Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.inference.net/llms.txt

Use this file to discover all available pages before exploring further.

Use inf trace to inspect multi-step LLM workflows captured by Catalyst Tracing. It mirrors the dashboard trace viewer for headless debugging: list trace summaries, open a trace tree, render a timeline, inspect captured conversation messages, discover filter facets, and queue/download trace exports. Alias: inf traces

inf trace list

Display trace summaries in the active project.
inf trace list
Alias: inf trace ls

Options

FlagRequiredDescriptionDefault
-l, --limit <n>NoMaximum number of traces25
--cursor <cursor>NoPagination cursor from a previous response-
--sort <key>NoSort by start_time, duration, total_cost, total_tokens, span_count, or llm_span_countServer default
--order <asc|desc>NoSort orderServer default
--range <preset>NoRelative time range: 1h, 6h, 12h, 1d, 3d, 7d, 14d, 30d, 90d, all1d
--from <iso>NoStart time. Must be used with --to-
--to <iso>NoEnd time. Must be used with --from-
--kind <kind>NoObservation kind. Repeat or comma-separate values like LLM,TOOL,AGENTAll kinds
--provider <name>NoLLM provider filterAll providers
--model <name>NoLLM model filterAll models
--service <name>NoOpenTelemetry service.name filterAll services
--environment <name>NoDeployment environment filterAll environments
--user <id>NoUser ID filterAll users
--session <id>NoSession ID filterAll sessions
--agent <name>NoAgent name filterAll agents
--status <ok|error>NoTrace status filterAll statuses
--filter <expr>NoAdvanced typed field filter. Repeatable-
--metadata <expr>NoSpan attribute filter. Repeatable-
--resource <expr>NoResource attribute filter. Repeatable-
Use --json for the raw API payload with full trace IDs, pagination cursors, and aggregate counts.

Examples

# Recent traces
inf trace list

# Failed LLM traces from the last hour
inf trace list --range 1h --kind LLM --status error

# Slow traces by duration, sorted longest first
inf trace list --filter "duration_ms>5000" --sort duration --order desc

# Filter by service and model
inf trace list --service api --model claude-sonnet-4-5

inf trace get

Open a single trace and its spans.
inf trace get <trace-id>
Alias: inf trace show

Arguments

ArgumentRequiredDescription
trace-idYesTrace ID

Options

FlagRequiredDescriptionDefault
--view <view>Nosummary, tree, timeline, thread, spans, or rawsummary
--span <span-id>NoHighlight a selected span in the tree view-
--limit <n>NoMaximum spans to fetch for this trace1000
--cursor <cursor>NoSpan pagination cursor-
-o, --output <path>NoWrite raw JSON to a file-
The default summary view prints trace metadata and an ASCII span tree. Use --view raw or global --json when piping trace data into scripts.

Examples

# Summary plus span tree
inf trace get 2f0d2b...

# Text waterfall ordered by span start time
inf trace get 2f0d2b... --view timeline

# Conversation-style view from captured input/output messages
inf trace get 2f0d2b... --view thread

# Persist raw trace + spans JSON for local analysis
inf trace get 2f0d2b... --view raw -o trace.json

inf trace facets

Inspect available trace filter values and counts. This is useful when building a repeatable query and you do not know the exact model, service, environment, or attribute values in a project.
inf trace facets

Options

inf trace facets accepts the same filter flags as inf trace list, plus:
FlagRequiredDescriptionDefault
--facet <id>NoFacet ID. Repeat or comma-separate valuesAll supported facets
--search <facet=query>NoSearch within a facet’s values. Repeatable-
--attribute-key <scope:key>NoFetch values for one span: or resource: attribute key-
-l, --limit <n>NoMaximum options per facet50

Examples

# Show all default trace facets
inf trace facets --range 7d

# Find model facet values containing "claude"
inf trace facets --facet llm_model_name --search llm_model_name=claude

# Explore values for an OpenTelemetry span attribute
inf trace facets --attribute-key span:gen_ai.operation.name

Advanced filter syntax

--filter, --metadata, and --resource are repeatable. Quote expressions so your shell does not interpret operators.
ExpressionMeaning
duration_ms>500Numeric comparison. duration and duration_ms are converted to nanoseconds for the API
total_tokens between:100,500Numeric range
span_count>=3Trace aggregate filter
llm_model_name~claudeString contains
service_name in:api,workerString set membership
agent_name not-emptyNon-empty string field
--metadata gen_ai.operation.name=chatSpan attribute equality
--resource service.version~2026Resource attribute contains

inf trace export

Trace exports create downloadable JSONL files for offline analysis, support escalations, or long-running review workflows.

inf trace export create

Queue an export job.
inf trace export create --range 7d --kind LLM
FlagRequiredDescriptionDefault
--from <iso> / --to <iso>NoExplicit export window-
--range <preset>NoRelative export window1d
--kind <kind>NoObservation kind filterAll kinds
--trace-id <id>NoTrace ID. Repeat or comma-separate values-
--session <id>NoSession ID filter-
--user <id>NoUser ID filter-
--agent <name>NoAgent name filter-
--model <name>NoLLM model filter-
--status-code <OK|ERROR|UNSET>NoSpan status code filter-
--attribute <key=value>NoAttribute equality match. Repeatable-
--waitNoPoll until the export finishesOff
--downloadNoDownload after the export is readyOff
-o, --output <path>NoDownload pathGenerated from job ID
# Queue and print a job ID
inf trace export create --range 30d --kind LLM

# Queue, wait, and download in one command
inf trace export create --range 7d --status-code ERROR --wait --download -o failed-traces.jsonl

inf trace export list

inf trace export list

inf trace export status

inf trace export status <job-id>

inf trace export download

inf trace export download <job-id> -o traces.jsonl