Simulation

Backend API

Local and Pod execution share request progress reporting through llm_d_lens.simulation.progress.report_request_progress. Pod reporting still waits for readiness; local reporting retains its original start time. Backend adapters share artifact error formatting through backends.analytics.artifact_error_message, while retaining their own error/timeout field precedence, status mapping, and metric units. Task APIs and backend environment preparation are unchanged.

Simulation routes live in llm_d_lens/simulation/router.py under the /api/simulation prefix.

List simulation backends

List Simulation backends Lens knows about and whether each backend is available in the current environment.

REST API
Python API

GET /api/simulation/backends

Request: no body.

Response:

{
  "backends": [
    {
      "name": "aiperf",
      "display_name": "AIPerf",
      "api_version": 1,
      "available": true,
      "version": "0.12.0",
      "unavailable_reason": null,
      "scenarios": [
        {
          "name": "chat",
          "display_name": "Chat",
          "description": "Conversational and general assistant traffic.",
          "supported_backends": []
        },
        {
          "name": "api-calling",
          "display_name": "Tool & API Use",
          "description": "Tool-use, agent, and business API traffic.",
          "supported_backends": []
        }
      ],
      "capabilities": {
        "prompt_kinds": ["trace"],
        "arrival_patterns": [],
        "supports_duration": true,
        "supports_request_count": false,
        "supports_request_rate": false,
        "supports_streaming": true,
        "supports_per_request_results": true,
        "supports_cancellation": true,
        "supports_trace_range": true,
        "scale_factor_trace_formats": ["baseten_trace"],
        "trace_format_capabilities": {
          "mooncake_trace": {"supports_trace_range": true, "supports_scale_factor": false}
        },
        "advanced_options": [],
        "trace_formats": [
          "mooncake_trace",
          "bailian_trace",
          "baseten_trace",
          "burst_gpt_trace",
          "weka_public_dataset"
        ]
      },
      "managed_installation": false
    }
  ]
}

from llm_d_lens.simulation.backends import list_backends

for backend in list_backends():
    print(backend.name, backend.available, backend.version)

Discover endpoint models

Probe a model endpoint and discover which models it reports. The optional api_key is sent as a Bearer token and is not included in the response. Failed connectivity, authentication, or invalid model lists return HTTP 400.

REST API
Python API

POST /api/simulation/models/discover

Request body: ModelDiscoveryRequest

endpoint_url (string, required)
api_key (string, optional, maximum 4096 characters; used only for this request)

{
  "endpoint_url": "http://127.0.0.1:38000/v1"
}

Response:

{
  "endpoint": "http://127.0.0.1:38000/v1",
  "models": [
    "Qwen/Qwen3-8B",
    "Qwen/Qwen3-8B-Instruct"
  ]
}

import asyncio

from llm_d_lens.simulation.endpoints import discover_models

async def main() -> None:
    models = await discover_models("http://127.0.0.1:38000/v1", api_key="your-model-access-token")
    print(models["endpoint"], models["models"])

asyncio.run(main())

List simulation scenarios

List the simulation scenario catalog Lens exposes, such as chat, API-calling, and coding.

REST API
Python API

GET /api/simulation/scenarios

Request: no body.

Response:

{
  "scenarios": [
    {
      "name": "chat",
      "display_name": "Chat",
      "description": "Conversational and general assistant traffic.",
      "supported_backends": ["aiperf", "trace-replayer"]
    },
    {
      "name": "coding",
      "display_name": "Code Generation",
      "description": "Code generation and software engineering traffic.",
      "supported_backends": ["aiperf"]
    }
  ]
}

from llm_d_lens.simulation.backends import list_scenarios

for scenario in list_scenarios():
    print(scenario.name, scenario.supported_backends)

List trace datasets

List registered trace datasets and the backends that can replay each one.

REST API
Python API

GET /api/simulation/trace-datasets

Request: no body.

