mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-14 11:12:17 +03:00
Compare commits
1 Commits
feat/bridg
...
feat/image
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
55a2af03df |
@@ -107,26 +107,6 @@ fragment the cache. Failed describes are never cached. Settings:
|
||||
| `modalityBridgeCacheTtlMinutes` | `60` | 1–1440 |
|
||||
| `modalityBridgeCacheMaxEntries` | `200` | 10–5000 |
|
||||
|
||||
#### Remote image normalization (self-loop describe/base64 fetch)
|
||||
|
||||
When the bridge fetches a **remote** image itself — the Anthropic describe
|
||||
self-call and the claude-wire-format base64 conversion
|
||||
(`ensureBase64ImagesForClaudeWire`), both via
|
||||
`fetchRemoteImageAsDataUri()` in `visionBridgeHelpers.ts` — the resulting data
|
||||
URI is passed through `normalizeDataUri()`
|
||||
(`open-sse/utils/imageNormalize.ts`) before being embedded in the vision-model
|
||||
request. Oversized images are downscaled to a **2048px long edge** (matching
|
||||
the resize cap OpenAI/Anthropic already apply server-side), which cuts
|
||||
upload bytes/latency without changing what the vision model sees. Resizing
|
||||
uses `sharp`, loaded via dynamic import: on a platform where its native
|
||||
binary fails to load, `normalizeDataUri()` **never throws** — it falls back
|
||||
to a passthrough of the original bytes, so the describe/base64-conversion
|
||||
path always keeps working. Non-image bytes (a fetch that did not return a
|
||||
decodable image) are also passed through untouched. This normalization is
|
||||
scoped to images the bridge fetches for its own self-call — it is never
|
||||
applied to the caller's raw passthrough payload, consistent with the
|
||||
opt-in-only mutation principle (Hard Rule #20).
|
||||
|
||||
#### Settings schema + migration
|
||||
|
||||
The new `modalityBridge*` keys are Zod-validated in `updateSettingsSchema`
|
||||
|
||||
@@ -1,62 +0,0 @@
|
||||
/**
|
||||
* Optional-sharp image normalization.
|
||||
*
|
||||
* Rationale (migrated from freellmapi `server/src/lib/image-normalize.ts:40-58`):
|
||||
* OpenAI resizes images to a long-edge cap of 2048px server-side, Anthropic applies
|
||||
* a similar cap. Downscaling client-side before upload reduces tokens/latency without
|
||||
* changing model behavior. `sharp` is loaded via dynamic import so that a platform
|
||||
* where its native binary fails to load never crashes the request path — it just
|
||||
* falls back to a passthrough (original buffer, unresized).
|
||||
*/
|
||||
|
||||
const DEFAULT_MAX_LONG_EDGE = 2048;
|
||||
|
||||
type SharpModule = typeof import("sharp");
|
||||
let sharpPromise: Promise<SharpModule | null> | null = null;
|
||||
|
||||
async function loadSharp(): Promise<SharpModule | null> {
|
||||
if (!sharpPromise) {
|
||||
sharpPromise = import("sharp").then((m) => (m.default ?? m) as SharpModule).catch(() => null);
|
||||
}
|
||||
return sharpPromise;
|
||||
}
|
||||
|
||||
export async function normalizeImageBuffer(
|
||||
input: Buffer,
|
||||
opts?: { maxLongEdge?: number }
|
||||
): Promise<{ buffer: Buffer; mime: string | null; resized: boolean }> {
|
||||
const maxLongEdge = opts?.maxLongEdge ?? DEFAULT_MAX_LONG_EDGE;
|
||||
const sharp = await loadSharp();
|
||||
if (!sharp) return { buffer: input, mime: null, resized: false };
|
||||
try {
|
||||
const img = sharp(input, { failOn: "error" });
|
||||
const meta = await img.metadata();
|
||||
const long = Math.max(meta.width ?? 0, meta.height ?? 0);
|
||||
if (!long || long <= maxLongEdge) {
|
||||
