Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, review experiments, and inspect datasets. Use when debugging AI/LLM applications, analyzing trace data, working with Phoenix observability, or investigating LLM performance issues.
npxskills add majiayu000/claude-skill-registry--skill phoenix-cliLoading…
Debug and analyze LLM applications using the Phoenix CLI (px).
npm install -g @arizeai/phoenix-cli
# Or run directly with npx
npx @arizeai/phoenix-cli
Set environment variables before running commands:
export PHOENIX_HOST=http://localhost:6006
export PHOENIX_PROJECT=my-project
export PHOENIX_API_KEY=your-api-key # if authentication is enabled
CLI flags override environment variables when specified.
px traces --limit 10
px traces --limit 50 --format raw --no-progress | jq '.[] | select(.status == "ERROR")'
px trace <trace-id>
px trace <trace-id> --format raw | jq '.spans[] | select(.status_code != "OK")'
px traces --limit 20 --format raw --no-progress | jq 'sort_by(-.duration) | .[0:5]'
px trace <trace-id> --format raw | jq '.spans | sort_by(-.duration_ms) | .[0:5] | .[] | {name, duration_ms, span_kind}'
Extract models and token counts:
px traces --limit 50 --format raw --no-progress | \
jq -r '.[].spans[] | select(.span_kind == "LLM") | {model: .attributes["llm.model_name"], prompt_tokens: .attributes["llm.token_count.prompt"], completion_tokens: .attributes["llm.token_count.completion"]}'
px datasets
px experiments --dataset my-dataset
px experiment <experiment-id> --format raw --no-progress | \
jq '.[] | select(.error != null) | {input: .input, error}'
px experiment <experiment-id> --format raw --no-progress | \
jq '[.[].latency_ms] | add / length'
Fetch recent traces from a project.
px traces [directory] [options]
| Option | Description |
|---|---|
[directory] | Save traces as JSON files to directory |
-n, --limit <number> | Number of traces (default: 10) |
--last-n-minutes <number> | Filter by time window |
--since <timestamp> | Fetch since ISO timestamp |
--format <format> | pretty, json, or raw |
Fetch a specific trace by ID.
px trace <trace-id> [options]
| Option | Description |
|---|---|
--file <path> | Save to file |
--format <format> | pretty, json, or raw |
--include-annotations | Include span annotations |
List all datasets.
px datasets [options]
Fetch examples from a dataset.
px dataset <dataset-name> [options]
| Option | Description |
|---|---|
--split <name> | Filter by split (repeatable) |
--version <id> | Specific dataset version |
--file <path> | Save to file |
List experiments for a dataset.
px experiments --dataset <name> [directory]
| Option | Description |
|---|---|
--dataset <name> | Dataset name or ID (required) |
[directory] | Export experiment JSON to directory |
Fetch a single experiment with run data.
px experiment <experiment-id> [options]
List all prompts.
px prompts [options]
Fetch a specific prompt.
px prompt <prompt-name> [options]
pretty (default): Human-readable tree viewjson: Formatted JSON with indentationraw: Compact JSON for piping to jq or other toolsUse --format raw --no-progress when piping output to other commands.
Traces contain spans with OpenInference semantic attributes:
{
"traceId": "abc123",
"spans": [{
"name": "chat_completion",
"span_kind": "LLM",
"status_code": "OK",
"attributes": {
"llm.model_name": "gpt-4",
"llm.token_count.prompt": 512,
"llm.token_count.completion": 256,
"input.value": "What is the weather?",
"output.value": "The weather is sunny..."
}
}],
"duration": 1250,
"status": "OK"
}
Key span kinds: LLM, CHAIN, TOOL, RETRIEVER, EMBEDDING, AGENT.
Key attributes for LLM spans:
llm.model_name: Model usedllm.provider: Provider name (e.g., "openai")llm.token_count.prompt / llm.token_count.completion: Token countsllm.input_messages.*: Input messages (indexed, with role and content)llm.output_messages.*: Output messages (indexed, with role and content)input.value / output.value: Raw input/output as textexception.message: Error message if failed--include-annotations | Include span annotations |
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).