Response:

{
  "data_dir": "/home/prism/.local/share/prism/data/datasets",
  "datasets": [
    {
      "name": "mooncake-arxiv",
      "filename": "mooncake_trace.jsonl",
      "scenario": "chat",
      "trace_format": "mooncake_trace",
      "description": "Mooncake chat trace derived from Arxiv summarization prompts.",
      "downloaded": false,
      "path": "/home/prism/.local/share/prism/data/datasets/mooncake_trace.jsonl",
      "artifact_uri": "artifact://dataset/mooncake-arxiv/mooncake_trace.jsonl",
      "size_bytes": null,
      "license": "Apache-2.0",
      "sha256": "f0c15fb14b60d0afca8b1f7c1ff29378f3df54318e6d112b47ad3b2a2f5881ef",
      "source_repository": "https://github.com/kvcache-ai/Mooncake.git",
      "supported_backends": ["aiperf", "trace-replayer"]
    }
  ]
}

from llm_d_lens.simulation.backends import list_backends
from llm_d_lens.simulation.traces import trace_registry

backends = list_backends()
for dataset in trace_registry.list():
    supported = [
        backend.name
        for backend in backends
        if any(scenario.name == dataset["scenario"] for scenario in backend.scenarios)
        and dataset["trace_format"] in backend.capabilities.get("trace_formats", [])
    ]
    print(dataset["name"], supported)

Download a trace dataset

Download a registered trace dataset into Lens's local trace store.

REST API
Python API

POST /api/simulation/trace-datasets/download

Request body: TraceDatasetDownloadRequest

dataset (string, required)
force (boolean, default false)

{
  "dataset": "mooncake-arxiv",
  "force": false
}

Response:

{
  "artifact_uri": "artifact://dataset/mooncake-arxiv/mooncake_trace.jsonl",
  "path": "/home/prism/.local/share/prism/data/datasets/mooncake_trace.jsonl",
  "trace_format": "mooncake_trace",
  "sha256": "f0c15fb14b60d0afca8b1f7c1ff29378f3df54318e6d112b47ad3b2a2f5881ef",
  "metadata_path": "/home/prism/.local/share/prism/data/datasets/mooncake_trace.jsonl.metadata.json",
  "size_bytes": 1048576
}

import asyncio

from llm_d_lens.simulation.traces import BaseTrace

async def main() -> None:
    result = await BaseTrace.download("mooncake-arxiv", force=False)
    print(result["path"], result["sha256"])

asyncio.run(main())

Get a trace dataset timeline

Get a pre-aggregated timeline view for one trace dataset.

REST API
Python API

GET /api/simulation/trace-datasets/{dataset_name}/timeline

Request: no body.

Path parameter: dataset_name (string, required)
Query parameter: bins (integer, default 800, range 50-2000)

Response:

{
  "dataset": "mooncake-arxiv",
  "trace_format": "mooncake_trace",
  "request_count": 12000,
  "duration_seconds": 3600.0,
  "source_size_bytes": 1048576,
  "bin_width_seconds": 4.5,
  "bins": [
    {"start_seconds": 0.0, "end_seconds": 4.5, "request_count": 12},
    {"start_seconds": 4.5, "end_seconds": 9.0, "request_count": 18}
  ]
}

import asyncio

from llm_d_lens.simulation.traces import get_trace_timeline

async def main() -> None:
    timeline = await get_trace_timeline("mooncake-arxiv", 800)
    print(timeline["dataset"], timeline["request_count"])

asyncio.run(main())

List simulation tasks

List Simulation tasks with optional filters for status, scenario, backend, model, dataset, endpoint, and creation window.

REST API
Python API

GET /api/simulation/tasks

Request: no body.

Query parameters: status, scenario, search, backend, model, dataset, trace_format, endpoint, created_after, created_before, offset, limit.

Response:

