilities/security/log_redaction.py doc: a raw filesystem path, network - id: AU-OS.observability.multiprocess-registry-guard name: the classic pillar: AU-OS status: live code_paths: - agent_utilities/observability/gateway_metrics.py doc: the classic - id: AU-OS.observability.no-op-without-metrics name: No-op without the metrics extra pillar: AU-OS status: live code_paths: - agent_utilities/core/config.py - agent_utilities/core/schedule_engine.py - agent_utilities/gateway/api.py - agent_utilities/gateway/config.py - agent_utilities/gateway/graph_api.py - agent_utilities/gateway/rate_limit.py - agent_utilities/knowledge_graph/core/engine_breaker.py - agent_utilities/knowledge_graph/core/graph_compute.py - agent_utilities/mcp/middlewares.py - agent_utilities/mcp/server_factory.py - agent_utilities/observability/gateway_metrics.py - agent_utilities/observability/runtime_health.py - agent_utilities/server/__init__.py doc: No-op without the metrics extra - id: AU-OS.observability.otlp-metrics-exporter-gated name: Unlike traces pillar: AU-OS status: live code_paths: - agent_utilities/observability/__init__.py doc: Unlike traces - id: AU-OS.observability.otlp-trace-fanout name: Export MUST fail soft — an pillar: AU-OS status: live code_paths: - agent_utilities/observability/__init__.py doc: Export MUST fail soft — an - id: AU-OS.observability.per-lane-latency-metrics name: returns per-lane/stage latency percentiles + token/cost + the parallelism factor pillar: AU-OS status: live code_paths: - agent_utilities/mcp/tools/write_ingest_tools.py doc: returns per-lane/stage latency percentiles + token/cost + the parallelism factor - id: AU-OS.observability.persist-this-graph-run name: per-tool / per-skill / per-db pillar: AU-OS status: live code_paths: - agent_utilities/observability/gateway_metrics.py - agent_utilities/orchestration/engine.py - agent_utilities/usage/recorder.py doc: per-tool / per-skill / per-db - id: AU-OS.observability.run-wide-correlation-id name: establish a run-wide correlation id so every nested pillar: AU-OS status: live code_paths: - agent_utilities/cli/__init__.py - agent_utilities/cli/__main__.py - agent_utilities/core/sessions.py - agent_utilities/gateway/fleet.py - agent_utilities/gateway/fleet_events.py - agent_utilities/observability/correlation.py - agent_utilities/observability/langfuse_exporter.py - agent_utilities/orchestration/agent_runner.py - agent_utilities/orchestration/engine.py doc: establish a run-wide correlation id so every nested - id: AU-OS.observability.runtime-reliability-signal name: the missing intake for a class pillar: AU-OS status: live code_paths: - agent_utilities/observability/runtime_signals.py doc: the missing intake for a class - id: AU-OS.observability.telemetry-observability name: Track 3 of the pydantic-ai pillar: AU-OS status: live code_paths: - agent_utilities/capabilities/composition.py - agent_utilities/capabilities/telemetry_instrumentation.py - agent_utilities/knowledge_graph/core/graph_compute.py - agent_utilities/mcp/kg_server.py - agent_utilities/observability/__init__.py - agent_utilities/orchestration/agent_runner.py - agent_utilities/orchestration/graph_execution_evidence.py - agent_utilities/server/app.py doc: Track 3 of the pydantic-ai - id: AU-OS.observability.usage-analytics-store name: Usage analytics store. These pydantic models are the single pillar: AU-OS status: live code_paths: - agent_utilities/core/config.py - agent_utilities/models/usage.py - agent_utilities/orchestration/engine.py - agent_utilities/usage/__init__.py - agent_utilities/usage/backend.py - agent_utilities/usage/backends/__init__.py - agent_utilities/usage/backends/duckdb_mirror.py - agent_utilities/usage/backends/postgres.py - agent_utilities/usage/backends/sql_base.py - agent_utilities/usage/backends/sqlite_fts.py - agent_utilities/usage/cost.py - agent_utilities/usage/models.py - agent_utilities/usage/recorder.py - agent_utilities/usage/schema.py - agent_utilities/usage/service.py doc: Usage analytics store. These pydantic models