Skip to content

Decision Records

The Decision Context Record (DCR) is the single source of truth for one runtime decision — created at intake and updated in place only until it reaches a terminal status. It is immutable per Agent Run: a retry never edits an existing record, it creates a brand-new one.

Fields

FieldDescription
decision_idUnique per Agent Run
tenant_idResolved tenant — see Security
case_id, task_type, user_roleWhat was requested
agent_id, agent_version, model_provider, model_versionWho produced the output
input_context_hashDeterministic hash of the input context
retrieved_sourcesThe sources available for evidence checking
agent_outputThe structured output submitted (null until received)
policy_resultsEvery policy evaluated, pass/fail
evidence_resultsPer-claim support assessment
risk_scoreComputed runtime risk
statusintake_rejected | awaiting_agent_output | awaiting_human_review | blocked | finalized
human_action, reviewer_id, review_notes, final_outputSet once a reviewer acts
runtime_eventsEvery step recorded against this record

Status lifecycle

text
awaiting_agent_output ──► (evaluated) ──┬─► finalized (auto-approved)
                                          ├─► awaiting_human_review ──► finalized
                                          └─► blocked ──► finalized
intake_rejected (terminal, gateway validation failed before any agent ran)

API

GET /runtime/decision-records
GET /runtime/decision-records/{id}
GET /runtime/decision-records/{id}/export
GET /runtime/decision-records/{id}/replay

export wraps the record with an exported_at timestamp for audit handoff. replay returns the single-run Decision Replay for this record.

SDK usage

ts
const record = await runtime.getDecisionRecord(decisionId);
const all = await runtime.listDecisionRecords("finalized");

Developer Platform v1 — Clinical Agent Runtime Control Platform