return { buffer: input, mime: meta.format ? `image/${meta.format}` : null, resized: false };
|
||||
}
|
||||
const buffer = await img
|
||||
.resize({ width: maxLongEdge, height: maxLongEdge, fit: "inside", withoutEnlargement: true })
|
||||
.toBuffer();
|
||||
return { buffer, mime: meta.format ? `image/${meta.format}` : null, resized: true };
|
||||
} catch {
|
||||
return { buffer: input, mime: null, resized: false };
|
||||
}
|
||||
}
|
||||
|
||||
export async function normalizeDataUri(
|
||||
dataUri: string,
|
||||
opts?: { maxLongEdge?: number }
|
||||
): Promise<string> {
|
||||
try {
|
||||
const match = /^data:([^;,]+);base64,(.*)$/s.exec(dataUri);
|
||||
if (!match) return dataUri;
|
||||
const input = Buffer.from(match[2], "base64");
|
||||
if (!input.length) return dataUri;
|
||||
const out = await normalizeImageBuffer(input, opts);
|
||||
if (!out.resized) return dataUri;
|
||||
return `data:${match[1]};base64,${out.buffer.toString("base64")}`;
|
||||
} catch {
|
||||
return dataUri;
|
||||
}
|
||||
}
|
||||
@@ -2,7 +2,6 @@
|
||||
* Vision Bridge helper functions for image processing.
|
||||
*/
|
||||
import { detectMediaParts, type MediaPart } from "@omniroute/open-sse/utils/mediaParts";
|
||||
import { normalizeDataUri } from "@omniroute/open-sse/utils/imageNormalize";
|
||||
import { fetchRemoteImage } from "@/shared/network/remoteImageFetch";
|
||||
import { getRuntimePorts } from "@/lib/runtime/ports";
|
||||
import { resolveSelfLoopBearer } from "@/shared/middleware/chatBodyAdmission";
|
||||
@@ -315,12 +314,7 @@ async function fetchRemoteImageAsDataUri(
|
||||
fetchImpl,
|
||||
});
|
||||
const mediaType = remoteImage.contentType.split(";")[0]?.trim() || "image/png";
|
||||
const dataUri = `data:${mediaType};base64,${remoteImage.buffer.toString("base64")}`;
|
||||
// Downscale to the long-edge cap before handing the image to the vision
|
||||
// model self-call — scoped to this bridge-fetched image only, never the
|
||||
// user's raw passthrough payload (opt-in principle, HR#20).
|
||||
// `normalizeDataUri` never throws and is a passthrough for non-image bytes.
|
||||
return normalizeDataUri(dataUri);
|
||||
return `data:${mediaType};base64,${remoteImage.buffer.toString("base64")}`;
|
||||
}
|
||||
|
||||
async function normalizeVisionImageInput(
|
||||
|
||||
@@ -11,6 +11,7 @@ export const APIKEY_PROVIDERS_FRONTIER = {
|
||||
color: "#10A37F",
|
||||
textIcon: "OA",
|
||||
website: "https://platform.openai.com",
|
||||
serviceKinds: ["llm", "imageToText"],
|
||||
},
|
||||
reka: {
|
||||
id: "reka",
|
||||
@@ -52,6 +53,7 @@ export const APIKEY_PROVIDERS_FRONTIER = {
|
||||
color: "#D97757",
|
||||
textIcon: "AN",
|
||||
website: "https://platform.claude.com",
|
||||
serviceKinds: ["llm", "imageToText"],
|
||||
},
|
||||
gemini: {
|
||||
id: "gemini",
|
||||
@@ -64,6 +66,7 @@ export const APIKEY_PROVIDERS_FRONTIER = {
|
||||
hasFree: true,
|
||||
freeNote:
|
||||
"Free tier available through Google AI Studio; current per-model quotas and regional limits apply",
|
||||
serviceKinds: ["llm", "imageToText"],
|
||||
},
|
||||
groq: {
|
||||
id: "groq",
|
||||
@@ -75,6 +78,7 @@ export const APIKEY_PROVIDERS_FRONTIER = {
|
||||
website: "https://groq.com",
|
||||
hasFree: true,
|
||||
freeNote: "Free tier: 30 RPM / 14.4K RPD — no credit card",
|
||||
serviceKinds: ["llm", "imageToText"],
|
||||
},
|
||||
blackbox: {
|
||||
id: "blackbox",
|
||||
@@ -96,6 +100,7 @@ export const APIKEY_PROVIDERS_FRONTIER = {
|
||||
color: "#1DA1F2",
|
||||
textIcon: "XA",
|
||||
website: "https://x.ai",
|
||||
serviceKinds: ["llm", "imageToText"],
