eric/scriptorium
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 6 Wiki Activity

Implement a library profile API and built-in profile docs

Browse Source
This commit is contained in:
Eric Rakestraw
2026-07-04 17:23:34 -05:00
parent 4669b73d38
commit d60ef66f53
10 changed files with 493 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/cli.md
View File

@@ -32,6 +32,7 @@ Integration references:
- an effective `prompt_dir` from flags or config
- `serve` requires an effective `prompt_dir` from flags or config.
- `profile_dir` is optional. If omitted, only built-in profiles are available; if provided, custom profiles override built-ins with the same ID.
- Built-in profile IDs are listed in the [configuration reference](config.md#profile-definition-files).
- Positional arguments are rejected.
- Prompt cache control is configured in prompt YAML (`messages[].cache_control`), not with CLI flags.
- Provider-specific `reasoning_effort` and `extra_params` are configured in profile YAML or HTTP model overrides, not with CLI flags.

28
docs/config.md
View File

@@ -220,6 +220,34 @@ Profile rules:
- Duplicate profile IDs are invalid. If multiple files declare the requested profile ID, Scriptorium fails instead of choosing one.
- `extra_params` keys must not be empty and must not collide with reserved outbound request fields: `model`, `session_id`, `messages`, `temperature`, `max_tokens`, `top_p`, `service_tier`, `reasoning_effort`, or `response_format`.
Built-in profile IDs:
| Provider | ID | Model | API key env |
| --- | --- | --- | --- |
| aion-labs | `aion-2` | `aion-labs/aion-2.0` | `OPENROUTER_API_KEY` |
| anthropic | `claude-fable-latest` | `~anthropic/claude-fable-latest` | `OPENROUTER_API_KEY` |
| anthropic | `claude-haiku-latest` | `~anthropic/claude-haiku-latest` | `OPENROUTER_API_KEY` |
| anthropic | `claude-opus-latest` | `~anthropic/claude-opus-latest` | `OPENROUTER_API_KEY` |
| anthropic | `claude-sonnet-latest` | `~anthropic/claude-sonnet-latest` | `OPENROUTER_API_KEY` |
| deepseek | `deepseek-3-2` | `deepseek/deepseek-v3.2` | `OPENROUTER_API_KEY` |
| deepseek | `deepseek-4-pro` | `deepseek/deepseek-v4-pro` | `OPENROUTER_API_KEY` |
| google | `gemini-2-flash` | `google/gemini-2.5-flash` | `OPENROUTER_API_KEY` |
| google | `gemini-2-flash-lite` | `google/gemini-2.5-flash-lite` | `OPENROUTER_API_KEY` |
| google | `gemini-2-pro` | `google/gemini-2.5-pro` | `OPENROUTER_API_KEY` |
| google | `gemini-3-flash-lite` | `google/gemini-3.1-flash-lite` | `OPENROUTER_API_KEY` |
| google | `gemini-flash-latest` | `~google/gemini-flash-latest` | `OPENROUTER_API_KEY` |
| google | `gemini-pro-latest` | `~google/gemini-pro-latest` | `OPENROUTER_API_KEY` |
| google | `gemma-4-31b` | `google/gemma-4-31b-it:exacto` | `OPENROUTER_API_KEY` |
| minimax | `minimax-m2` | `minimax/minimax-m2.5` | `OPENROUTER_API_KEY` |
| minimax | `minimax-m3` | `minimax/minimax-m3` | `OPENROUTER_API_KEY` |
| mistral | `mistral-large-2512` | `mistralai/mistral-large-2512` | `OPENROUTER_API_KEY` |
| mistral | `mistral-medium-3-5` | `mistralai/mistral-medium-3-5` | `OPENROUTER_API_KEY` |
| mistral | `mistral-small-3` | `mistralai/mistral-small-3.2-24b-instruct` | `OPENROUTER_API_KEY` |
| mistral | `mistral-small-4` | `mistralai/mistral-small-2603` | `OPENROUTER_API_KEY` |
| nvidia | `nemotron-3-ultra` | `nvidia/nemotron-3-ultra-550b-a55b` | `OPENROUTER_API_KEY` |
| openai | `gpt-5-mini` | `openai/gpt-5.4-mini` | `OPENROUTER_API_KEY` |
| openai | `gpt-5-nano` | `openai/gpt-5.4-nano` | `OPENROUTER_API_KEY` |
Current outbound request behavior:
- The OpenAI-compatible client currently serializes: `model`, optional `session_id`, `messages`, `temperature`, `max_tokens`, `top_p`, `service_tier`, `reasoning_effort`, optional `response_format` for `json_schema` prompts, and `extra_params`.

19
docs/consumers/pkg-scriptorium.md
View File

@@ -33,6 +33,25 @@ Directory fields on `Config` remain the compatibility path. Explicit source opti
Prompt and profile sources load standard Scriptorium YAML with the same strict validation as directory sources. Prompt `content_file` paths resolve relative to the prompt file in the same source. Profile options overlay custom profiles above built-ins. Schema `fs.FS` sources preserve prompt `schema_path` semantics; schema file options expose the file by its base name.
## In-Memory Profiles
Use `WithProfiles` when the consuming application already has profile settings in typed Go configuration:
```go
profile := scriptorium.OpenAICompatibleProfile(scriptorium.OpenAICompatibleProfileConfig{
ID: "app.default",
Endpoint: "https://openrouter.ai/api/v1",
Model: "mistralai/mistral-small-3.2-24b-instruct",
APIKeyRequired: true,
})
engine, err := scriptorium.NewEngine(cfg, scriptorium.WithProfiles(profile))
```
In-memory profiles have highest precedence, followed by configured profile file/FS/directory sources, then built-in profiles. Duplicate IDs in one `WithProfiles` call return `ErrInvalidConfig`.
`Profile` and `OpenAICompatibleProfileConfig` include endpoint, model, numeric defaults, service tier, reasoning effort, `APIKeyRequired`, and JSON-compatible `ExtraParams`. They do not accept raw API-key fields. When `APIKeyRequired` is true, pass the secret with `RunRequest.APIKey`.
## Prepare A Prompt
`Prepare` resolves the prompt definition, profile, inputs, variables, output contract, structured-output metadata, and rendered messages without calling an LLM.