Files
scriptorium/docs/cli.md

18 KiB

CLI Reference

This is the canonical contract for invoking Scriptorium. Configuration discovery, precedence, application source locations, and server settings are defined in the configuration reference. The HTTP API reference owns service request and response behavior.

Shortest Useful Command

go run ./cmd/scriptorium render \
  --config ./examples/config.yml \
  --prompt generic.markdown_summary \
  --input transcript=./examples/fixtures/transcript.md \
  --input glossary=./examples/fixtures/glossary.yml

render prepares a request without calling an LLM.

Commands

  • scriptorium run: prepare a prompt, call the configured LLM, and write the generated artifact.
  • scriptorium render: prepare a prompt and write prepared-run output.
  • scriptorium serve: start the HTTP server.
  • scriptorium inspect prompt: inspect one prompt definition without model execution.
  • scriptorium inspect profile: inspect one effective profile without model execution.
  • scriptorium inspect configuration: validate or inspect Promptkit's captured framework configuration.
  • scriptorium config validate: validate application configuration without building an engine.
  • scriptorium config show: show the resolved application configuration.
  • scriptorium config sources: show the ordered configuration sources.
  • scriptorium config explain: explain one effective or historical configuration path.

All command families accept --config <path> and --config-overlay <name>; positional arguments are rejected. --config-overlay selects one application configuration overlay; it is separate from --profile, which selects a Promptkit execution profile. See configuration composition for name, root, and no-base behavior. run, render, serve, inspect prompt, inspect profile, and inspect configuration accept repeated --promptkit-source <path> flags and --schema-dir <dir> where applicable. They replace the configured source sequence in flag order. --prompt-dir and --profile-dir are no longer supported; use promptkit_sources in application configuration or the repeated source flags. Application config commands remain independent of framework source loading. Explicit application flags, including empty values, override file settings. Configuration load diagnostics go to stderr and exit with status 1; successful load warnings are printed once before command work.

scriptorium run

scriptorium run [flags]

Required flags:

Flag Meaning
--prompt <id> Prompt ID to execute.

Optional flags:

Flag Meaning
--config <path> Application configuration file.
--config-overlay <name> Selected application configuration overlay.
--promptkit-source <path> PromptKit source file or directory; repeat to select ordered sources.
--schema-dir <dir> Schema base-directory override.
--prompt-version <version> Optional prompt-definition version selector.
--profile <id> Execution-profile override.
--session-id <id> Optional direct session identifier.
--input name=path Optional input file mapping; repeat or use comma-separated mappings.
--var name=value Template-variable mapping; repeat or use comma-separated mappings.
--out <path> Write generated content to this file instead of stdout.
--execution-report <path> Write an opt-in terminal execution report as newline-terminated JSON to a separate file.
--llm-base-url <url> Runtime endpoint override.
--model <name> Runtime model override.
--api-key-env <name> Runtime API-key environment-variable name override.
--temperature <float> Runtime temperature override.
--max-tokens <int> Runtime maximum-token override.
--top-p <float> Runtime top-p override.
--reasoning-effort <value> Runtime reasoning-effort override.
--timeout <duration> Runtime timeout override using Go duration syntax.
--run-timeout <duration> Optional whole-run engine deadline using Go duration syntax; zero or omission adds no deadline, negative values are invalid.
--transient-retries <integer> Nonnegative additional transient attempt count for this request; 0 disables additional attempts.

Deprecated aliases: --prompt-id for --prompt, and --profile-id for --profile.

Omitted numeric runtime flags preserve the selected effective value; explicit zero values override it. --timeout 0s disables the per-attempt generation deadline only; the caller context and configured transport cap remain active. CLI durations are converted to whole seconds by truncation toward zero, so any duration whose absolute value is below one second becomes an explicit zero-second override. The timeout layers are defined in the Promptkit outbound integration contract. With the built-in client, each transient retry gets a fresh generation timeout; this flag does not limit the complete run. --run-timeout keeps subsecond precision and starts immediately before engine execution. It bounds preparation, capacity waits, retry waits, generation, and repairs where they honor context. Parsing, engine construction, and output writes are outside that interval. A failed run whose execution context reaches this deadline exits 1 with a safe deadline diagnostic; a completed invalid output still exits 2. It does not promise immediate interruption of synchronous work. Omitting --transient-retries inherits the application setting or Promptkit's current default of two additional attempts. The flag overrides only this request; it does not alter the configured engine. Structural repair generations have separate transient retry budgets.

There is no raw API-key flag. Use --api-key-env.

--prompt-version is passed directly to Promptkit. When it is omitted, the selected prompt ID must have exactly one available version. --input is optional at the CLI boundary: Promptkit decides whether the selected definition requires declared inputs or template-referenced values.

