Trace

Get an interaction (the evidence view)

The full per-call scorecard (findings with plain-English reasons + cited regulations, satisfied requirements, redactions, gate health, verdict) plus the tamper-evident audit_hash. With scorecard-v1 the response also carries the optional per-call timeline and quality_metrics eval blocks (empty until the engine emits them) and derived_metrics, the platform's score-ready rollup of the timeline (TTFB, turn counts, barge detect + recovery). Requires the trace:read scope.

get/v1/trace/interactions/{id}

Request

  • Base URL: https://api.pyai.com
  • URL: https://api.pyai.com/v1/trace/interactions/{id}
  • Auth: one of:
    • HTTP bearer
    • API key in header x-api-key

Path parameters

idstring required

The call_id.

Response

Interaction detail

objectstring
idstring

call_id

agent_idstring nullable
product'hear' | 'speak' | 'clone' | 'cue' | 'omni' | 'agents' | 'null' nullable
verdict'PASS' | 'WARN' | 'FAIL'
findingsinteger
blocked_turnsinteger
modified_turnsinteger
packs_enforcedstring
scored_atinteger

Unix ms.

sourcestring nullable

Call origin, for example external.

audit_hashstring

Hash-chain link proving this record is unaltered (the signed-evidence guarantee).

scorecardobject

The full trace-scorecard-v0/v1 record: findings, satisfied requirements, redactions, gate health, verdict, and (scorecard-v1) the optional timeline/quality_metrics eval blocks.

Example response

{
  "object": "trace.interaction",
  "tier2_findings": [
    {
      "object": "trace.finding",
      "check_id": "hallucination",
      "verdict": "concern",
      "tier": 2
    }
  ]
}

Changes

No recorded changes to this operation across all 1 revision of this API.