|
||||
},
|
||||
mistral: {
|
||||
id: "mistral",
|
||||
@@ -107,6 +112,7 @@ export const APIKEY_PROVIDERS_FRONTIER = {
|
||||
website: "https://mistral.ai",
|
||||
hasFree: true,
|
||||
freeNote: "Free Experiment tier: rate-limited access to all models, no credit card required",
|
||||
serviceKinds: ["llm", "imageToText"],
|
||||
},
|
||||
perplexity: {
|
||||
id: "perplexity",
|
||||
|
||||
@@ -82,6 +82,7 @@ export const APIKEY_PROVIDERS_GATEWAYS = {
|
||||
website: "https://openrouter.ai",
|
||||
hasFree: true,
|
||||
freeNote: "Free models at $0/token with :free suffix - 20 RPM / 200 RPD",
|
||||
serviceKinds: ["llm", "imageToText"],
|
||||
},
|
||||
requesty: {
|
||||
id: "requesty",
|
||||
|
||||
@@ -1,52 +0,0 @@
|
||||
import { test } from "node:test";
|
||||
import assert from "node:assert/strict";
|
||||
import { normalizeImageBuffer, normalizeDataUri } from "../../open-sse/utils/imageNormalize.ts";
|
||||
|
||||
test("passthrough when input is not a decodable image (sharp absent or garbage bytes)", async () => {
|
||||
const junk = Buffer.from("not-an-image");
|
||||
const out = await normalizeImageBuffer(junk);
|
||||
assert.equal(out.resized, false);
|
||||
assert.ok(out.buffer.equals(junk));
|
||||
});
|
||||
|
||||
test("normalizeDataUri never throws and preserves the uri on failure", async () => {
|
||||
const uri = "data:image/png;base64,%%%broken%%%";
|
||||
assert.equal(await normalizeDataUri(uri), uri);
|
||||
});
|
||||
|
||||
// Só roda quando sharp estiver instalado (optionalDependency presente no devbox):
|
||||
test("downscales a large PNG to the long-edge cap when sharp is available", async (t) => {
|
||||
let sharp: typeof import("sharp");
|
||||
try {
|
||||
sharp = (await import("sharp")).default as never;
|
||||
} catch {
|
||||
t.skip("sharp not installed");
|
||||
return;
|
||||
}
|
||||
const big = await sharp({ create: { width: 4096, height: 100, channels: 3, background: "#fff" } })
|
||||
.png()
|
||||
.toBuffer();
|
||||
const out = await normalizeImageBuffer(big, { maxLongEdge: 2048 });
|
||||
assert.equal(out.resized, true);
|
||||
const meta = await sharp(out.buffer).metadata();
|
||||
assert.equal(meta.width, 2048);
|
||||
});
|
||||
|
||||
test("downscales a height-dominant PNG to the long-edge cap on the height axis", async (t) => {
|
||||
let sharp: typeof import("sharp");
|
||||
try {
|
||||
sharp = (await import("sharp")).default as never;
|
||||
} catch {
|
||||
t.skip("sharp not installed");
|
||||
return;
|
||||
}
|
||||
const tall = await sharp({
|
||||
create: { width: 100, height: 4096, channels: 3, background: "#fff" },
|
||||
})
|
||||
.png()
|
||||
.toBuffer();
|
||||
const out = await normalizeImageBuffer(tall, { maxLongEdge: 2048 });
|
||||
assert.equal(out.resized, true);
|
||||
const meta = await sharp(out.buffer).metadata();
|
||||
assert.equal(meta.height, 2048);
|
||||
});
|
||||
42
tests/unit/imagetotext-service-kinds.test.ts
Normal file
42
tests/unit/imagetotext-service-kinds.test.ts
Normal file
@@ -0,0 +1,42 @@
|
||||
import { test } from "node:test";
|
||||
import assert from "node:assert/strict";
|
||||
|
||||
import { AI_PROVIDERS } from "../../src/shared/constants/providers.ts";
|
||||
import { resolveProviderServiceKinds } from "../../open-sse/config/mediaServiceKinds.ts";
|
||||
|
||||
/**
|
||||
* The Image-to-Text category (/dashboard/media-providers/imageToText) fills from
|
||||
* providers whose resolved serviceKinds include "imageToText". It has no backing
|
||||
* registry, so major vision-capable providers must declare it explicitly.