--session-id supplies a direct, non-secret session identifier. A nonblank value replaces a definition-rendered session ID; an omitted or blank value lets the definition supply one. Promptkit trims direct values and limits them to 256 Unicode code points. Use stable, non-sensitive identifiers because effective session IDs may appear in prepared output, run metadata, and provider-facing requests.

--reasoning-effort is presence-aware: omitting it inherits the selected profile value, a nonblank value replaces that value, and --reasoning-effort= explicitly clears inherited reasoning. Promptkit treats nonblank values as provider-specific opaque strings.

Execution report file

--execution-report requires a nonempty path. It is available only for run; - is an ordinary filename. Parent directories are not created. An existing file is replaced through ordinary file writing, without rollback or an atomic replacement guarantee. Generated content still goes to stdout or --out. Equal output/report paths, including existing paths that refer to the same file, are rejected before execution.

The file is written after engine execution when Promptkit supplies a terminal event, including for a failed run or invalid generated output. A failure before invocation leaves the report path untouched. If no terminal event is supplied, Scriptorium leaves the path untouched and emits a diagnostic; an existing file may therefore contain an older report. Artifact output is attempted first on a successful run, and report writing is attempted even if artifact writing fails. Any output or report write failure exits 1; already-written output is not undone. Without a write failure, the actual run keeps its usual exit status.

The HTTP API reference defines the shared report fields and usage-presence semantics. The file contains that JSON object followed by a newline.

The report excludes content, credentials, URLs, headers, and raw errors, but its identifiers can still be sensitive. The caller owns file retention and access.

scriptorium render

scriptorium render [flags]

--prompt <id> is required. The following optional flags are supported: --config, --config-overlay, repeatable --promptkit-source, --schema-dir, --prompt-version, --profile, --input, --var, --out, --llm-base-url, --model, --api-key-env, --temperature, --max-tokens, --top-p, --reasoning-effort, --session-id, --timeout, --transient-retries, and --format text|json. Their meanings match the corresponding run flags; --format selects prepared-run output and otherwise uses defaults.render_format.

The same deprecated aliases and numeric/timeout behavior as run apply. The same session and reasoning inheritance, replacement, and clearing behavior also applies. render validates the retry override but does not generate model output or include a retry field in prepared output. render resolves profiles and schemas as part of preparation but does not call an LLM.

scriptorium serve

scriptorium serve [flags]

Optional flags:

Flag Meaning
--config <path> Application configuration file.
--config-overlay <name> Selected application configuration overlay.
--addr <listen-address> HTTP listen-address override.
--promptkit-source <path> PromptKit source file or directory; repeat to select ordered sources.
--schema-dir <dir> Schema base-directory override.
--artifact-root <dir> Root for HTTP file input references.
--max-request-bytes <n> Maximum encoded HTTP request-body bytes; 0 disables the limit.
--max-artifact-bytes <n> Maximum HTTP file-input artifact bytes; 0 disables the limit.
--max-response-bytes <n> Maximum encoded HTTP response bytes; 0 disables the limit.

serve accepts no runtime model override flags. HTTP request fields, response schemas, and error codes are defined in the HTTP API reference.

scriptorium inspect prompt

scriptorium inspect prompt --prompt ID [--prompt-version VERSION]
    [--config PATH] [--config-overlay NAME] [--promptkit-source PATH ...] [--schema-dir DIR] [--format text|json] [--out PATH]

--prompt is required. Inspection uses normal configuration discovery and the selected Promptkit sources, defaults to text regardless of defaults.render_format, and writes to stdout unless --out is supplied.

Both definition-inspection commands first construct the same engine used for execution from the complete selected source sequence. Construction resolves and validates all effective definitions, including unused ones, and captures referenced message-file contents and static template syntax. Invalid unused definitions or unreadable message resources can therefore prevent inspection. No prompt collection is mandatory, but selected prompts are not ignored.

Inspection does not prepare an execution request, load request-time schemas or artifacts, resolve credential values, reserve backend capacity, or call a model. Prompt inspection does not select an execution profile or render request-specific templates.

scriptorium inspect profile

scriptorium inspect profile --profile ID
    [--config PATH] [--config-overlay NAME] [--promptkit-source PATH ...] [--schema-dir DIR] [--format text|json] [--out PATH]

--profile is required. After the full-source engine construction described above, inspection selects one effective profile with resolved inheritance and backend defaults. Unset provider controls are shown as zero values when Promptkit leaves them unspecified.