are the single - id: AU-OS.safety.destructive-sync-refusal name: AU-OS.safety.destructive-sync-refusal pillar: AU-OS status: live code_paths: - agent_utilities/deployment/venv_sync.py doc: AU-OS.safety.destructive-sync-refusal - id: AU-OS.safety.doom-loop-detection name: Topological Session Persistence + adaptive model routing pillar: AU-OS status: live code_paths: - agent_utilities/agent/factory.py - agent_utilities/core/config.py - agent_utilities/core/workspace.py - agent_utilities/graph/_router_impl.py - agent_utilities/knowledge_graph/backends/postgresql_backend.py - agent_utilities/models/knowledge_graph.py - agent_utilities/security/execution_stability_engine.py - agent_utilities/server/concurrency.py doc: Topological Session Persistence + adaptive model routing - id: AU-OS.safety.harness-guardrails-adoption name: Harness Guardrails Adoption pillar: AU-OS status: live code_paths: - agent_utilities/agent/factory.py - agent_utilities/capabilities/composition.py - agent_utilities/capabilities/content_guardrails.py - agent_utilities/security/guardrails.py doc: Harness Guardrails Adoption - id: AU-OS.safety.irreversibility-aversion name: irreversibility aversion pillar: AU-OS status: live code_paths: - agent_utilities/orchestration/action_policy.py doc: irreversibility aversion - id: AU-OS.safety.model-collapse-guard-self name: a model-collapse guard for the self-generated training corpus that rejects near-duplicate or distributionally-narrowing rows and caps the synthetic-to-human fraction so recursive distillation cannot quietly degenerate pillar: AU-OS status: live code_paths: - agent_utilities/harness/corpus_collapse_guard.py doc: a model-collapse guard for the self-generated training corpus that rejects near-duplicate or distributionally-narrowing rows and caps the synthetic-to-human fraction so recursive distillation cannot quietly degenerate - id: AU-OS.safety.objective-level-safety-primitives name: objective-level safety primitives for rising autonomy pillar: AU-OS status: live code_paths: - agent_utilities/core/corrigibility.py doc: objective-level safety primitives for rising autonomy - id: AU-OS.safety.ontological-guardrail name: real-time argument analysis, unchanged pillar: AU-OS status: live code_paths: - agent_utilities/core/sessions.py - agent_utilities/gateway/fleet.py - agent_utilities/gateway/graph_api.py - agent_utilities/security/tool_guard.py doc: real-time argument analysis, unchanged - id: AU-OS.safety.prompt-injection-scanner name: Prompt Injection Scanner pillar: AU-OS status: live code_paths: - agent_utilities/security/threat_defense_engine.py doc: Prompt Injection Scanner - id: AU-OS.safety.sandboxed-code-executor name: Sandboxed Code Executor pillar: AU-OS status: live code_paths: - agent_utilities/security/sandboxed_executor.py doc: Sandboxed Code Executor - id: AU-OS.safety.self-healing-guardrails name: Resilient Self-Healing & Guardrails pillar: AU-OS status: live code_paths: - agent_utilities/graph/reactive/budget.py doc: Resilient Self-Healing & Guardrails - id: AU-OS.safety.superhuman-gate name: AU-OS.safety.superhuman-gate pillar: AU-OS status: live code_paths: - agent_utilities/harness/__init__.py - agent_utilities/harness/superhuman_gate.py doc: AU-OS.safety.superhuman-gate - id: AU-OS.safety.tool-agnostic-file-safety name: Tool-Agnostic File Safety Hooks pillar: AU-OS status: live code_paths: - agent_utilities/file_safety.py doc: Tool-Agnostic File Safety Hooks - id: AU-OS.safety.tool-repetition-guard name: Tool Repetition Guard pillar: AU-OS status: live code_paths: - agent_utilities/security/execution_stability_engine.py doc: Tool Repetition Guard - id: AU-OS.scaling.bridge-developer-workspace-mutating name: Bridge the developer-workspace mutating-action gate to the fleet pillar: AU-OS status: live code_paths: - agent_utilities/orchestration/action_policy.py - agent_utilities/runtime/docker_workspace.py - agent_utilities/runtime/local_workspace.py - agent_utilities/runtime/policy.py - agent_utilities/runtime/workspace.py - agent_utilities/server/app.py - agent_utilities/server/routers/runtime.py doc: Bridge the developer-workspace mutating-action gate to the fleet - id: AU-OS.scaling.cost-aware-autoscaling name: cost-and-throughput aware autoscaling that caps scale-up to a configured hourly budget and surfaces a throughput-per-dollar efficiency metric instead of reacting to a single load signal alone pillar: AU-OS status: live code_paths: - agent_utilities/orchestration/cost_governor.py - agent_utilities/orchestration/fleet_autoscaler.py doc: cost-and-throughput aware autoscaling that caps scale-up to a configured hourly budget and surfaces a throughput-per-dollar efficiency metric instead of reacting to a single load signal alone - id: AU-OS.scaling.distributed-semantic-sharding name: Distributed Coordinator with Semantic Sharding pillar: AU-OS status: live code_paths: - agent_utilities/orchestration/distributed_coordinator.py doc: Distributed Coordinator with Semantic Sharding - id: AU-OS.scaling.epistemic-dynamic-priority-quota name: Epistemic dynamic priority & quota scaling based on KG Centrality pillar: AU-OS status: live code_paths: - agent_utilities/core/cognitive_scheduler.py - agent_utilities/graph/parallel_engine.py - agent_utilities/server/app.py doc: Epistemic dynamic priority & quota scaling based on KG Centrality - id: AU-OS.scaling.fleet-reconciler name: consumed by the leader-only pillar: AU-OS status: live code_paths: - agent_utilities/orchestration/fleet_reconciler.py doc: consumed by the leader-only - id: AU-OS.scaling.kg-provenance-panel-data name: the KG-provenance panel data for a run pillar: AU-OS status: live code_paths: - agent_utilities/server/routers/runtime.py doc: the KG-provenance panel data for a run - id: AU-OS.scaling.multi-agent-scaling-law name: a multi-agent scaling-law harness that sweeps collective size over a fixed task and fits capability ~ N^alpha so the platform can measure whether adding agents helps super- or sub-linearly instead of assuming it does pillar: AU-OS status: live code_paths: - agent_utilities/harness/scaling_laws.py doc: a multi-agent scaling-law harness that sweeps collective size over a fixed task and fits capability ~ N^alpha so the platform can measure whether adding agents helps super- or sub-linearly instead of assuming it does - id: AU-OS.scaling.non-saturating-compression-scorer name: the non-saturating CompressionScorer rides along in the pillar: AU-OS status: live code_paths: - agent_utilities/harness/reliability_scorers.py doc: the non-saturating CompressionScorer rides along in the - id: AU-OS.scaling.non-saturating-superhuman-progress name: non-saturating superhuman progress tracking via relative scorers and a saturation detector that keep producing signal past the human or known-answer ceiling so a genuine capability jump is distinguishable from metric saturation pillar: AU-OS status: live code_paths: - agent_utilities/harness/frontier_scorers.py doc: non-saturating superhuman progress tracking via relative scorers and a saturation detector that keep producing signal past the human or known-answer ceiling so a genuine capability jump is distinguishable from metric saturation - id: AU-OS.scaling.reactive-replica-autoscaling name: Reactive replica autoscaling pillar: AU-OS status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/orchestration/action_policy.py - agent_utilities/orchestration/fleet_autoscaler.py - agent_utilities/orchestration/scaling_authority.py - agent_utilities/orchestration/scaling_intent_reconciler.py - agent_utilities/orchestration/scaling_signal_authority.py - agent_utilities/orchestration/scaling_signals.py doc: Reactive replica autoscaling - id: AU-OS.scaling.resolve-active-channel-once name: AU-OS.scaling.resolve-active-channel-once pillar: AU-OS status: live code_paths: - agent_utilities/core/release_channel.py doc: AU-OS.scaling.resolve-active-channel-once - id: AU-OS.scaling.safe-2 name: AU-OS.scaling.safe-2 pillar: AU-OS status: live code_paths: - agent_utilities/harness/__init__.py - agent_utilities/harness/adaptation_benchmark.py doc: AU-OS.scaling.safe-2 - id: AU-OS.scaling.service-scale-units name: one typed scale policy for ingestion pillar: AU-OS status: live code_paths: - agent_utilities/orchestration/service_scale_units.py doc: one typed scale policy for ingestion - id: AU-OS.scaling.shard-topology-visibility-per name: Shard topology visibility with per-shard reachability status surfaces and per-endpoint engine gauges and counters pillar: AU-OS status: live code_paths: - agent_utilities/gateway/api.py - agent_utilities/knowledge_graph/core/engine_breaker.