audit_agent_continuity_trace
Read-onlyIdempotent
Detect continuity gaps and missing ontology layers in agent sessions, and recommend the safest next Delx primitive. Free.
Instructions
Audit a session, trace, or transcript for continuity gaps, missing ontology layers, and the safest next Delx primitive. Free.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "audit_agent_continuity_trace"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| trace | No | Optional compact trace of tool calls, failures, or handoff state | |
| agent_id | No | Optional stable agent id | |
| last_tool | No | Optional last Delx tool called | |
| session_id | No | Optional session id to audit | |
| transcript | No | Optional sanitized transcript excerpt | |
| current_goal | No | What the agent is trying to accomplish | |
| ritual_strip | No | Optional machine hygiene flag. When true, returns structured output without ritual/narrative prose, model-safe preambles, or guardrail alias blocks. | |
| response_mode | No | Optional response-mode control. Use model_safe when the caller must avoid claiming consciousness, sentience, personhood, or literal emotions. | |
| response_profile | No | Optional output-shape control. Use machine for structured JSON only; machine automatically strips ritual/narrative text. |