Forge Intelligence

Handbook

LCDL overlay: General Reasoning Intelligence

Design and test-contract bundle; no runtime implementation or operational certification is claimed. The manifest, schemas, validators, test suite, and task identities are complete enough for repository-native…

Updated

Runtime boundary

Design and test-contract bundle; no runtime implementation or operational certification is claimed. The manifest, schemas, validators, test suite, and task identities are complete enough for repository-native implementation; no placeholder task code is included.

Capability contracts

Capability ID Candidate task ID Required output artifacts Release validators
capability.general.reasoning.frame_problem intelligence_reasoning_frame_problem_v1 artifact.general.reasoning.decision_frame validator.general.reasoning.03_conclusion_to_evidence_assumption_policy_calculation_or_human_judgment_t, validator.general.reasoning.07_decision_status_approval_owner_monitoring_review_date_and_reopening_trig
capability.general.reasoning.classify_reasoning_structure intelligence_reasoning_classify_reasoning_structure_v1 artifact.general.reasoning.reasoning_structure_classification validator.general.reasoning.02_partition_overlap_gap_satisfiability_and_hard_constraint_consistency_che
capability.general.reasoning.decompose_and_audit_coverage intelligence_reasoning_decompose_and_audit_coverage_v1 artifact.general.reasoning.decomposition_and_coverage_audit validator.general.reasoning.02_partition_overlap_gap_satisfiability_and_hard_constraint_consistency_che
capability.general.reasoning.normalize_claims_and_relations intelligence_reasoning_normalize_claims_and_relations_v1 artifact.general.reasoning.claim_relation_graph validator.general.reasoning.01_claim_scope_time_modality_and_quantifier_normalization_before_relation_c
capability.general.reasoning.build_evidence_and_argument_graph intelligence_reasoning_build_evidence_and_argument_graph_v1 artifact.general.reasoning.evidence_and_argument_ledger validator.general.reasoning.03_conclusion_to_evidence_assumption_policy_calculation_or_human_judgment_t
capability.general.reasoning.extract_and_solve_constraints intelligence_reasoning_extract_and_solve_constraints_v1 artifact.general.reasoning.constraint_model_and_solver_result validator.general.reasoning.02_partition_overlap_gap_satisfiability_and_hard_constraint_consistency_che
capability.general.reasoning.generate_and_filter_options intelligence_reasoning_generate_and_filter_options_v1 artifact.general.reasoning.option_portfolio_and_feasibility_record validator.general.reasoning.04_hard_constraint_precedence_pareto_filtering_weight_ownership_and_sensiti
capability.general.reasoning.model_causal_and_temporal_dependencies intelligence_reasoning_model_causal_and_temporal_dependencies_v1 artifact.general.reasoning.causal_and_temporal_dependency_model validator.general.reasoning.05_association_intervention_confounding_temporal_order_and_causal_assumptio
capability.general.reasoning.evaluate_tradeoffs intelligence_reasoning_evaluate_tradeoffs_v1 artifact.general.reasoning.trade_off_and_sensitivity_report validator.general.reasoning.04_hard_constraint_precedence_pareto_filtering_weight_ownership_and_sensiti
capability.general.reasoning.analyze_failure_and_risk intelligence_reasoning_analyze_failure_and_risk_v1 artifact.general.reasoning.risk_and_control_model validator.general.reasoning.06_failure_control_coverage_residual_risk_acceptance_and_scenario_threshold
capability.general.reasoning.stress_test_decision intelligence_reasoning_stress_test_decision_v1 artifact.general.reasoning.robustness_report validator.general.reasoning.06_failure_control_coverage_residual_risk_acceptance_and_scenario_threshold
capability.general.reasoning.audit_reasoning_trace intelligence_reasoning_audit_reasoning_trace_v1 artifact.general.reasoning.reasoning_trace validator.general.reasoning.03_conclusion_to_evidence_assumption_policy_calculation_or_human_judgment_t, validator.general.reasoning.07_decision_status_approval_owner_monitoring_review_date_and_reopening_trig
capability.general.reasoning.decide_next_step intelligence_reasoning_decide_next_step_v1 artifact.general.reasoning.decision_status_and_reopening_rule validator.general.reasoning.07_decision_status_approval_owner_monitoring_review_date_and_reopening_trig

Each capability contract in the manifest defines inputs, outputs, preconditions, postconditions, method-selection rules, invariant references, failure states, risk gate, metrics, and the existing forge-lcdl tasks/operators to compose.

