Files
scriptorium/docs/roadmap/library.md

135 lines
5.2 KiB
Markdown

# Library API Roadmap
This roadmap defines the target behavior for making Scriptorium usable as an imported Go library while retaining the current standalone CLI and HTTP application behavior.
The implementation plan for this feature lives in `docs/roadmap/implementation.md`.
## Motivation
Scriptorium is currently optimized for subprocess use by other applications. That contract remains useful because it is language-neutral, operationally simple, and process-isolated.
For Go callers, an imported library should provide:
- typed requests and results instead of stdout/stderr parsing;
- direct `context.Context` cancellation;
- lower overhead for repeated calls;
- easier test integration through injected clients or fixtures;
- direct access to prepared-run data without process management;
- fewer integration points where secrets or output metadata can be mishandled.
The library is an additional adapter surface, not a replacement for the CLI or HTTP API.
## Target State
Scriptorium should expose a small public Go API suitable for common embedding use cases:
- construct an engine from app-level settings such as prompt, profile, and schema directories;
- prepare a prompt request without calling an LLM;
- run a prompt request and receive a typed result;
- pass file and inline artifacts;
- apply profile selection, runtime overrides, vars, validation behavior, cache-control behavior, and structured-output behavior consistently with CLI/HTTP;
- inject a custom LLM client or HTTP client where needed;
- preserve existing CLI and HTTP behavior by continuing to route all entry paths through the same use-case layer.
The public library API should be stable, narrow, and intentionally higher-level than the current `internal/*` package layout.
## Public Package Policy
The public package should be the module root:
```go
import "gitea.maximumdirect.net/eric/scriptorium"
```
Recommended usage shape:
```go
engine, err := scriptorium.NewEngine(scriptorium.Config{
PromptDir: "./prompts",
ProfileDir: "./profiles",
SchemaDir: "./schemas",
})
if err != nil {
return err
}
prepared, err := engine.Prepare(ctx, scriptorium.RunRequest{
PromptID: "generic.markdown_summary",
Inputs: map[string]scriptorium.ArtifactRef{
"transcript": scriptorium.File("./transcript.md"),
},
})
result, err := engine.Run(ctx, scriptorium.RunRequest{
PromptID: "generic.markdown_summary",
Inputs: map[string]scriptorium.ArtifactRef{
"transcript": scriptorium.File("./transcript.md"),
},
})
```
## Policy Decisions
### Public Package Scope
Expose a narrow root facade package and keep existing `internal/*` packages internal.
Reasoning:
This gives callers the workflow they need without freezing the internal architecture as public API. It also preserves the current package-boundary policy and keeps future refactoring possible.
### Public Type Strategy
Define public facade types and map them to internal domain types.
Reasoning:
Public types can be designed around caller needs and long-term stability. Internal types can continue to evolve with implementation details such as adapter metadata, validation internals, and provider-specific behavior.
### CLI And HTTP Reuse
Keep CLI and HTTP on current internal wiring for the initial library release. Consider migrating them to the public facade only after the facade proves stable.
Reasoning:
This minimizes risk to the existing subprocess and HTTP contracts while adding the new API. It also avoids forcing the first public facade to satisfy every adapter edge case immediately.
### Error Surface
Expose public sentinel errors or typed error categories and map internal errors to them while preserving wrapped context.
Reasoning:
Library callers need stable, idiomatic error checks. Mapping internal errors avoids exposing internal package paths as public compatibility promises.
## Scope
In scope:
- Public facade package for library consumers.
- Public request, result, prepared-run, artifact reference, execution override, validation, and config types.
- Public constructors for common file and inline input references.
- Public engine methods for `Prepare` and `Run`.
- Optional dependency injection for LLM behavior and HTTP behavior.
- Stable error behavior suitable for `errors.Is` and `errors.As`.
- Tests proving public API behavior matches CLI/use-case behavior.
- Documentation and examples for library usage after implementation.
Out of scope for the first library release:
- Making every `internal/*` package public.
- Replacing or rewiring the CLI or HTTP adapters.
- Adding a durable run store or workflow engine.
- Adding broad provider-specific SDK surfaces.
- Adding non-Go language bindings.
- Adding global mutable configuration.
## Acceptance Criteria
- A Go caller can import the root module and run a prompt without invoking a subprocess.
- A Go caller can prepare a prompt without invoking an LLM.
- Public library behavior matches current CLI/HTTP use-case semantics for prompt/profile loading, artifact reading, rendering, validation, and model invocation.
- Existing CLI and HTTP behavior remains unchanged.
- Library tests use injected/fake LLM behavior and do not require real provider credentials.
- Public documentation is concise and limited to implemented behavior once code exists.