Files
memabra/docs/demo-artifacts/trajectories/traj-439e4552-f248-43cb-b4eb-25db14da1ebc.json
2026-04-15 11:06:05 +08:00

207 lines
5.3 KiB
JSON

{
"trajectory_id": "traj-439e4552-f248-43cb-b4eb-25db14da1ebc",
"task": {
"task_id": "task-cde62e1c-0106-4803-9c7d-a0c2f58206d6",
"input": "Check the current system status.",
"channel": "local",
"created_at": "2026-04-14T14:37:42.380386+00:00",
"user_id": "oza"
},
"context_snapshot": {
"conversation_summary": "",
"environment_summary": "",
"recent_failures": []
},
"candidate_sets": {
"memory": [
{
"id": "mem-telegram-pref",
"type": "memory",
"title": "Telegram preference",
"summary": "Prefer plain text on Telegram.",
"triggers": [
"telegram",
"preference",
"answer"
],
"cost": 0.0,
"confidence": 0.95,
"success_rate": 0.9,
"freshness": 0.9,
"risk": 0.0,
"tags": [
"output"
],
"source": "user",
"type_payload": {}
}
],
"skill": [
{
"id": "skill-deploy",
"type": "skill",
"title": "Deploy workflow",
"summary": "Reusable deployment workflow.",
"triggers": [
"deploy",
"workflow",
"service"
],
"cost": 0.0,
"confidence": 0.8,
"success_rate": 0.9,
"freshness": 0.8,
"risk": 0.0,
"tags": [
"ops"
],
"source": "system",
"type_payload": {}
}
],
"tool": [
{
"id": "tool-terminal",
"type": "tool",
"title": "terminal",
"summary": "Run terminal-style inspection commands.",
"triggers": [
"check",
"current",
"status",
"system"
],
"cost": 0.0,
"confidence": 0.95,
"success_rate": 0.9,
"freshness": 1.0,
"risk": 0.0,
"tags": [
"inspection"
],
"source": "system",
"type_payload": {}
}
]
},
"decisions": [
{
"step": 1,
"decision_type": "call_tool",
"selected_ids": [
"tool-terminal"
],
"selected_payloads": [
{}
],
"rejected_ids": [],
"rationale": "Task asks for current state or external action; tool use is justified.",
"estimated_cost": 0.0
}
],
"events": [
{
"event_id": "evt-9252427a-3ceb-476a-b72d-a7e4f812194c",
"trajectory_id": "traj-439e4552-f248-43cb-b4eb-25db14da1ebc",
"timestamp": "2026-04-14T14:37:42.380442+00:00",
"stage": "retrieval",
"event_type": "task_received",
"payload": {
"input": "Check the current system status."
},
"metrics": {},
"parent_event_id": null
},
{
"event_id": "evt-333fbd7f-75b1-495f-acfa-6a66348ef16e",
"trajectory_id": "traj-439e4552-f248-43cb-b4eb-25db14da1ebc",
"timestamp": "2026-04-14T14:37:42.380447+00:00",
"stage": "retrieval",
"event_type": "candidates_recalled",
"payload": {
"memory_ids": [
"mem-telegram-pref"
],
"skill_ids": [
"skill-deploy"
],
"tool_ids": [
"tool-terminal"
]
},
"metrics": {},
"parent_event_id": "evt-9252427a-3ceb-476a-b72d-a7e4f812194c"
},
{
"event_id": "evt-7f4eddba-f609-4d72-bf7c-cd6a938233a7",
"trajectory_id": "traj-439e4552-f248-43cb-b4eb-25db14da1ebc",
"timestamp": "2026-04-14T14:37:42.380452+00:00",
"stage": "policy",
"event_type": "action_selected",
"payload": {
"step": 1,
"decision_type": "call_tool",
"selected_ids": [
"tool-terminal"
],
"selected_payloads": [
{}
],
"rejected_ids": [],
"rationale": "Task asks for current state or external action; tool use is justified.",
"estimated_cost": 0.0
},
"metrics": {},
"parent_event_id": "evt-333fbd7f-75b1-495f-acfa-6a66348ef16e"
},
{
"event_id": "evt-tool-traj-439e4552-f248-43cb-b4eb-25db14da1ebc-tool-terminal",
"trajectory_id": "traj-439e4552-f248-43cb-b4eb-25db14da1ebc",
"timestamp": "2026-04-14T14:37:42.380461+00:00",
"stage": "execution",
"event_type": "tool_called",
"payload": {
"tool_id": "tool-terminal",
"input": "Check the current system status."
},
"metrics": {},
"parent_event_id": null
},
{
"event_id": "evt-tool-result-traj-439e4552-f248-43cb-b4eb-25db14da1ebc-tool-terminal",
"trajectory_id": "traj-439e4552-f248-43cb-b4eb-25db14da1ebc",
"timestamp": "2026-04-14T14:37:42.380464+00:00",
"stage": "execution",
"event_type": "tool_result",
"payload": {
"tool_id": "tool-terminal",
"status": "success",
"output": "demo-result-for:tool-terminal",
"error": null,
"latency_ms": 42
},
"metrics": {},
"parent_event_id": null
}
],
"outcome": {
"status": "success",
"steps": 1,
"latency_ms": 42,
"user_corrections": 0,
"tool_errors": 0,
"notes": "Draft trajectory generated by MemabraRunner with execution hooks."
},
"reward": {
"total": 1.032,
"components": {
"task_success": 0.8,
"retrieval_hit": 0.25,
"tool_error": 0.0,
"user_correction": 0.0,
"latency": 0.008,
"context_cost": 0.06,
"useful_reuse": 0.05
}
}
}