CLI | Respan Docs

The Respan CLI lets you authenticate, integrate coding agents, query traces and logs, manage prompts and datasets, run evaluators, and more.

Install


Setup

The fastest way to get started with Respan. Sets up your API key, installs the Respan skill for your coding agent, and opens the agent to instrument your project.


The wizard walks through:

  1. API key — saved to .env, verified with a demo trace
  2. Agent selection — auto-detects Claude Code, Cursor, Codex, Gemini CLI, or OpenCode
  3. Skill install — the agent learns how to set up Respan tracing
  4. Launch — opens the agent with the setup skill pre-loaded
Command Description
respan setup Interactive setup wizard
respan setup doctor Diagnose agent setup (installed skills, API key, configs)
Flag Description
--agent <name> Skip detection (claude-code, cursor, codex-cli, gemini-cli, opencode)
--no-instrument Skip opening the agent after setup

Authentication


Command Description
respan auth login Authenticate interactively or with --api-key
respan auth status Check auth status and available profiles
respan whoami Show current authenticated user

Profiles allow you to manage multiple environments (e.g. staging vs production):

Flag Description
--profile <name> Use or create a named profile

Any command accepts --profile to target a specific environment.

Integrate

Set up tracing for CLI coding agents with a single command. Each writes a hook to ~/.respan/hooks/ and registers it with the agent. See the CLI agents cookbook for details.

Command Description
respan integrate claude-code Set up tracing for Claude Code
respan integrate codex-cli Set up tracing for Codex CLI
respan integrate gemini-cli Set up tracing for Gemini CLI
respan integrate opencode Set up tracing for OpenCode
Flag Description
--customer-id <id> Customer identifier attached to traces
--workflow-name <name> Workflow name for grouping traces
--span-name <name> Root span name (defaults to agent name)
--project-id <id> Respan project ID
--attrs <json> Custom attributes as JSON string
--global Apply to all projects
--local Apply to current project only
--dry-run Preview changes without writing files

Logs

Query and inspect individual LLM request spans.

Command Description
respan logs list List recent logs
respan logs get <id> Get a specific log by ID
respan logs summary Get aggregated stats
respan logs create Create a log span manually
Flag Description
--filter <expr> Filter results (e.g. model::gpt-4o, cost:gt:0.01)
--start-time <iso> Start of time range
--end-time <iso> End of time range
--model <name> Model for create
--prompt <text> Input for create
--completion <text> Output for create

Traces

Query and inspect traces (hierarchical groups of spans).

Command Description
respan traces list List recent traces
respan traces get <id> Get a trace with its full span tree
respan traces summary Get trace summary stats
Flag Description
--filter <expr> Filter results (e.g. total_cost:gt:0.10, customer_identifier::user_123)
--start-time <iso> Start of time range
--end-time <iso> End of time range

Users

Manage customer and user records.

Command Description
respan users list List users
respan users get <id> Get user details
respan users create Create a user
respan users update <id> Update a user
Flag Description
--sort-by <field> Sort results (prefix with - for descending)
--customer-identifier <id> Customer identifier for create
--name <name> User display name

Prompts

Manage prompt templates and versions.

Command Description
respan prompts list List all prompts
respan prompts get <id> Get a prompt with its current version
respan prompts versions <id> List all versions of a prompt
respan prompts create Create a new prompt
respan prompts create-version <id> Create a new version of a prompt
respan prompts update <id> Update prompt metadata
Flag Description
--name <name> Prompt name
--model <model> Default model
--messages <json> Messages array as JSON

Datasets

Manage evaluation datasets and their spans.

Command Description
respan datasets list List datasets
respan datasets get <id> Get dataset details
respan datasets create Create a dataset
respan datasets update <id> Update a dataset
respan datasets spans <id> List spans in a dataset
respan datasets add-spans <id> Add existing spans to a dataset
respan datasets create-span <id> Create a new span in a dataset
Flag Description
--name <name> Dataset name
--span-ids <ids> Comma-separated span IDs for add-spans
--input <text> Span input for create-span
--output <text> Span output for create-span

Evaluators

Manage and run evaluators on datasets.

Command Description
respan evaluators list List evaluators
respan evaluators get <id> Get evaluator details
respan evaluators create Create an evaluator
respan evaluators run <id> Run an evaluator on a dataset
respan evaluators update <id> Update an evaluator
Flag Description
--name <name> Evaluator name
--type <type> Evaluator type (llm, human, code)
--dataset-id <id> Target dataset for run

Experiments

Manage experiments for comparing prompt and model configurations.

Command Description
respan experiments list List experiments
respan experiments get <id> Get experiment details
respan experiments create Create an experiment
Flag Description
--name <name> Experiment name
--dataset-id <id> Dataset to run against

Global options

These options work with any command.

Flag Description
--json Output as JSON
--csv Output as CSV
--limit <n> Limit number of results
--page <n> Page number for pagination
--profile <name> Use a named profile

Filter syntax

All list commands support --filter field:operator:value:

Operator Description Example
(empty) Exact match model::gpt-4o
gt / gte Greater than (or equal) cost:gt:0.01
lt / lte Less than (or equal) latency:lt:500
not Not equal status_code:not:200
icontains Case-insensitive contains customer_identifier:icontains:alice
startswith Starts with model:startswith:gpt
in Value in list model:in:gpt-4o,claude-3