{
  "tasks": [
    {
      "id": "1a2b3c4d",
      "name": "Trace simulation",
      "description": "Replay a chat trace against a ready deployment",
      "scenario": "chat",
      "status": "running",
      "endpoint_mode": "deployment",
      "endpoint_namespace": "prism-sim",
      "endpoint_service": "qwen-router",
      "endpoint_deployment_execution_id": "00000000-0000-4000-8000-000000000001",
      "endpoint_deployment_run_id": null,
      "endpoint_deployment_case_id": null,
      "endpoint_cluster_id": "cluster-1",
      "endpoint_cluster_name": "dev-cluster",
      "endpoint_deployment_name": "qwen3-guide",
      "endpoint_url": "http://127.0.0.1:38000/v1",
      "model_name": "Qwen/Qwen3-8B",
      "simulation": {
        "backend": "trace-replayer",
        "backend_options": {},
        "duration_seconds": 60.0,
        "num_requests": null,
        "stream": true,
        "warmup_enabled": false,
        "grace_period_seconds": 30.0
      },
      "prompt": {
        "type": "trace",
        "dataset": {"name": "mooncake-arxiv", "scenario": "chat", "tokenizer": null},
        "trace": {
          "path": "/home/prism/.local/share/prism/data/datasets/mooncake_trace.jsonl",
          "format": "mooncake_trace",
          "fixed_schedule": true,
          "timeout_seconds": 3600.0,
          "synthesis_speedup_ratio": 1.0,
          "start_seconds": 0.0,
          "end_seconds": null
        }
      },
      "task_dir": "/home/prism/.local/share/prism/data/artifacts/simulations/1a2b3c4d",
      "artifact_uri": null,
      "artifact_error": null,
      "logs_truncated": false,
      "artifacts_incomplete": false,
      "backend_version_inferred": false,
      "backend_version": null,
      "configuration_ids": ["config-1"],
      "progress_percent": 42.5,
      "progress_message": "Simulation running",
      "logs": [],
      "result": null,
      "error_message": null,
      "created_at": "2026-09-23T09:18:24.287000Z",
      "started_at": "2026-09-23T09:18:25.000000Z",
      "execution_started_at": "2026-09-23T09:18:27.000000Z",
      "completed_at": null,
      "owner_pid": null,
      "owner_instance_id": null,
      "live_summary": {
        "completed_requests": 420,
        "successful_requests": 418
      }
    }
  ],
  "total": 1,
  "offset": 0,
  "limit": 10,
  "counts": {
    "queued": 0,
    "running": 1,
    "completed": 0,
    "failed": 0,
    "cancelled": 0
  },
  "facets": {
    "backends": ["trace-replayer"],
    "models": ["Qwen/Qwen3-8B"],
    "datasets": ["mooncake-arxiv"],
    "trace_formats": ["mooncake_trace"],
    "endpoints": ["http://127.0.0.1:38000/v1"]
  }
}

import asyncio

from llm_d_lens.simulation.service import list_tasks

async def main() -> None:
    page = await list_tasks(status="running", limit=20)
    print(page.total, [task.id for task in page.tasks])

asyncio.run(main())

Create a simulation task

For Endpoint URL targets (endpoint_mode != "deployment"), the service checks /v1/models with the supplied api_key before persisting or scheduling the task. A failed check returns HTTP 400; direct Python calls raise SimulationConfigurationError. Manual model names do not bypass this check. Deployment-bound Model Service tasks retain their cluster execution path.

Create a Simulation task that replays a trace dataset against a target model endpoint.

REST API
Python API

POST /api/simulation/tasks

Request body: SimulationTaskCreateRequest

name, description, scenario, backend, endpoint_mode
cluster_session_id, endpoint_namespace, endpoint_service, endpoint_deployment_execution_id, endpoint_cluster_id, endpoint_cluster_name, endpoint_deployment_name
model_service_group_id (string, optional) — target a published, continuously health-probed Model Service instead of a raw deployment execution. When set, the backend resolves it to the group's active member and published name and forces endpoint_mode to "deployment", overriding any supplied endpoint_deployment_execution_id/model_name. Requires api_key.
api_key (string, optional) — model access token; required when model_service_group_id is set.
endpoint_url, model_name, trace_dataset, trace_path
duration_seconds, scale_factor, trace_start_seconds, trace_end_seconds, trace_timeout_seconds, fixed_schedule, stream, backend_options

