feat(catalogue): a curated file of providers and models, refreshed daily
The five connections in the database were never configured by anyone — a migration minted one per model from the adapter's own list, so the table held five decisions nobody made. What that list actually is, is a CATALOGUE: what you can choose from, which is not the same kind of thing as what you chose. So it is a file. `sidecar/catalogue/shipped.ts` is the curated baseline, in git, reviewed; `$OFFICER_ROOT/data/atelier/catalogue.json` is what a refresh writes, and it wins where it has something to say. Data dir, not the plugin dir — a plugin directory is a clone an update replaces, which is the rule env.ts already states for images. Refresh runs in the sidecar, daily, and only on boot when the file is actually stale — this process has restarted twenty times in an afternoon and should not hit OpenAI twenty times for it. Two sources, unequal, and the code says so. `GET /v1/models` is authoritative and thin: ids and nothing else, so a model matching /^(gpt-image|dall-e)/ appears the day it ships without a release. Prices come off an HTML page because there is no pricing endpoint for any plan, and that parser is written to give up rather than guess — a guess gets written to disk and then believed. When it gives up it says so in the log; the durable replacement is handing the page to a model for structured output, which Officer can already do locally. Nothing a refresh cannot establish overwrites a curated value: fields merge one by one, not objects wholesale, so an id-only listing cannot wipe the sizes and prices that were written by hand. Retiring is decided by the merge, which can tell a complete listing from a request that failed halfway — and it marks `deprecated` rather than deleting, because the gallery labels 88 historical rows from this list. Per-model sizes, qualities and transparency now travel with each entry, which is what will let the form stop offering dall-e-2 a transparent background it cannot do. The catalogue is advisory throughout: validate.ts still refuses to enforce per-model rules, exactly as before.
This commit is contained in:
+23
-1
@@ -22,14 +22,36 @@ export type ProviderStatus = {
|
||||
updated_at: string;
|
||||
};
|
||||
|
||||
/** The code side — what a new provider can be built on. */
|
||||
/** One model in the catalogue — what it makes, what it accepts, what it costs. */
|
||||
export type CatalogueModel = {
|
||||
id: string;
|
||||
label?: string;
|
||||
kind: 'image' | 'video';
|
||||
sizes?: string[];
|
||||
qualities?: string[];
|
||||
transparency?: boolean;
|
||||
edit?: boolean;
|
||||
pricing?: Record<string, unknown>;
|
||||
status?: 'current' | 'deprecated';
|
||||
source?: 'shipped' | 'api' | 'scraped';
|
||||
};
|
||||
|
||||
/**
|
||||
* What a new connection can be built on: a catalogue provider that has an adapter behind it.
|
||||
*
|
||||
* `models` is the flat list of ids; `model_details` carries the per-model facts, which is what lets a
|
||||
* form offer dall-e-2's three sizes rather than gpt-image-1's four. The catalogue is refreshed daily
|
||||
* in the sidecar — `updated_at` says when, and is null while only the shipped file has been read.
|
||||
*/
|
||||
export type Adapter = {
|
||||
name: string;
|
||||
label: string;
|
||||
models: string[];
|
||||
model_details: CatalogueModel[];
|
||||
default_model: string;
|
||||
env_var: string;
|
||||
supports_edit: boolean;
|
||||
updated_at: string | null;
|
||||
};
|
||||
|
||||
/** Snake case, matching the server — one spelling per field across every endpoint. */
|
||||
|
||||
Reference in New Issue
Block a user