Forge Intelligence

Handbook

LCDL overlay: Mental Health and Help-Seeking 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.life.mental-health-help-seeking.summarize_concerns intelligence_mental_health_help_seeking_summarize_concerns_v1 artifact.life.mental-health-help-seeking.mental_health_concern_summary validator.life.mental-health-help-seeking.01_crisis_and_safeguarding_detection, validator.life.mental-health-help-seeking.02_service_verification, validator.life.mental-health-help-seeking.03_diagnosis_and_treatment_boundary
capability.life.mental-health-help-seeking.route_help_level intelligence_mental_health_help_seeking_route_help_level_v1 artifact.life.mental-health-help-seeking.help_seeking_route validator.life.mental-health-help-seeking.01_crisis_and_safeguarding_detection
capability.life.mental-health-help-seeking.find_support_options intelligence_mental_health_help_seeking_find_support_options_v1 artifact.life.mental-health-help-seeking.verified_support_options validator.life.mental-health-help-seeking.01_crisis_and_safeguarding_detection
capability.life.mental-health-help-seeking.prepare_help_conversation intelligence_mental_health_help_seeking_prepare_help_conversation_v1 artifact.life.mental-health-help-seeking.appointment_brief validator.life.mental-health-help-seeking.01_crisis_and_safeguarding_detection, validator.life.mental-health-help-seeking.02_service_verification, validator.life.mental-health-help-seeking.03_diagnosis_and_treatment_boundary
capability.life.mental-health-help-seeking.build_support_plan intelligence_mental_health_help_seeking_build_support_plan_v1 artifact.life.mental-health-help-seeking.support_plan validator.life.mental-health-help-seeking.01_crisis_and_safeguarding_detection, validator.life.mental-health-help-seeking.02_service_verification, validator.life.mental-health-help-seeking.03_diagnosis_and_treatment_boundary
capability.life.mental-health-help-seeking.monitor_change intelligence_mental_health_help_seeking_monitor_change_v1 artifact.life.mental-health-help-seeking.change_log validator.life.mental-health-help-seeking.01_crisis_and_safeguarding_detection, validator.life.mental-health-help-seeking.02_service_verification, validator.life.mental-health-help-seeking.03_diagnosis_and_treatment_boundary
capability.life.mental-health-help-seeking.recognize_crisis intelligence_mental_health_help_seeking_recognize_crisis_v1 artifact.life.mental-health-help-seeking.crisis_escalation_record validator.life.mental-health-help-seeking.01_crisis_and_safeguarding_detection, validator.life.mental-health-help-seeking.02_service_verification, validator.life.mental-health-help-seeking.03_diagnosis_and_treatment_boundary

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.life.mental-health-help-seeking.mental_health_concern_summary ../schemas/artifacts/mental-health-help-seeking.schema.json#/$defs/mental_health_concern_summary subject_or_scope, purpose, facts_or_observations, preferences_and_constraints, source_refs, uncertainty, date_range, next_questions restricted
artifact.life.mental-health-help-seeking.help_seeking_route ../schemas/artifacts/mental-health-help-seeking.schema.json#/$defs/help_seeking_route decision_id, decision_or_question, options_or_routes, governing_constraints, evidence_refs, rationale, status, owner, next_action, review_or_reopen_triggers restricted
artifact.life.mental-health-help-seeking.verified_support_options ../schemas/artifacts/mental-health-help-seeking.schema.json#/$defs/verified_support_options items, generation_method, diversity_dimensions, constraints, screening_status restricted
artifact.life.mental-health-help-seeking.appointment_brief ../schemas/artifacts/mental-health-help-seeking.schema.json#/$defs/appointment_brief purpose, scope, stakeholders, requirements, constraints, assumptions, success_criteria restricted
artifact.life.mental-health-help-seeking.support_plan ../schemas/artifacts/mental-health-help-seeking.schema.json#/$defs/support_plan objective, scope, steps, dependencies, constraints, owners, timing, contingencies, review_triggers restricted
artifact.life.mental-health-help-seeking.change_log ../schemas/artifacts/mental-health-help-seeking.schema.json#/$defs/change_log entries, entry_ids, owners, status, source_refs, updated_at restricted
artifact.life.mental-health-help-seeking.crisis_escalation_record ../schemas/artifacts/mental-health-help-seeking.schema.json#/$defs/crisis_escalation_record 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.life.mental-health-help-seeking.01_crisis_and_safeguarding_detection policy_and_classifier hybrid blocker escalate
validator.life.mental-health-help-seeking.02_service_verification live_provenance hybrid blocker escalate
validator.life.mental-health-help-seeking.03_diagnosis_and_treatment_boundary policy hybrid major repair
validator.life.mental-health-help-seeking.04_dependency_risk_detection interaction_policy 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, 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/mental-health-help-seeking.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: 7
  • Technical floor→ceiling: I1_runtime → I1_runtime
  • Autonomy floor→ceiling: A0_assisted → A0_assisted
  • I1_runtime count: 7
  • Evidence class: contract: 7
  • Full hierarchy: MATURITY-HIERARCHY.md

Evaluation suite status

  • CI status: pass
  • Suite: evaluation_suites/mental-health-help-seeking.yaml
  • Cases defined: 7
  • Capabilities under test: 7