{
  "name": "Trace simulation",
  "description": "Replay a chat trace against a ready deployment",
  "scenario": "chat",
  "backend": "trace-replayer",
  "endpoint_mode": "deployment",
  "cluster_session_id": "123e4567-e89b-12d3-a456-426614174000",
  "endpoint_namespace": "prism-sim",
  "endpoint_service": "qwen-router",
  "endpoint_deployment_execution_id": "00000000-0000-4000-8000-000000000001",
  "endpoint_cluster_id": "cluster-1",
  "endpoint_cluster_name": "dev-cluster",
  "endpoint_deployment_name": "qwen3-guide",
  "endpoint_url": "http://127.0.0.1:38000/v1",
  "model_name": "Qwen/Qwen3-8B",
  "trace_dataset": "mooncake-arxiv",
  "trace_path": "/home/prism/.local/share/prism/data/datasets/mooncake_trace.jsonl",
  "duration_seconds": 60,
  "scale_factor": 1,
  "trace_start_seconds": 0,
  "trace_end_seconds": null,
  "trace_timeout_seconds": 3600,
  "fixed_schedule": true,
  "stream": true,
  "backend_options": {}
}

To target a published Model Service instead, set model_service_group_id and api_key; the backend discards the supplied endpoint_deployment_execution_id/endpoint_url/model_name and re-resolves them from the group's active member (a syntactically valid placeholder URL still satisfies request validation):

{
  "name": "Trace simulation",
  "scenario": "chat",
  "backend": "trace-replayer",
  "endpoint_mode": "deployment",
  "model_service_group_id": "01998e6b-4b2e-7c7e-8c6d-8e2a3f0c9b11",
  "api_key": "lens-mk-…",
  "endpoint_url": "http://model-service.internal",
  "model_name": "qwen3-8b",
  "trace_dataset": "mooncake-arxiv",
  "trace_path": "/home/prism/.local/share/prism/data/datasets/mooncake_trace.jsonl"
}

Response:

{
  "task_id": "1a2b3c4d",
  "status": "queued",
  "task": {
    "id": "1a2b3c4d",
    "name": "Trace simulation",
    "description": "Replay a chat trace against a ready deployment",
    "scenario": "chat",
    "status": "queued",
    "endpoint_mode": "deployment",
    "endpoint_namespace": "prism-sim",
    "endpoint_service": "qwen-router",
    "endpoint_deployment_execution_id": "00000000-0000-4000-8000-000000000001",
    "endpoint_deployment_run_id": null,
    "endpoint_deployment_case_id": null,
    "endpoint_cluster_id": "cluster-1",
    "endpoint_cluster_name": "dev-cluster",
    "endpoint_deployment_name": "qwen3-guide",
    "endpoint_url": "http://127.0.0.1:38000/v1",
    "model_name": "Qwen/Qwen3-8B",
    "simulation": {
      "backend": "trace-replayer",
      "backend_options": {},
      "duration_seconds": 60.0,
      "num_requests": null,
      "stream": true,
      "warmup_enabled": false,
      "grace_period_seconds": 30.0
    },
    "prompt": {
      "type": "trace",
      "dataset": {"name": "mooncake-arxiv", "scenario": "chat", "tokenizer": null},
      "trace": {
        "path": "/home/prism/.local/share/prism/data/datasets/mooncake_trace.jsonl",
        "format": "mooncake_trace",
        "fixed_schedule": true,
        "timeout_seconds": 3600.0,
        "synthesis_speedup_ratio": 1.0,
        "start_seconds": 0.0,
        "end_seconds": null
      }
    },
    "task_dir": "/home/prism/.local/share/prism/data/artifacts/simulations/1a2b3c4d",
    "artifact_uri": null,
    "artifact_error": null,
    "logs_truncated": false,
    "artifacts_incomplete": false,
    "backend_version_inferred": false,
    "backend_version": null,
    "configuration_ids": ["config-1"],
    "progress_percent": 0.0,
    "progress_message": "Queued",
    "logs": [],
    "result": null,
    "error_message": null,
    "created_at": "2026-09-23T09:18:24.287000Z",
    "started_at": null,
    "execution_started_at": null,
    "completed_at": null,
    "owner_pid": null,
    "owner_instance_id": null
  }
}

import asyncio

from llm_d_lens.simulation.models import SimulationTaskCreateRequest
from llm_d_lens.simulation.service import create_task


async def main() -> None:
    task = await create_task(
        SimulationTaskCreateRequest(
            scenario="chat",
            backend="trace-replayer",
            endpoint_mode="deployment",
            endpoint_deployment_execution_id="00000000-0000-4000-8000-000000000001",
            endpoint_url="http://127.0.0.1:38000/v1",
            model_name="Qwen/Qwen3-8B",
            trace_dataset="mooncake-arxiv",
            trace_path="/home/prism/.local/share/prism/data/datasets/mooncake_trace.jsonl",
        )
    )
    print(task.id, task.status)