Application configuration inspection

scriptorium config validate [flags]
scriptorium config show [flags]
scriptorium config sources [flags]
scriptorium config explain --path JSON_POINTER [flags]

Each accepts --config, --config-overlay, --schema-dir, --addr, --artifact-root, --max-request-bytes, --max-artifact-bytes, and --max-response-bytes. These are application configuration selectors and overrides; request, credential, backend-editing, output-format, and output-file flags are not accepted. Positional arguments are rejected.

validate writes no success output; status 0 means the application configuration loaded and passed its own validation. It does not establish that selected Promptkit sources can construct an engine, credentials are present, or a provider is available. show writes ConfigKit's resolved YAML snapshot. sources writes one newline-terminated JSON array of source records in load order. Each record has id, label, and layer, plus path when available; explicit CLI overrides appear as synthetic sources. Defaults-only input without overrides produces [] for sources.

explain requires an explicitly supplied --path in JSON Pointer syntax. The empty string selects the root; /server/addr selects a field; ~1 and ~0 escape / and ~ inside mapping keys. Numeric tokens are interpreted according to the containing mapping or sequence. Dotted paths, file paths, and URL fragments are not accepted. ConfigKit writes a human-readable account of the effective value and its chronological default, file/import, overlay, CLI, normalization, and removed-value history. This is not a JSON schema or a byte-for-byte stable prose format. Unknown and malformed paths exit 1 without successful explanation output.

Diagnostics and warnings go to stderr, never into successful stdout. Parse, load, output, and diagnostic-write failures exit 1. Ordinary output writes may leave partial data on failure. Application inspection can contain paths and configured values; protect its output accordingly. Raw API-key values are not accepted by the application configuration schema.

Framework configuration inspection

scriptorium inspect configuration validate [flags]
scriptorium inspect configuration show [flags]
scriptorium inspect configuration sources [flags]
scriptorium inspect configuration explain --path JSON_POINTER [flags]

Each operation accepts --config, --config-overlay, repeatable --promptkit-source, and --schema-dir. These flags select the application settings and framework sources; positional arguments, --format, and --out are not accepted. Unlike config validate, framework validate constructs the Promptkit engine and validates all effective definitions, including unused ones. It writes nothing on success and does not prepare a request, resolve a credential, or contact a provider.

show writes Promptkit's native effective YAML, an inspection snapshot rather than a promised reloadable file. sources writes a newline-terminated JSON array in captured source order. Each source record has id, label, layer, kind, and underlay_index, plus path when available and imported_from for imported sources. That nested object has source_id, line, and column. Values and output structure are a projection of the captured Promptkit view, not Scriptorium's application-source records.

explain requires an explicitly supplied --path in ConfigKit JSON Pointer syntax; --path '' selects the root. For example, /profiles/team~1summary/model addresses the model field of the literal profile ID team/summary. Escape / as ~1 and ~ as ~0; dots in a key remain literal. Malformed and unknown pointers exit 1 without a successful report. Explanation prose is native and is not a stable machine-readable format.

Framework show and explain use Promptkit's native redaction for its classified credential-shaped provider fields, including historical values. Environment-variable reference names and ordinary provider parameters remain visible. Arbitrary prompt or provider content is not classified as secret by name inspection, so treat these reports as sensitive. This redaction policy is limited to framework configuration reports; it does not add redaction to inspect profile or prepared-run output. Credentials are not resolved by any of these inspection operations. Promptkit owns detailed field and source semantics; see its tagged format reference.

Warnings and errors go to stderr. Successful validate writes nothing to stdout; successful show, sources, and explain write their reports there. Parse, load, path, and output failures exit 1. A native writer error may leave partial output.

Input And Variable Syntax

--input name=path maps an input name to a local file; --var name=value maps a template variable to a string. Both flags can be repeated or contain comma-separated mappings. Values may contain = after the first separator. Empty names and values are rejected.

CLI inputs are file references. HTTP inline inputs are defined by the HTTP API reference.

Output And Exit Behavior

  • run writes generated content to stdout, or to --out when supplied, and writes a concise summary to stderr. The summary includes backend=<id> when Promptkit selected a backend; endpoint-only profiles omit it.
  • render writes prepared-run output to stdout, or to --out when supplied, without a success summary. Text output includes selected_backend_id after selected_profile_id when Promptkit selected one; endpoint-only profiles omit it.
  • serve writes startup and server errors to stderr.

Exit statuses:

Status Meaning
0 Success.
1 Parse, configuration, loading, rendering, generation, output-write, or other runtime error.
2 run generated and wrote output, but validation failed.

A backend admission rejection is a runtime error and prints run error: model backend capacity is exhausted. The HTTP capacity response is defined in the HTTP API reference.

Workflows And Examples

The maintained render script is a copyable render workflow. The HTTP request example is for a running serve process.