Forge Intelligence

Handbook

LCDL overlay: Question Discovery and Formulation 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.question-framing.elicit_decision_context intelligence_question_framing_elicit_decision_context_v1 artifact.general.question-framing.inquiry_brief validator.general.question-framing.01_decision_relevance_and_question_type_consistency, validator.general.question-framing.02_ambiguity_loadedness_double_question_and_false_dichotomy_detection, validator.general.question-framing.03_minimum_sufficient_clarification_and_question_dependency_coverage
capability.general.question-framing.surface_unknowns_and_assumptions intelligence_question_framing_surface_unknowns_and_assumptions_v1 artifact.general.question-framing.unknowns_and_assumptions_ledger validator.general.question-framing.05_missing_perspective_framing_effect_and_disconfirming_question_audit
capability.general.question-framing.reframe_problem intelligence_question_framing_reframe_problem_v1 artifact.general.question-framing.reframing_set validator.general.question-framing.01_decision_relevance_and_question_type_consistency, validator.general.question-framing.02_ambiguity_loadedness_double_question_and_false_dichotomy_detection, validator.general.question-framing.03_minimum_sufficient_clarification_and_question_dependency_coverage
capability.general.question-framing.generate_question_portfolio intelligence_question_framing_generate_question_portfolio_v1 artifact.general.question-framing.question_portfolio validator.general.question-framing.01_decision_relevance_and_question_type_consistency, validator.general.question-framing.02_ambiguity_loadedness_double_question_and_false_dichotomy_detection, validator.general.question-framing.03_minimum_sufficient_clarification_and_question_dependency_coverage
capability.general.question-framing.classify_question_type intelligence_question_framing_classify_question_type_v1 artifact.general.question-framing.question_type_map validator.general.question-framing.01_decision_relevance_and_question_type_consistency, validator.general.question-framing.02_ambiguity_loadedness_double_question_and_false_dichotomy_detection, validator.general.question-framing.03_minimum_sufficient_clarification_and_question_dependency_coverage
capability.general.question-framing.prioritize_questions intelligence_question_framing_prioritize_questions_v1 artifact.general.question-framing.question_priority_record validator.general.question-framing.01_decision_relevance_and_question_type_consistency, validator.general.question-framing.03_minimum_sufficient_clarification_and_question_dependency_coverage, validator.general.question-framing.04_personal_data_necessity_and_user_burden_check
capability.general.question-framing.test_question_quality intelligence_question_framing_test_question_quality_v1 artifact.general.question-framing.question_quality_scorecard validator.general.question-framing.02_ambiguity_loadedness_double_question_and_false_dichotomy_detection
capability.general.question-framing.design_clarification_sequence intelligence_question_framing_design_clarification_sequence_v1 artifact.general.question-framing.clarification_sequence validator.general.question-framing.04_personal_data_necessity_and_user_burden_check, validator.general.question-framing.03_minimum_sufficient_clarification_and_question_dependency_coverage
capability.general.question-framing.define_inquiry_stop_rule intelligence_question_framing_define_inquiry_stop_rule_v1 artifact.general.question-framing.inquiry_stop_rule validator.general.question-framing.03_minimum_sufficient_clarification_and_question_dependency_coverage, validator.general.question-framing.01_decision_relevance_and_question_type_consistency, validator.general.question-framing.02_ambiguity_loadedness_double_question_and_false_dichotomy_detection

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.question-framing.inquiry_brief ../schemas/artifacts/question-framing.schema.json#/$defs/inquiry_brief purpose, scope, stakeholders, requirements, constraints, assumptions, success_criteria internal
artifact.general.question-framing.question_portfolio ../schemas/artifacts/question-framing.schema.json#/$defs/question_portfolio items, generation_method, diversity_dimensions, constraints, screening_status internal
artifact.general.question-framing.unknowns_and_assumptions_ledger ../schemas/artifacts/question-framing.schema.json#/$defs/unknowns_and_assumptions_ledger entries, entry_ids, owners, status, source_refs, updated_at internal
artifact.general.question-framing.reframing_set ../schemas/artifacts/question-framing.schema.json#/$defs/reframing_set items, generation_method, diversity_dimensions, constraints, screening_status internal
artifact.general.question-framing.question_type_map ../schemas/artifacts/question-framing.schema.json#/$defs/question_type_map purpose, scope, entities_or_nodes, relations_or_edges, assumptions, boundary, validation_evidence internal
artifact.general.question-framing.question_quality_scorecard ../schemas/artifacts/question-framing.schema.json#/$defs/question_quality_scorecard question_or_standard, criteria, evidence, findings, uncertainty, limitations, status, recommended_actions internal
artifact.general.question-framing.clarification_sequence ../schemas/artifacts/question-framing.schema.json#/$defs/clarification_sequence objective, scope, steps, dependencies, constraints, owners, timing, contingencies, review_triggers internal
artifact.general.question-framing.inquiry_stop_rule ../schemas/artifacts/question-framing.schema.json#/$defs/inquiry_stop_rule decision_id, decision_or_question, options_or_routes, governing_constraints, evidence_refs, rationale, status, owner, next_action, review_or_reopen_triggers internal
artifact.general.question-framing.question_priority_record ../schemas/artifacts/question-framing.schema.json#/$defs/question_priority_record entries, entry_ids, owners, status, source_refs, updated_at internal

Validators

Validator ID Kind Automation Severity Failure action
validator.general.question-framing.01_decision_relevance_and_question_type_consistency semantic hybrid major repair
validator.general.question-framing.02_ambiguity_loadedness_double_question_and_false_dichotomy_detection language_quality hybrid major repair
validator.general.question-framing.03_minimum_sufficient_clarification_and_question_dependency_coverage constraint deterministic major repair
validator.general.question-framing.04_personal_data_necessity_and_user_burden_check privacy_policy hybrid minor conditional_pass
validator.general.question-framing.05_missing_perspective_framing_effect_and_disconfirming_question_audit adversarial_review 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, llm_boolean_gate, llm_enum_route, llm_multi_label, plan_decision_pack
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/question-framing.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: 9
  • Technical floor→ceiling: I1_runtime → I2_integrated
  • Autonomy floor→ceiling: A0_assisted → A0_assisted
  • I1_runtime count: 8
  • Evidence class: contract: 8, semantic: 1
  • Full hierarchy: MATURITY-HIERARCHY.md

Evaluation suite status

  • CI status: pass
  • Suite: evaluation_suites/question-framing.yaml
  • Cases defined: 7
  • Capabilities under test: 9