    # Or target a published Model Service (resolves to its active member and
    # published name; requires api_key, and endpoint_url/model_name are discarded):
    task = await create_task(
        SimulationTaskCreateRequest(
            scenario="chat",
            backend="trace-replayer",
            endpoint_mode="deployment",
            model_service_group_id="01998e6b-4b2e-7c7e-8c6d-8e2a3f0c9b11",
            api_key="lens-mk-…",
            endpoint_url="http://model-service.internal",
            model_name="qwen3-8b",
            trace_dataset="mooncake-arxiv",
            trace_path="/home/prism/.local/share/prism/data/datasets/mooncake_trace.jsonl",
        )
    )
    print(task.id, task.status)


asyncio.run(main())

Get a simulation task

Get one Simulation task by id, including progress, logs, and result artifacts when they exist.

Artifact publication status and errors, log truncation, artifact completeness, backend version provenance, and configuration IDs persist with the task in the database. An artifact URI is returned only after publication has been recorded; an older on-disk manifest alone does not make an unpublished result available.

REST API
Python API

GET /api/simulation/tasks/{task_id}

Request: no body.

Path parameter: task_id (string, required)

Response:

{
  "id": "1a2b3c4d",
  "name": "Trace simulation",
  "description": "Replay a chat trace against a ready deployment",
  "scenario": "chat",
  "status": "completed",
  "endpoint_mode": "deployment",
  "endpoint_namespace": "prism-sim",
  "endpoint_service": "qwen-router",
  "endpoint_deployment_execution_id": "00000000-0000-4000-8000-000000000001",
  "endpoint_deployment_run_id": null,
  "endpoint_deployment_case_id": null,
  "endpoint_cluster_id": "cluster-1",
  "endpoint_cluster_name": "dev-cluster",
  "endpoint_deployment_name": "qwen3-guide",
  "endpoint_url": "http://127.0.0.1:38000/v1",
  "model_name": "Qwen/Qwen3-8B",
  "simulation": {
    "backend": "trace-replayer",
    "backend_options": {},
    "duration_seconds": 60.0,
    "num_requests": null,
    "stream": true,
    "warmup_enabled": false,
    "grace_period_seconds": 30.0
  },
  "prompt": {
    "type": "trace",
    "dataset": {"name": "mooncake-arxiv", "scenario": "chat", "tokenizer": null},
    "trace": {
      "path": "/home/prism/.local/share/prism/data/datasets/mooncake_trace.jsonl",
      "format": "mooncake_trace",
      "fixed_schedule": true,
      "timeout_seconds": 3600.0,
      "synthesis_speedup_ratio": 1.0,
      "start_seconds": 0.0,
      "end_seconds": null
    }
  },
  "task_dir": "/home/prism/.local/share/prism/data/artifacts/simulations/1a2b3c4d",
  "artifact_uri": "artifact://simulation/1a2b3c4d",
  "artifact_error": null,
  "logs_truncated": false,
  "artifacts_incomplete": false,
  "backend_version_inferred": false,
  "backend_version": "0.2.0",
  "configuration_ids": ["config-1"],
  "progress_percent": 100.0,
  "progress_message": "Simulation completed",
  "logs": ["Starting trace-replayer", "Simulation completed"],
  "result": {
    "run_id": "trace-replayer-1",
    "backend": "trace-replayer",
    "backend_version": "0.2.0",
    "summary": {
      "throughput_tps": 1180.4,
      "success_rate": 99.8,
      "completion_timeline": []
    },
    "artifacts": [
      {
        "uri": "artifact://simulation/1a2b3c4d/summary.json",
        "kind": "summary-json",
        "path": "/home/prism/.local/share/prism/data/artifacts/simulations/1a2b3c4d/summary.json",
        "media_type": "application/json"
      }
    ],
    "per_request": [
      {
        "request_id": 1,
        "status_code": 200,
        "successful": true,
        "error": null,
        "started_at_seconds": 0.0,
        "completed_at_seconds": 0.42,
        "latency_ms": 420.0,
        "ttft_ms": 110.0,
        "tpot_ms": 8.3,
        "input_tokens": 512.0,
        "output_tokens": 128.0,
        "metadata": {}
      }
    ],
    "backend_metrics": {},
    "warnings": []
  },
  "error_message": null,
  "created_at": "2026-09-23T09:18:24.287000Z",
  "started_at": "2026-09-23T09:18:25.000000Z",
  "execution_started_at": "2026-09-23T09:18:27.000000Z",
  "completed_at": "2026-09-23T09:19:32.000000Z",
  "owner_pid": null,
  "owner_instance_id": null
}

