Skip to main content

vLLora CLI

The vLLora CLI brings the core functionality of the vLLora MCP server to the terminal. It’s designed for fast iteration, local reproduction, and automation workflows where you want direct command-line access to traces, exports, and recent failures.

Quick Start​

The core workflow is:

Find a trace​

vllora traces list --last-n-minutes 60 --limit 20
+--------------------------------------+----------------------+------------------+--------+---------------+---------------------+--------------------------------------+--------------------------------------+
| Trace ID                             | Span ID              | Operation        | Status | Duration (ms) | Start Time          | Run ID                               | Thread ID                            |
+--------------------------------------+----------------------+------------------+--------+---------------+---------------------+--------------------------------------+--------------------------------------+
| a7838793-6421-43b9-9dcb-0bc08fc6ab6f | 13919283956904092872 | openai           | ✓ OK   | 14312         | 2025-12-23 05:04:38 | 4ea18f79-4c4c-4d2c-b628-20d510af7181 | 7510b431-109c-42b2-a858-f05c29a4f952 |
+--------------------------------------+----------------------+------------------+--------+---------------+---------------------+--------------------------------------+--------------------------------------+
| a7838793-6421-43b9-9dcb-0bc08fc6ab6f | 314675728497877876   | run              | ✓ OK   | 14320         | 2025-12-23 05:04:38 | 4ea18f79-4c4c-4d2c-b628-20d510af7181 | 7510b431-109c-42b2-a858-f05c29a4f952 |
+--------------------------------------+----------------------+------------------+--------+---------------+---------------------+--------------------------------------+--------------------------------------+
... truncated ...

Inspect the run​

vllora traces run-info --run-id <run-id>
Run Overview:
+--------------+--------------------------------------+
| Field        | Value                                |
+--------------+--------------------------------------+
| Run ID       | 4ea18f79-4c4c-4d2c-b628-20d510af7181 |
| Status       | ok                                   |
| Start Time   | 2025-12-23T05:02:52.801745+00:00     |
| Duration     | 120114 ms                            |
| Root Span ID | 10384579106551160164                 |
+--------------+--------------------------------------+

LLM Calls (18):
+----------------------+----------+--------------+----------+-------+
| Span ID              | Provider | Model        | Messages | Tools |
+----------------------+----------+--------------+----------+-------+
| 12495210593948314377 | openai   | gpt-4.1-mini | 30       | 0     |
+----------------------+----------+--------------+----------+-------+
... truncated ...

Inspect an LLM call​

vllora traces call-info --span-id <span-id>
{
  "span_id": "12495210593948314377",
  "trace_id": "40c1a59d-5d10-47c5-8e68-65dcf7a31668",
  "run_id": "4ea18f79-4c4c-4d2c-b628-20d510af7181",
  "thread_id": "7510b431-109c-42b2-a858-f05c29a4f952",
  "duration_ms": 1515,
  "costs": "0.0016456000245213508",
  "raw_request": "{\"messages\":[{\"role\":\"system\",\"content\":\"...\"},{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Plan a 5-day trip to Tokyo in April\"}]}],\"model\":\"gpt-4.1-mini\",\"stream\":false,\"temperature\":0.7,\"tool_choice\":\"auto\",\"tools\":[...]}",
  "raw_response": "{\"id\":\"chatcmpl_...\",\"choices\":[{\"index\":0,\"message\":{\"role\":\"assistant\",\"tool_calls\":[{\"id\":\"call_...\",\"type\":\"function\",\"function\":{\"name\":\"research_destination\",\"arguments\":\"{\\\"destination\\\":\\\"Tokyo\\\"}\"}}]},\"finish_reason\":\"tool_calls\"}],\"model\":\"gpt-4.1-mini-2025-04-14\",\"usage\":{\"prompt_tokens\":3910,\"completion_tokens\":51,\"total_tokens\":3961}}"
}

Commands​

traces list​

Search/list traces by various criteria.

vllora traces list [OPTIONS]

Options:

  • --limit <LIMIT> - Limit number of results (default: 20)
  • --offset <OFFSET> - Offset for pagination (default: 0)
  • --run-id <RUN_ID> - Filter by run ID
  • --thread-id <THREAD_ID> - Filter by thread ID
  • --operation-name <OPERATION_NAME> - Filter by operation name: run, agent, task, tools, openai, anthropic, bedrock, gemini, model_call
  • --text <TEXT> - Text search query
  • --last-n-minutes <LAST_N_MINUTES> - Filter traces from last N minutes
  • --sort-by <SORT_BY> - Sort by field (default: start_time)
  • --sort-order <SORT_ORDER> - Sort order: asc or desc (default: desc)
  • --output <OUTPUT> - Output format: table or json (default: table)

Example:

vllora traces list --last-n-minutes 60 --limit 20

traces call-info​

Get detailed LLM call information for a span.

vllora traces call-info --span-id <SPAN_ID> [OPTIONS]

Options:

  • --span-id <SPAN_ID> - Span ID (required)
  • --output <OUTPUT> - Output format: table or json (default: table)

Example:

vllora traces call-info --span-id 12495210593948314377 --output json

traces run-info​

Get overview of a run and its spans.

vllora traces run-info --run-id <RUN_ID> [OPTIONS]

Options:

  • --run-id <RUN_ID> - Run ID (required)
  • --output <OUTPUT> - Output format: table or json (default: table)

Example:

vllora traces run-info --run-id 4ea18f79-4c4c-4d2c-b628-20d510af7181

traces overview​

Get aggregated stats for recent LLM and tool calls.

vllora traces overview --last-n-minutes <LAST_N_MINUTES> [OPTIONS]

Options:

  • --last-n-minutes <LAST_N_MINUTES> - Number of minutes in the past to include (required)
  • --output <OUTPUT> - Output format: table or json (default: table)

Example:

vllora traces overview --last-n-minutes 60

When to Use CLI vs Other Methods​

The CLI is ideal for:

  • Terminal workflows - Quick checks without leaving your terminal
  • Scripts and automation - Monitoring, reporting. Use --output json with shell redirection to export: vllora traces list --last-n-minutes 60 --output json > traces.json
  • Local reproduction - Exporting trace data for debugging
  • Bulk operations - Processing many traces at once

For visual exploration and deep dives, use the Web UI. For debugging from coding agents or IDE tools, use the MCP Server.