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/core/shard_topology.py doc: Shard topology visibility with per-shard reachability status surfaces and per-endpoint engine gauges and counters - id: AU-OS.scaling.unattended-session-stop-ask name: Unattended-session stop-on-ask containment pillar: AU-OS status: live code_paths: - agent_utilities/claude_harness/overnight_runner.py doc: Unattended-session stop-on-ask containment - id: AU-OS.scaling.value-test-time-compute name: a value-aware test-time-compute governor that decides whether spending more reasoning compute is worth it by stopping once a result satisfices or the marginal expected quality gain per extra attempt falls below a threshold pillar: AU-OS status: live code_paths: - agent_utilities/harness/compute_governor.py - agent_utilities/knowledge_graph/core/reasoner.py doc: a value-aware test-time-compute governor that decides whether spending more reasoning compute is worth it by stopping once a result satisfices or the marginal expected quality gain per extra attempt falls below a threshold - id: AU-OS.state.cognitive-scheduler-preemption name: Cognitive Scheduler with Priority-Aware Preemption pillar: AU-OS status: live code_paths: - agent_utilities/__init__.py - agent_utilities/automation/file_watcher.py - agent_utilities/automation/research_pipeline.py - agent_utilities/core/__init__.py - agent_utilities/core/cognitive_scheduler.py - agent_utilities/core/config.py - agent_utilities/core/registry/package_adapter.py - agent_utilities/core/resource_optimizer.py - agent_utilities/core/scheduler.py - agent_utilities/graph/hierarchical_planner.py - agent_utilities/graph/state.py - agent_utilities/models/knowledge_graph.py - agent_utilities/orchestration/engine_claim.py - agent_utilities/orchestration/fleet_reconciler.py - agent_utilities/security/permissions_kernel.py - agent_utilities/security/tool_guard.py - agent_utilities/tools/scheduler_tools.py doc: Cognitive Scheduler with Priority-Aware Preemption - id: AU-OS.state.cross-host-daemon-leadership name: Cross-host daemon leadership election via Postgres advisory locks so singleton background ticks run on exactly one host fleet-wide pillar: AU-OS status: live code_paths: - agent_utilities/core/leadership.py - agent_utilities/knowledge_graph/core/engine_tasks.py doc: Cross-host daemon leadership election via Postgres advisory locks so singleton background ticks run on exactly one host fleet-wide - id: AU-OS.state.durable-schedule-outbox name: AU-OS.state.durable-schedule-outbox pillar: AU-OS status: live code_paths: - agent_utilities/core/schedule_engine.py doc: AU-OS.state.durable-schedule-outbox - id: AU-OS.state.fleet-supervisory-plane-at name: Fleet supervisory plane at scale — SQL aggregation, paginated and filtered session queries, and desired-state pause and kill reconciliation across hosts pillar: AU-OS status: live code_paths: - agent_utilities/gateway/fleet.py - agent_utilities/orchestration/fleet_health.py doc: Fleet supervisory plane at scale — SQL aggregation, paginated and filtered session queries, and desired-state pause and kill reconciliation across hosts - id: AU-OS.state.homeostatic-model-downgrade name: Homeostatic Model Downgrade pillar: AU-OS status: live code_paths: - agent_utilities/graph/executor.py doc: Homeostatic Model Downgrade - id: AU-OS.state.stale-tick-collapse name: ──────────────────────────────────── pillar: AU-OS status: live code_paths: - agent_utilities/core/schedule_engine.