import asyncio

from llm_d_lens.simulation.service import get_task

async def main() -> None:
    task = await get_task("1a2b3c4d")
    if task is not None:
        print(task.id, task.status, task.progress_percent)

asyncio.run(main())

Download a simulation artifact

Download a saved simulation artifact by task id and artifact kind as a file attachment.

REST API
Python API

GET /api/simulation/tasks/{task_id}/artifacts/{kind}

Request: no body.

Path parameters: task_id (string, required), kind (string, required)

Response: file attachment streamed from the saved artifact path. No JSON body is returned. The task's result.artifacts list tells you which kind values are available.

import asyncio

from llm_d_lens.simulation.router import download_simulation_artifact

async def main() -> None:
    response = await download_simulation_artifact("1a2b3c4d", "summary-json")
    print(response.media_type)

asyncio.run(main())

Get response-code issues for a simulation task

Get requests from a Simulation task that returned a specific HTTP status code.

REST API
Python API

GET /api/simulation/tasks/{task_id}/response-code-issues

Request: no body.

Path parameter: task_id (string, required)
Query parameters: status_code (string, required; use unknown for missing status), offset (integer, default 0), limit (integer, default 100, max 500)

Response:

{
  "task_id": "1a2b3c4d",
  "status_code": 500,
  "issues": [
    {
      "request_number": 12,
      "request_id": 12,
      "status_code": 500,
      "error": "Transport error: upstream reset the connection",
      "started_at_seconds": 14.2,
      "latency_ms": 982.5,
      "input_tokens": 512.0,
      "output_tokens": 0.0
    }
  ],
  "total": 1,
  "offset": 0,
  "limit": 100
}

import asyncio

from llm_d_lens.simulation.service import get_response_code_issues

async def main() -> None:
    issues = await get_response_code_issues("1a2b3c4d", 500, offset=0, limit=20)
    print(issues.task_id, issues.total)

asyncio.run(main())

Stop a simulation task

Stop an active Simulation task.

REST API
Python API

POST /api/simulation/tasks/{task_id}/stop

Request: no body.

Path parameter: task_id (string, required)

Response:

{
  "task_id": "1a2b3c4d",
  "status": "cancelling"
}

import asyncio

from llm_d_lens.simulation.service import stop_task

async def main() -> None:
    await stop_task("1a2b3c4d")

asyncio.run(main())

Rerun a simulation task

Queue a rerun of a previous Simulation task, optionally rebinding it to a fresh endpoint or deployment execution.

REST API
Python API

POST /api/simulation/tasks/{task_id}/rerun

Request body: SimulationTaskRerunRequest (optional)

Path parameter: task_id (string, required)
Optional body fields: endpoint_url, endpoint_deployment_execution_id, endpoint_cluster_id, endpoint_cluster_name, endpoint_deployment_name
model_service_group_id (string, optional) — re-bind to a published, health-probed Model Service instead of a raw deployment execution; resolved the same way as on task creation and preferred over endpoint_deployment_execution_id when both are supplied.

