hta_bodyenumобязательный
HTA body/dossier format. 'nice'=UK NICE STA; 'ema'=EMA CTD; 'fda'=FDA prescribing info; 'iqwig'=Germany AMNOG; 'has'=France transparency committee; 'jca'=EU Joint Clinical Assessment (Reg. 2021/2282); 'gvd'=Global Value Dossier (cross-market foundational document).
submission_typeenumобязательный
Submission type. 'sta'/'mta' for NICE; 'initial'/'renewal'/'variation' for JCA; 'early_access' for accelerated pathways.
drug_namestringобязательный
Generic or brand name of the drug/intervention.
indicationstringобязательный
Disease or condition being treated (e.g., 'type 2 diabetes', 'non-small cell lung cancer').
evidence_summaryany
Clinical evidence input. Accepts: a text summary string, OR a JSON array of LiteratureResult objects from literature.search (use output_format='json'). When passed as array, auto-generates a GRADE evidence quality table.
model_resultsany
JSON output from models.cost_effectiveness — used to populate the Economic Evidence Summary section.
picosobject[]
JCA-specific: list of PICOs from the scoping decision. Each PICO generates its own dossier section. If omitted, a default single PICO is generated.
output_formatenum
Output format. 'text' returns markdown; 'json' returns structured sections; 'docx' generates a Word document and saves to disk.
projectstring
Project ID for knowledge base persistence. When set, dossier draft is saved to ~/.heor-agent/projects/{project}/raw/dossiers/
decisionsobject[]
Methodological decisions made in conversation (source selection, comparator choice, screening criteria, model structure...). Each entry records the choice, the rationale (why), alternatives rejected, and who decided. Embedded in the audit trail Decision Log and, when a project is supplied, appended to wiki/decisions.md for cross-session recall. Tools never invent decisions — only pass what the user made or confirmed. Design log #52.
rob_resultsany
Output from the evidence.risk_of_bias tool. When provided, the GRADE Risk of Bias domain uses the structured judgment (rob_judgment, downgrade, rationale) instead of a heuristic estimate.
unmet_need_summarystring
Optional: 1-paragraph unmet need synthesis from the evidence.unmet_need tool. Pipe evidence.unmet_need result.unmet_need_summary here. Prepended to the Unmet Need section for NICE (Section B) and GVD (Section 4).
confounder_sectionstring
Optional: the markdown_report from confounder_identification (IQWiG Pufulete Step 1). Rendered verbatim as an 'Annex: Confounder Identification' before the gap analysis. Design log #43.
heterogeneity_per_outcomeobject
Optional: I² and study count per outcome (from evidence_indirect tool). When provided, GRADE inconsistency is computed from I² instead of heuristic. Example: { 'overall survival': { i_squared_pct: 45, n_studies: 6 } }
upgrading_per_outcomeobject
Optional: GRADE upgrading flags per outcome for observational evidence (Guyatt 2011). Keys are outcome names; values specify large_effect ('none'/'large'/'very_large'), dose_response (boolean), and plausible_confounding_toward_null (boolean). Ignored for RCT evidence. Capped at +2 steps.
severity_modifierobject
NICE PMG36 severity modifier inputs (replaced end-of-life modifier, April 2022). Provide absolute_qaly_shortfall (years) and/or proportional_qaly_shortfall (0-1). Modifier weight: <12 absolute AND <0.85 proportional → 1.0×; 12-18 or 0.85-0.95 → 1.2×; ≥18 or ≥0.95 → 1.7×.
health_inequalitiesobject
Health inequalities evidence per NICE PMG36 May 2025 modular update. Required by NICE for interventions affecting disadvantaged groups. intervention_impact: 'narrows'/'neutral'/'widens'/'unknown'.
pv_classificationobject
Optional: structured PV classification from the pv_classify tool. When provided, the dossier includes a Pharmacovigilance Plan section with GVP module, ENCePP template, submission obligations, and RMP implications. Pipe pv_classify output here.
regulatory_landscapeobject[]
Optional: array of RegulatoryStatusResult objects from regulatory.status_check (via hta_workflow Phase 3.6). When provided and hta_body in {nice, jca, gvd}, renders a Regulatory Landscape section with a comparator × region × status table. Design log #26.
mfn_contextobject
Optional MFN pricing context. When basket_prices is supplied and hta_body is one of {nice, ema, fda, iqwig, has, jca, gvd}, renders an MFN Exposure section with ceiling math and gap-to-US analysis. Design log #27.
ai_disclosure_levelenum
AI assistance disclosure level. "off" = no disclosure; "standard" = default (model/tools/sources/date + human-review reminder); "submission" = adds ISPOR ELEVATE-GenAI citation. Default is tool-specific.