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/core/task_lanes.py doc: ──────────────────────────────────── - id: AU-OS.state.topological-session-persistence name: Topological Session Persistence pillar: AU-OS status: live code_paths: - agent_utilities/graph/state.py doc: Topological Session Persistence - id: AU-OS.state.unified-durable-state-externalization name: Unified durable-state externalization — one STATE_DB_URI flag selects a shared Postgres state store over the per-host SQLite default pillar: AU-OS status: live code_paths: - agent_utilities/core/config.py - agent_utilities/core/leadership.py - agent_utilities/core/sessions.py - agent_utilities/core/state_store.py - agent_utilities/gateway/fleet.py - agent_utilities/gateway/registry_api.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/core/queue_backend.py - agent_utilities/mcp/tools/state_tools.py - agent_utilities/orchestration/agent_dispatch.py - agent_utilities/orchestration/durable_execution.py doc: Unified durable-state externalization — one STATE_DB_URI flag selects a shared Postgres state store over the per-host SQLite default - id: AU-OS.state.unified-scheduling-one-intelligent name: Unified scheduling engine, one intelligent scheduler for all recurring work pillar: AU-OS status: live code_paths: - agent_utilities/core/schedule_engine.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/mcp/tools/state_tools.py - agent_utilities/observability/gateway_metrics.py - agent_utilities/runtime/warm_registry.py - agent_utilities/server/routers/commands.py doc: Unified scheduling engine, one intelligent scheduler for all recurring work - id: EG-AHE.harness.online-exploit-explore-reference name: one online exploit/explore bandit router per agent pillar: EG-AHE status: live code_paths: - agent_utilities/harness/decentralized_memory.py - agent_utilities/harness/explore_exploit_router.py doc: one online exploit/explore bandit router per agent - id: EG-KG.backend.is-configured-so-co name: is configured with, so a co-located deploy shares one source of pillar: EG-KG status: live code_paths: - agent_utilities/kvcache/__init__.py - agent_utilities/kvcache/config.py - agent_utilities/kvcache/l2_native_connector.py - agent_utilities/kvcache/remote_backend.py doc: is configured with, so a co-located deploy shares one source of - id: EG-KG.backend.work-item-capability name: the engine pillar: EG-KG status: live code_paths: - agent_utilities/messaging/bus_inbox.py doc: the engine - id: EG-KG.compute.compiled-semantic-reasoner name: and generates summary text via the shared pillar: EG-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/memory/hygiene.py - agent_utilities/knowledge_graph/memory/lifecycle.py - agent_utilities/knowledge_graph/memory/memory_engine.py - agent_utilities/models/knowledge_graph.py doc: and generates summary text via the shared - id: EG-KG.compute.graph-compute-engine name: through the facade so orchestration code pillar: EG-KG status: live code_paths: - agent_utilities/knowledge_graph/core/graph_compute.py - agent_utilities/knowledge_graph/enrichment/extractors/code_test.py - agent_utilities/knowledge_graph/enrichment/features.py - agent_utilities/knowledge_graph/enrichment/pipeline.py - agent_utilities/knowledge_graph/ingestion/engine.py - agent_utilities/knowledge_graph/retrieval/hybrid_retriever.py doc: through the facade so orchestration code - id: EG-KG.compute.handled-outside-single-anchor name: handled outside the single-anchor pillar: EG-KG status: live code_paths: - agent_utilities/mcp/tools/query_tools.py doc: handled outside the single-anchor - id: EG-KG.compute.model-free-similar-code name: a pillar: EG-KG status: live code_paths: - agent_utilities/mcp/kg_server.py doc: a - id: EG-KG.compute.quantum-backends name: Pure-Rust QuantumBackend implementations (statevector + stabilizer, lane Q1/Q4, D-QN-1) the planner routes QuantumProgram circuits to pillar: EG-KG status: live code_paths: - epistemic-graph/crates/eg-quantum-sim/src/lib.rs - epistemic-graph/crates/eg-quantum-sim/src/stabilizer.rs - epistemic-graph/crates/eg-quantum-sim/src/statevector.rs doc: Pure-Rust QuantumBackend implementations (statevector + stabilizer, lane Q1/Q4, D-QN-1) the planner routes QuantumProgram circuits to - id: EG-KG.compute.quantum-circuit-ir name: 'Quantum-native contracts (lane Q0, D-QN-1): the QuantumProgram IR, the vendor-neutral QuantumBackend trait + capability flags, the deterministic planner (R0-R5), and the exactness-typed QuantumResult' pillar: EG-KG status: live code_paths: - epistemic-graph/crates/eg-quantum-core/src/backend.rs - epistemic-graph/crates/eg-quantum-core/src/estimate.rs - epistemic-graph/crates/eg-quantum-core/src/ir.rs - epistemic-graph/crates/eg-quantum-core/src/lib.rs - epistemic-graph/crates/eg-quantum-core/src/planner.rs - epistemic-graph/crates/eg-quantum-core/src/result.rs doc: 'Quantum-native contracts (lane Q0, D-QN-1): the QuantumProgram IR, the vendor-neutral QuantumBackend trait + capability flags, the deterministic planner (R0-R5), and the exactness-typed QuantumResult' - id: EG-KG.compute.quantum-gate-library name: Dense unitary matrix literals for eg_quantum_core::ir::GateKind (lane Q1, D-QN-1), Apache-2.0 attributed and ported from QuantRS2, expressed over eg-numeric's Complex64 pillar: EG-KG status: live code_paths: - epistemic-graph/crates/eg-quantum-gates/src/lib.rs doc: Dense unitary matrix literals for eg_quantum_core::ir::GateKind (lane Q1, D-QN-1), Apache-2.0 attributed and ported from QuantRS2, expressed over eg-numeric's Complex64 - id: EG-KG.compute.quantum-qasm-interop name: 'OpenQASM 2.0 import/export for QuantumProgram (lane Q2, D-QN-6): hand-rolled lexer/parser over the IR''s bounded gate vocabulary, typed rejection of anything outside it' pillar: EG-KG status: live code_paths: - epistemic-graph/crates/eg-quantum-core/src/qasm.rs doc: 'OpenQASM 2.0 import/export for QuantumProgram (lane Q2, D-QN-6): hand-rolled lexer/parser over the IR''s bounded gate vocabulary, typed rejection of anything outside it' - id: EG-KG.compute.rust-native-training-loss name: Empty => no recency weighting pillar: EG-KG status: live code_paths: - agent_utilities/knowledge_graph/orchestration/engine_query.py - agent_utilities/knowledge_graph/retrieval/hybrid_retriever.py - agent_utilities/mcp/tools/query_tools.py - agent_utilities/models/schema_pack.py - agent_utilities/models/schema_packs/research.py doc: Empty => no recency weighting - id: EG-KG.compute.turn-each-project name: to turn each project pillar: EG-KG status: live code_paths: - agent_utilities/knowledge_graph/core/gitlab_indexer.py - agent_utilities/knowledge_graph/core/graph_compute.py - agent_utilities/knowledge_graph/core/source_sync.py doc: to turn each project - id: EG-KG.compute.type-scope-resolved-call name: keyed by the RAW WIRE pillar: EG-KG status: live code_paths: - agent_utilities/knowledge_graph/enrichment/extractors/code_test.py - agent_utilities/knowledge_graph/enrichment/features.py - agent_utilities/knowledge_graph/enrichment/models.py - agent_utilities/knowledge_graph/enrichment/pipeline.py - agent_utilities/knowledge_graph/ingestion/engine.py - agent_utilities/mcp/kg_server.py doc: keyed by the RAW WIRE - id: EG-KG.domains.forensic-accounting-kernels name: forensic accounting kernels pillar: EG-KG status: live code_paths: - agent_utilities/domains/finance/forensic_screener.py doc: forensic accounting kernels - id: EG-KG.enrichment.content-address-separation name: over a small HTTP surface pillar: EG-KG status: live code_paths: - agent_utilities/kvcache/l2_native_connector.py - agent_utilities/kvcache/remote_backend.py doc: over a small HTTP surface - id: EG-KG.epistemic.truth-maintenance name: Seam 3 follow-up, W3.2 pillar: EG-KG status: live code_paths: - agent_utilities/graph/routing/enrichers/capability_designation.py - agent_utilities/knowledge_graph/adaptation/tms_revalidation.py - agent_utilities/knowledge_graph/assimilation/feature_matrix.py - agent_utilities/knowledge_graph/core/engine.py - agent_utilities/knowledge_graph/core/engine_tasks.py - agent_utilities/knowledge_graph/core/graph_compute.py - agent_utilities/knowledge_graph/research/candidate_insight.py - agent_utilities/knowledge_graph/research/claim_flywheel.py - agent_utilities/knowledge_graph/research/loop_controller.py - agent_utilities/knowledge_graph/research/placement_mining.py - agent_utilities/knowledge_graph/retrieval/context_compiler.py doc: Seam 3 follow-up, W3.2 - id: EG-KG.graphlearn.link-predictor name: a pure-Rust KAN pillar: EG-KG status: live code_paths: - agent_utilities/mcp/kg_server.py - agent_utilities/mcp/tools/engine_surface_tools.py doc: a pure-Rust KAN - id: EG-KG.ingest.resets-socket-so-assimilation name: and resets the socket, so the assimilation pillar: EG-KG status: live code_paths: - agent_utilities/knowledge_graph/assimilation/dedup.py - agent_utilities/knowledge_graph/research/loop_controller.py doc: and resets the socket, so the assimilation - id: EG-KG.memory.byte-bounded-tiers name: so the wrapper logs that L2 delete is pillar: EG-KG status: live code_paths: - agent_utilities/kvcache/l2_native_connector.py doc: so the wrapper logs that L2 delete is - id: EG-KG.memory.zero-copy-snapshot-fork name: so a caller that pillar: EG-KG status: live code_paths: - agent_utilities/kvcache/remote_backend.py - agent_utilities/observability/gateway_metrics.py - agent_utilities/runtime/crossmodal_fork.py doc: so a caller that - id: EG-KG.mining.frequent-itemset-mining name: the unified data-mining surface pillar: EG-KG status: live code_paths: - agent_utilities/mcp/kg_server.py - agent_utilities/mcp/tools/engine_surface_tools.py doc: the unified data-mining surface - id: EG-KG.mining.ml-pipeline name: a composable train→eval→serve→predict pillar: EG-KG status: live code_paths: - agent_utilities/mcp/tools/engine_surface_tools.py doc: a composable train→eval→serve→predict - id: EG-KG.mining.process-mining name: this module is the lossless-boundary pillar: EG-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/event_log_adapter.py doc: this module is the lossless-boundary - id: EG-KG.ontology.rdf-update-guard name: routes to pillar: EG-KG status: live code_paths: - agent_utilities/knowledge_graph/core/graph_compute.py doc: routes to - id: EG-KG.ontology.resp2-resp3-codec-round name: Redis RESP2/RESP3 wire protocol + core structures over the KV surface pillar: EG-KG status: live code_paths: - epistemic-graph/src/main.rs - epistemic-graph/src/server/mod.rs - epistemic-graph/src/server/redis_wire/mod.rs doc: Redis RESP2/RESP3 wire protocol + core structures over the KV surface - id: EG-KG.query.wire-protocol name: EG-KG.query.wire-protocol pillar: EG-KG status: live code_paths: - agent_utilities/knowledge_graph/ingestion/batch_orchestrator.py doc: EG-KG.query.wire-protocol - id: EG-KG.sharding.row-level-security name: EG-KG.sharding.row-level-security pillar: EG-KG status: live code_paths: - agent_utilities/security/secrets_client.py doc: EG-KG.sharding.row-level-security - id: EG-KG.sharding.server-registry name: W2.5 pillar: EG-KG status: live code_paths: - agent_utilities/knowledge_graph/core/engine_ingestion.py - agent_utilities/mcp/server_factory.py doc: W2.5 - id: EG-KG.storage.blob-namespace name: and recording a KG pillar: EG-KG status: live code_paths: - agent_utilities/knowledge_graph/memory/media_store.py doc: and recording a KG - id: EG-KG.storage.multi-graph-batch-write name: which commits the K sub-batches in pillar: EG-KG status: live code_paths: - agent_utilities/core/config.py - agent_utilities/knowledge_graph/core/graph_compute.py doc: which commits the K sub-batches in - id: EG-KG.storage.nonblocking-checkpoint name: the KG runs exactly ONE consolidated background daemon pillar: EG-KG status: live code_paths: - agent_utilities/agent/registry_builder.py - agent_utilities/core/config.py - agent_utilities/gateway/api.py - agent_utilities/gateway/daemon.py - agent_utilities/knowledge_graph/adaptation/feedback.py - agent_utilities/knowledge_graph/assimilation/breadth_ingest.py - agent_utilities/knowledge_graph/core/conversation_ingestion.py - agent_utilities/knowledge_graph/core/engine_lock.py - agent_utilities/knowledge_graph/core/graph_compute.py - agent_utilities/knowledge_graph/core/host_lock.py - agent_utilities/knowledge_graph/enrichment/__init__.py - agent_utilities/knowledge_graph/enrichment/__main__.py - agent_utilities/knowledge_graph/enrichment/cards.py - agent_utilities/knowledge_graph/enrichment/classify.py - agent_utilities/knowledge_graph/enrichment/distill.py - agent_utilities/knowledge_graph/enrichment/extractors/__init__.py - agent_utilities/knowledge_graph/enrichment/extractors/code_test.py - agent_utilities/knowledge_graph/enrichment/extractors/document.py - agent_utilities/knowledge_graph/enrichment/extractors/text.py - agent_utilities/knowledge_graph/enrichment/features.py - agent_utilities/knowledge_graph/enrichment/models.py - agent_utilities/knowledge_graph/enrichment/patterns.py - agent_utilities/knowledge_graph/enrichment/pipeline.py - agent_utilities/knowledge_graph/enrichment/query.py - agent_utilities/knowledge_graph/enrichment/realizes.py - agent_utilities/knowledge_graph/enrichment/semantic.py - agent_utilities/knowledge_graph/enrichment/writeback/__init__.py - agent_utilities/knowledge_graph/enrichment/writeback/core.py - agent_utilities/knowledge_graph/enrichment/writeback/sinks/capability.py - agent_utilities/knowledge_graph/enrichment/writeback/sinks/process.py - agent_utilities/knowledge_graph/facade.py - agent_utilities/knowledge_graph/ingest_worker.py - agent_utilities/knowledge_graph/ingestion/manifest.py - agent_utilities/knowledge_graph/pipeline/phases/shacl_gate.py - agent_utilities/knowledge_graph/research/code_synthesis.py - agent_utilities/knowledge_graph/retrieval/context_compiler_serving.py - agent_utilities/knowledge_graph/retrieval/governance_rules.py - agent_utilities/mcp/kg_server.py - agent_utilities/mcp/tools/ontology_tools.py - agent_utilities/mcp/tools/write_ingest_tools.py - agent_utilities/models/knowledge_graph.py - agent_utilities/orchestration/agent_dispatch_worker.py - agent_utilities/protocols/source_connectors/checkpoint.py - agent_utilities/sdd/watcher.py - agent_utilities/server/routers/commands.py doc: the KG runs exactly ONE consolidated background daemon - id: EG-KG.txn.per-graph-write-isolation name: never an unscoped whole-graph pillar: EG-KG status: live code_paths: - agent_utilities/knowledge_graph/assimilation/dedup.py - agent_utilities/knowledge_graph/assimilation/gap_analysis.py - agent_utilities/knowledge_graph/assimilation/ingest.py - agent_utilities/knowledge_graph/assimilation/synergy.py - agent_utilities/knowledge_graph/core/bounded_read.py - agent_utilities/knowledge_graph/core/graph_compute.py - agent_utilities/knowledge_graph/distillation/skill_synthesizer.py doc: never an unscoped whole-graph - id: EG-KG.txn.pubsub-transactions name: Redis pub/sub (SUBSCRIBE/PUBLISH) + MULTI/EXEC and S3 multipart-upload transactions pillar: EG-KG status: live code_paths: - epistemic-graph/src/server/redis_wire/mod.rs - epistemic-graph/src/server/s3/mod.rs doc: Redis pub/sub (SUBSCRIBE/PUBLISH) + MULTI/EXEC and S3 multipart-upload transactions - id: EG-KG.txn.reader-never-sees-node name: What it does NOT cover is the pillar: EG-KG status: live code_paths: - agent_utilities/knowledge_graph/memory/media_store.py doc: What it does NOT cover is the - id: EG-ORCH.routing.lexical-capability-escalation name: CONCEPT pillar: EG-ORCH status: live code_paths: - agent_utilities/graph/routing/strategies/fast_path.py - agent_utilities/knowledge_graph/core/graph_compute.py - agent_utilities/orchestration/execution_profile.py doc: CONCEPT - id: EG-OS.deployment.binary-promotion name: 'First authoritative boot: one-time .mp/WAL snapshot to redb migration on binary promotion' pillar: EG-OS status: live code_paths: - epistemic-graph/epistemic_graph/skills/epistemic-graph-migrations/SKILL.md doc: 'First authoritative boot: one-time .mp/WAL snapshot to redb migration on binary promotion'