{
  "endpoint_url": "http://127.0.0.1:39000/v1",
  "endpoint_deployment_execution_id": "00000000-0000-4000-8000-000000000002",
  "endpoint_cluster_id": "cluster-1",
  "endpoint_cluster_name": "dev-cluster",
  "endpoint_deployment_name": "qwen3-guide-rerun"
}

Response:

{
  "task_id": "5e6f7a8b",
  "status": "queued",
  "task": {
    "id": "5e6f7a8b",
    "name": "Trace simulation · rerun 5e6f7a8b",
    "description": "Replay a chat trace against a ready deployment",
    "scenario": "chat",
    "status": "queued",
    "endpoint_mode": "deployment",
    "endpoint_namespace": "prism-sim",
    "endpoint_service": "qwen-router",
    "endpoint_deployment_execution_id": "00000000-0000-4000-8000-000000000002",
    "endpoint_deployment_run_id": null,
    "endpoint_deployment_case_id": null,
    "endpoint_cluster_id": "cluster-1",
    "endpoint_cluster_name": "dev-cluster",
    "endpoint_deployment_name": "qwen3-guide-rerun",
    "endpoint_url": "http://127.0.0.1:39000/v1",
    "model_name": "Qwen/Qwen3-8B",
    "simulation": {
      "backend": "trace-replayer",
      "backend_options": {},
      "duration_seconds": 60.0,
      "num_requests": null,
      "stream": true,
      "warmup_enabled": false,
      "grace_period_seconds": 30.0
    },
    "prompt": {
      "type": "trace",
      "dataset": {"name": "mooncake-arxiv", "scenario": "chat", "tokenizer": null},
      "trace": {
        "path": "/home/prism/.local/share/prism/data/datasets/mooncake_trace.jsonl",
        "format": "mooncake_trace",
        "fixed_schedule": true,
        "timeout_seconds": 3600.0,
        "synthesis_speedup_ratio": 1.0,
        "start_seconds": 0.0,
        "end_seconds": null
      }
    },
    "task_dir": "/home/prism/.local/share/prism/data/artifacts/simulations/5e6f7a8b",
    "artifact_uri": null,
    "artifact_error": null,
    "logs_truncated": false,
    "artifacts_incomplete": false,
    "backend_version_inferred": false,
    "backend_version": null,
    "configuration_ids": ["config-2"],
    "progress_percent": 0.0,
    "progress_message": "Queued",
    "logs": [],
    "result": null,
    "error_message": null,
    "created_at": "2026-09-23T09:25:24.287000Z",
    "started_at": null,
    "execution_started_at": null,
    "completed_at": null,
    "owner_pid": null,
    "owner_instance_id": null
  }
}

import asyncio

from llm_d_lens.simulation.models import SimulationTaskRerunRequest
from llm_d_lens.simulation.service import rerun_task


async def main() -> None:
    task = await rerun_task(
        "1a2b3c4d",
        override=SimulationTaskRerunRequest(
            endpoint_deployment_execution_id="00000000-0000-4000-8000-000000000002",
            endpoint_url="http://127.0.0.1:39000/v1",
        ),
    )
    print(task.id, task.name)

    # Or re-bind to a published Model Service (preferred over
    # endpoint_deployment_execution_id when both are supplied):
    task = await rerun_task(
        "1a2b3c4d",
        override=SimulationTaskRerunRequest(model_service_group_id="01998e6b-4b2e-7c7e-8c6d-8e2a3f0c9b11"),
    )
    print(task.id, task.name)


asyncio.run(main())

Delete a simulation task

Delete a Simulation task record.

REST API
Python API

DELETE /api/simulation/tasks/{task_id}

Request: no body.

Path parameter: task_id (string, required)

Response:

{
  "task_id": "1a2b3c4d",
  "status": "deleted"
}

import asyncio

from llm_d_lens.simulation.service import delete_task

async def main() -> None:
    await delete_task("1a2b3c4d")

asyncio.run(main())

See the full request/response schemas in the FastAPI OpenAPI schema (regenerate with npm run docs:api).

Backend API​

List simulation backends​

Discover endpoint models​

List simulation scenarios​

List trace datasets​

Download a trace dataset​

Get a trace dataset timeline​

List simulation tasks​

Create a simulation task​

Get a simulation task​

Download a simulation artifact​

Get response-code issues for a simulation task​

Stop a simulation task​

Rerun a simulation task​

Delete a simulation task​

Backend API

List simulation backends

Discover endpoint models

List simulation scenarios

List trace datasets

Download a trace dataset

Get a trace dataset timeline

List simulation tasks

Create a simulation task

Get a simulation task

Download a simulation artifact

Get response-code issues for a simulation task

Stop a simulation task

Rerun a simulation task

Delete a simulation task