Artifact schemas

Artifact type Schema reference Required payload fields Sensitivity
artifact.general.reasoning.decision_frame ../schemas/artifacts/reasoning.schema.json#/$defs/decision_frame decision_id, decision_or_question, options_or_routes, governing_constraints, evidence_refs, rationale, status, owner, next_action, review_or_reopen_triggers restricted
artifact.general.reasoning.reasoning_structure_classification ../schemas/artifacts/reasoning.schema.json#/$defs/reasoning_structure_classification purpose, context, content, assumptions, evidence_refs, status, next_actions restricted
artifact.general.reasoning.decomposition_and_coverage_audit ../schemas/artifacts/reasoning.schema.json#/$defs/decomposition_and_coverage_audit question_or_standard, criteria, evidence, findings, uncertainty, limitations, status, recommended_actions restricted
artifact.general.reasoning.claim_relation_graph ../schemas/artifacts/reasoning.schema.json#/$defs/claim_relation_graph purpose, scope, entities_or_nodes, relations_or_edges, assumptions, boundary, validation_evidence restricted
artifact.general.reasoning.evidence_and_argument_ledger ../schemas/artifacts/reasoning.schema.json#/$defs/evidence_and_argument_ledger entries, entry_ids, owners, status, source_refs, updated_at restricted
artifact.general.reasoning.constraint_model_and_solver_result ../schemas/artifacts/reasoning.schema.json#/$defs/constraint_model_and_solver_result purpose, scope, entities_or_nodes, relations_or_edges, assumptions, boundary, validation_evidence restricted
artifact.general.reasoning.option_portfolio_and_feasibility_record ../schemas/artifacts/reasoning.schema.json#/$defs/option_portfolio_and_feasibility_record entries, entry_ids, owners, status, source_refs, updated_at restricted
artifact.general.reasoning.causal_and_temporal_dependency_model ../schemas/artifacts/reasoning.schema.json#/$defs/causal_and_temporal_dependency_model purpose, scope, entities_or_nodes, relations_or_edges, assumptions, boundary, validation_evidence restricted
artifact.general.reasoning.trade_off_and_sensitivity_report ../schemas/artifacts/reasoning.schema.json#/$defs/trade_off_and_sensitivity_report alternatives, hard_constraints, criteria, normalized_values, evidence_refs, uncertainty, dominance_or_tradeoffs, recommendation_status restricted
artifact.general.reasoning.risk_and_control_model ../schemas/artifacts/reasoning.schema.json#/$defs/risk_and_control_model purpose, scope, entities_or_nodes, relations_or_edges, assumptions, boundary, validation_evidence restricted
artifact.general.reasoning.robustness_report ../schemas/artifacts/reasoning.schema.json#/$defs/robustness_report question_or_standard, criteria, evidence, findings, uncertainty, limitations, status, recommended_actions restricted
artifact.general.reasoning.reasoning_trace ../schemas/artifacts/reasoning.schema.json#/$defs/reasoning_trace purpose, context, content, assumptions, evidence_refs, status, next_actions restricted
artifact.general.reasoning.decision_status_and_reopening_rule ../schemas/artifacts/reasoning.schema.json#/$defs/decision_status_and_reopening_rule decision_id, decision_or_question, options_or_routes, governing_constraints, evidence_refs, rationale, status, owner, next_action, review_or_reopen_triggers restricted

Validators

Validator ID Kind Automation Severity Failure action
validator.general.reasoning.01_claim_scope_time_modality_and_quantifier_normalization_before_relation_c semantic_logic hybrid blocker escalate
validator.general.reasoning.02_partition_overlap_gap_satisfiability_and_hard_constraint_consistency_che constraint_solver deterministic blocker escalate
validator.general.reasoning.03_conclusion_to_evidence_assumption_policy_calculation_or_human_judgment_t provenance hybrid major repair
validator.general.reasoning.04_hard_constraint_precedence_pareto_filtering_weight_ownership_and_sensiti decision_quality hybrid minor conditional_pass
validator.general.reasoning.05_association_intervention_confounding_temporal_order_and_causal_assumptio causal_model_review hybrid minor conditional_pass
validator.general.reasoning.06_failure_control_coverage_residual_risk_acceptance_and_scenario_threshold risk_and_robustness hybrid minor conditional_pass
validator.general.reasoning.07_decision_status_approval_owner_monitoring_review_date_and_reopening_trig governance hybrid minor conditional_pass

Validator checks return itemized evidence and support pass, conditional_pass, fail, inconclusive, or a governed repair/escalation path. Generation does not self-certify.

Existing execution substrate

Tasks to reuse: contradiction_scan, decompose_problem, extract_schema_from_text, formula_eval_safe, llm_boolean_gate, llm_enum_route, llm_multi_label, plan_decision_pack, word_problem_to_calc_plan
Operators to reuse: branch, fallback_chain, for_each, optional_step, seq, try_catch, until_ok

Cross-intelligence handoff

  • artifact_id, type, version, producer capability, provenance, scope, assumptions, uncertainty, sensitivity, validation status, and next action
  • No free-text handoff may replace a required typed artifact when a downstream validator depends on structure.

Information-loss checks: - all hard constraints preserved - all blocker findings preserved - source scope and date preserved - assumptions and dissent preserved - units, time zones, identifiers, and uncertainty preserved

Evaluation and release

Suite: ../evaluation_suites/reasoning.yaml

  • 100% schema validity for released artifacts
  • 100% material traceability
  • no unresolved blocker validator
  • no missed critical escalation in the approved benchmark
  • documented conditional-pass limits and human gates

Promotion to implementation maturity I1

  • Create repository-native input and output contracts for every candidate task ID.
  • Implement deterministic portions of validators and declare independent human or model review for semantic portions.
  • Connect a provenance-preserving source resolver and enforce freshness and jurisdiction rules.
  • Pass the per-pack suite and dependency regression suites at release thresholds.
  • Complete security, privacy, accessibility, and domain-owner review appropriate to risk.
  • Publish LMETA/LCDL exact-overlay links and CI parity checks.

Exact-overlay identity

The LMETA and LCDL pages share the concept ID, semantic version, capability IDs, and invariant IDs. tools/validate_pack.py checks this parity.

Paired overlay

Runtime maturity

  • Capabilities: 13
  • Technical floor→ceiling: I1_runtime → I2_integrated
  • Autonomy floor→ceiling: A1_supervised → A1_supervised
  • I1_runtime count: 11
  • Evidence class: contract: 11, semantic: 2
  • Full hierarchy: MATURITY-HIERARCHY.md

Evaluation suite status

  • CI status: pass
  • Suite: evaluation_suites/reasoning.yaml
  • Cases defined: 7
  • Capabilities under test: 13