|
||||
*/
|
||||
const IMAGE_TO_TEXT_PROVIDERS = [
|
||||
"openai",
|
||||
"anthropic",
|
||||
"gemini",
|
||||
"openrouter",
|
||||
"mistral",
|
||||
"xai",
|
||||
"groq",
|
||||
] as const;
|
||||
|
||||
test("major vision providers declare the imageToText serviceKind", () => {
|
||||
for (const id of IMAGE_TO_TEXT_PROVIDERS) {
|
||||
const provider = AI_PROVIDERS[id] as { serviceKinds?: string[] } | undefined;
|
||||
assert.ok(provider, `provider "${id}" missing from AI_PROVIDERS`);
|
||||
const kinds = resolveProviderServiceKinds(id, provider.serviceKinds);
|
||||
assert.ok(kinds.includes("imageToText"), `"${id}" must resolve the imageToText serviceKind`);
|
||||
}
|
||||
});
|
||||
|
||||
test("declaring imageToText keeps the llm kind (inline Test button + playground default)", () => {
|
||||
// ProviderCard treats an EMPTY serviceKinds as "regular LLM provider"; once a
|
||||
// provider declares any kind, "llm" must be declared too or the Test button
|
||||
// and the playground default silently disappear.
|
||||
for (const id of IMAGE_TO_TEXT_PROVIDERS) {
|
||||
const provider = AI_PROVIDERS[id] as { serviceKinds?: string[] };
|
||||
assert.ok(
|
||||
(provider.serviceKinds ?? []).includes("llm"),
|
||||
`"${id}" declares serviceKinds without "llm" — this hides the inline Test button`
|
||||
);
|
||||
}
|
||||
});
|
||||
@@ -1,95 +0,0 @@
|
||||
/**
|
||||
* Task B2: the vision bridge self-loop fetches a remote image and hands it
|
||||
* to the vision model as a data URI (`fetchRemoteImageAsDataUri`,
|
||||
* `src/lib/guardrails/visionBridgeHelpers.ts`). That fetched image must be
|
||||
* normalized (long-edge cap 2048, `@omniroute/open-sse/utils/imageNormalize`)
|
||||
* before being embedded — the same treatment `normalizeDataUri` already
|
||||
* gives any other image, now applied to remote fetches performed by the
|
||||
* bridge itself. Scope: ONLY this self-call path, never the user's raw
|
||||
* passthrough payload (HR#20 opt-in principle).
|
||||
*
|
||||
* `ensureBase64ImagesForClaudeWire` is the exported entry point that reaches
|
||||
* the private `fetchRemoteImageAsDataUri` — it resolves every non-data-URI
|
||||
* image part of a claude-wire-format request via that same fetch helper, so
|
||||
* it is the smallest public surface to exercise the fetch → normalize path
|
||||
* with dependency-injected `fetchImpl` (mirrors the DI pattern used by
|
||||
* `tests/unit/vision-bridge-describe-cache.test.ts` and
|
||||
* `tests/unit/remote-image-fetch.test.ts`).
