pflow settings command group manages pflow configuration stored in ~/.pflow/settings.json. This includes API keys, environment variables, and node filtering.
Your commands. These are setup commands that you run directly - not your agent. API keys and security settings should always be configured by you, never by an AI agent. Read-only discovery (
llm show, llm providers, llm models) is safe for agents to run.Commands
pflow settings init
Initialize settings file with defaults.~/.pflow/settings.json with default configuration. Prompts for confirmation if the file already exists.
Default settings:
pflow settings show
Display current settings with everyenv value masked.
Every
env value is masked to its length (*** (N chars)), whatever its name — the same rule as list-env. Use pflow settings list-env --show-values to see full values.pflow settings set-env
Set an environment variable for pflow workflows.KEY- Environment variable nameVALUE- Environment variable value
- It fills the declared workflow input of the same name. A
${...}template reads it only through that input. - It is exported into pflow’s environment when a run starts, unless your shell already exports that name. Shell, code and agent steps see it like any other exported variable, and LLM providers that LiteLLM handles itself (such as OpenRouter) find their keys there.
ANTHROPIC_API_KEY, OPENAI_API_KEY, GEMINI_API_KEY, and provider-specific equivalents from your environment first, then from settings.
pflow settings unset-env
Remove an environment variable.KEY- Environment variable name to remove
pflow settings list-env
List all configured environment variables.--show-values- Display full unmasked values (use with caution)
pflow settings allow
Add an allow pattern for node filtering.PATTERN- Glob-style pattern for nodes to allow
*matches any characters?matches single character[seq]matches any character in seq
pflow settings deny
Add a deny pattern for node filtering.PATTERN- Glob-style pattern for nodes to deny
Deny patterns take precedence over allow patterns.
pflow settings remove
Remove a pattern from allow or deny list.PATTERN- Pattern to remove
--allow- Remove from allow list (default)--deny- Remove from deny list
pflow settings check
Check if a node would be included based on current settings.NODE_NAME- Node name to check
pflow settings reset
Reset settings to defaults.LLM model settings
These commands let you override which models pflow uses for its internal features. By default, pflow auto-detects based on your configured API keys - these are optional.pflow settings llm show
Display LLM model settings with resolution status.pflow settings llm models
List the model ids you can pass to an LLM node’smodel, per provider.
- No keyword: up to 10 models for each provider you have a key for, each with a
see allcommand. - A provider name (e.g.
anthropic,bedrock): that provider’s complete list, even without a key. The header shows the env var to set. - Any other keyword: filters model ids across your configured providers (or within a named provider). All keywords must match; matching ignores case.
provider/model even if it isn’t listed. The catalog can also lag behind a provider: an id it still lists may already be retired (the run then fails with Unknown model and names a working one).
Examples:
source is live or offline; status is set, - (no key) or n/a (local provider). JSON lists every matched model. Naming a provider inspects it without its key. With no provider named and no keys configured, or when nothing matches, providers is empty and the guidance goes to stderr.
pflow settings llm set-default
Override the auto-detected model for all pflow LLM usage.MODEL- Model identifier (e.g.,openai/gpt-5.2,anthropic/claude-sonnet-4-5,gemini/gemini-3-flash-preview). LiteLLM requires the provider prefix.
- LLM nodes in workflows (when no model specified in params)
- Discovery commands (when
discovery_modelnot set) - Smart filtering (when
filtering_modelnot set)
Bare model names are auto-prefixed. Bare names from known providers
(
gpt-*, o1*, o3*, o4*, claude-*, gemini-*) are rewritten to
the canonical <provider>/<name> form at write time, with a
Normalized: line confirming the rewrite. Unknown bare names pass
through with a warning so custom or self-hosted models still work.
This applies to set-default, set-discovery, and set-filtering —
not to the TTS setters (TTS ids aren’t LiteLLM-routed).pflow settings llm set-discovery
Set the model for discovery commands (pflow mcp find, pflow find).
MODEL- Model identifier
pflow settings llm set-filtering
Set the model for smart field filtering (used whensmart output mode filters large API responses).
MODEL- Model identifier
pflow settings llm set-tts-model / set-tts-voice
Configure voice narration forpflow ui focus/frame --say (see the UI command). Both have working defaults — you only need these to change the voice or track a new TTS model. Narration also needs a Gemini API key (pflow settings set-env GEMINI_API_KEY <value>).
pflow settings llm unset
Remove an LLM model setting. Models revert to auto-detection; the TTS fields revert to their built-in defaults.SETTING- Which setting to remove:default,discovery,filtering,tts-model,tts-voice, orall
Model resolution order
pflow uses the same resolution order for all LLM usage (discovery, filtering, and workflow LLM nodes):- Explicit setting (workflow params or feature-specific setting)
default_modelfrom settings- Auto-detect from configured API keys (Anthropic → Google → OpenAI)
- Error with setup instructions
Most users just need an API key configured. pflow auto-detects the appropriate model. Use these commands only to override the auto-detected model.
Registry settings
Configure howpflow probe displays output.
pflow settings registry output-mode
Show or set the output display mode forpflow probe.
MODE(optional) - One ofsmart,structure, orfull. If omitted, shows current mode.
Examples:
How node filtering works
Node filtering uses allow and deny patterns evaluated in this order:- Deny patterns - Block matching nodes (highest precedence)
- Allow patterns - Include matching nodes
- Default - Include if
*in allow list
Environment variable precedence
When a workflow declares an input, pflow looks for its value in this order:- CLI parameters (
key=valuearguments) - Shell environment variables (
export key=value) - Settings environment variables (
pflow settings set-env) - Workflow defaults
- Error if required and not found
Sensitive parameter detection
Values under these names are masked as<REDACTED> when pflow displays them:
password,passwd,pwdtoken,api_token,access_token,auth_tokenapi_key,apikey,api-keysecret,client_secret,secret_keyprivate_key,ssh_keycredential,credentials,authorization,authcookie,cookies(so the HTTPCookieandSet-Cookieheaders)
snake_case, kebab-case and camelCase: GITHUB_TOKEN, X-API-Key and sessionCookie are masked, while author and tokens are not.
Masking applies to pflow report, the web UI, approval previews and error output. Execution always uses the real value, and declared workflow outputs are not masked by name.
Secret values
Masking by name misses a secret that travels into free text — shell stderr, an error message, a workflow result. So pflow also replaces every occurrence of a run’s secret values with<REDACTED> in everything it prints: CLI text and JSON output (results included), MCP responses, pflow report, the web UI and -v.
A run’s secret values are every value stored with pflow settings set-env and every value passed to a declared input with a sensitive name — strings of 8 characters or more. A value exported only in your shell, or one a step produces mid-run, is not known to be secret and prints as is. The trace file keeps every value raw so pflow resume can restore it.
File locations
Related
- CLI overview - Main pflow command
- Configuration reference - All configuration options
- Quickstart - Initial setup including API keys

