pastilhasandClaude Opus 5
d7f3223b6a
sd-server (stable-diffusion.cpp, Vulkan) serving Qwen-Image 2.1 on this machine. It already speaks OpenAI's image API, which is the vocabulary `ImageRequest` is written in, so there is no translation layer — only the parts that are true of a local GPU and not of a hosted one. ── keyless is a category, not an exception ── `credentials.ts` decided a provider was usable by asking whether a key existed, so a service that takes none read as unconfigured forever. The fix is an adapter declaring `keyless`, not a dummy secret: a dummy would record a credential that does not exist and make the secret store lie about what is configured, and that store is the one place meant to be the truth about them. A keyless adapter never reaches `keyFor` at all. That function's own comment says why it uses `getSecret` rather than `getKey` — so a missing FOREIGN credential is never minted — and a provider with no credential by design has no business in that path. whisper, OCR and TTS already run on this machine, so this will not be the last. ── measured, not assumed ── The integration doc said "tens of seconds, not two". The server's own log says 512x512 completes in ~185s and 1024x1024 samples at ~41.4s/step over 20 steps, about 14 minutes. And it serialises strictly: a second caller waits for the first to finish entirely, so a queued 512 can wait 17 minutes before a byte comes back. So: 512 is the default and the substitute for `auto`, 1024 is offered with the cost in its label, and `timeout: false` is a requirement rather than caution — every default anyone would reach for is far under 17 minutes. The caller's `signal` still aborts, because a user cancelling is not a client giving up. ── the model id moved, because only it could ── `GET /v1/models` returns `sd-cpp-local`, hardcoded in sd-server with no override. The catalogue now agrees with the server and carries "Qwen-Image 2.1 (local)" in the label, so requests name a model the server knows while the UI still says something meaningful. ── not shipped: edit() ── Same GPU, same queue. It doubles the ways generation can be blocked while the generate path is unproven in anger, and `ImageAdapter` makes absence the way to say so — the route answers 400 instead of the queue finding out late. Verified: /v1/models answers, provider statuses report qwen-local as configured/keyless/usable, and the shipped entry survives the merge with the stored catalogue.json. NOT verified end to end — a generation is occupying the GPU and I left it alone. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Officer-Session: de3ed4e6-f88a-429c-94e6-a760336ba83b
23 lines
947 B
TypeScript
23 lines
947 B
TypeScript
import { openaiAdapter } from './openai';
|
|
import { qwenLocalAdapter } from './qwen-local';
|
|
import type { ImageAdapter } from './types';
|
|
|
|
export * from './types';
|
|
|
|
/**
|
|
* Every adapter Atelier can speak — the CODE side.
|
|
*
|
|
* An adapter knows a vendor's HTTP API. It is written once and rarely changes. What model to use,
|
|
* whose key, and whether it is switched on are not its business: those are a `providers` row, made
|
|
* and edited at runtime. Several providers can share one adapter, which is the entire point — OpenAI
|
|
* with gpt-image-1 and OpenAI with dall-e-3 are two configurations of one piece of code.
|
|
*
|
|
* A list in one place, the way `hono.ts` keeps its mounts: adding an adapter is a new file plus a
|
|
* line here.
|
|
*/
|
|
export const ADAPTERS: ImageAdapter[] = [openaiAdapter, qwenLocalAdapter];
|
|
|
|
export function adapterByName(name: string): ImageAdapter | undefined {
|
|
return ADAPTERS.find((adapter) => adapter.name === name);
|
|
}
|