|
||||
*/
|
||||
import { test } from "node:test";
|
||||
import assert from "node:assert/strict";
|
||||
|
||||
import { ensureBase64ImagesForClaudeWire } from "../../src/lib/guardrails/visionBridgeHelpers.ts";
|
||||
|
||||
// zai speaks the claude wire format (open-sse/config/providers/registry/zai/index.ts),
|
||||
// so `isClaudeWireFormatModel` routes it through the base64 self-fetch path.
|
||||
const CLAUDE_WIRE_MODEL = "zai/glm-4.6";
|
||||
|
||||
function bodyWithRemoteImage(url: string) {
|
||||
return {
|
||||
messages: [
|
||||
{
|
||||
role: "user",
|
||||
content: [
|
||||
{ type: "text", text: "describe this" },
|
||||
{ type: "image_url", image_url: { url } },
|
||||
],
|
||||
},
|
||||
],
|
||||
};
|
||||
}
|
||||
|
||||
test("remote image fetched for the claude-wire self-call is downscaled to the long-edge cap", async (t) => {
|
||||
let sharp: typeof import("sharp");
|
||||
try {
|
||||
sharp = (await import("sharp")).default as never;
|
||||
} catch {
|
||||
t.skip("sharp not installed");
|
||||
return;
|
||||
}
|
||||
const big = await sharp({ create: { width: 4096, height: 100, channels: 3, background: "#fff" } })
|
||||
.png()
|
||||
.toBuffer();
|
||||
|
||||
const fetchImpl = (async () =>
|
||||
new Response(big, {
|
||||
status: 200,
|
||||
headers: { "content-type": "image/png" },
|
||||
})) as unknown as typeof fetch;
|
||||
|
||||
const result = await ensureBase64ImagesForClaudeWire(
|
||||
bodyWithRemoteImage("https://example.com/big.png"),
|
||||
CLAUDE_WIRE_MODEL,
|
||||
fetchImpl
|
||||
);
|
||||
|
||||
const imagePart = (result.messages?.[0]?.content as Array<{ image_url?: { url: string } }>)[1];
|
||||
const dataUri = imagePart?.image_url?.url ?? "";
|
||||
assert.match(dataUri, /^data:image\/png;base64,/);
|
||||
|
||||
const b64 = dataUri.split(",")[1] ?? "";
|
||||
const decoded = Buffer.from(b64, "base64");
|
||||
const meta = await sharp(decoded).metadata();
|
||||
assert.ok((meta.width ?? 0) <= 2048, `expected width <= 2048, got ${meta.width}`);
|
||||
assert.notEqual(meta.width, 4096, "image must have been downscaled, not left at 4096");
|
||||
});
|
||||
|
||||
test("remote non-image bytes pass through untouched (fail-open, no normalization)", async () => {
|
||||
const junk = Buffer.from("not-an-image-at-all");
|
||||
|
||||
const fetchImpl = (async () =>
|
||||
new Response(junk, {
|
||||
status: 200,
|
||||
headers: { "content-type": "application/octet-stream" },
|
||||
})) as unknown as typeof fetch;
|
||||
|
||||
const result = await ensureBase64ImagesForClaudeWire(
|
||||
bodyWithRemoteImage("https://example.com/junk.bin"),
|
||||
CLAUDE_WIRE_MODEL,
|
||||
fetchImpl
|
||||
);
|
||||
|
||||
const imagePart = (result.messages?.[0]?.content as Array<{ image_url?: { url: string } }>)[1];
|
||||
const dataUri = imagePart?.image_url?.url ?? "";
|
||||
assert.equal(dataUri, `data:application/octet-stream;base64,${junk.toString("base64")}`);
|
||||
});
|
||||
Reference in New Issue
Block a user