diff --git a/app/api/models/embeddings/route.ts b/app/api/models/embeddings/route.ts
new file mode 100644
index 0000000..fe1cf23
--- /dev/null
+++ b/app/api/models/embeddings/route.ts
@@ -0,0 +1,17 @@
+/**
+ * GET /api/models/embeddings — the BYOK embedding-model picker's data
+ * (wave 6, owner ruling 2026-09-23): every KEYED provider's embedding
+ * catalog, federated LIVE (unlike /api/models — pi-ai's static catalog
+ * carries no embedding models). Rows are provider-qualified slugs, the
+ * exact shape graph.embeddingModel stores. Empty array when no provider
+ * is keyed (or every catalog fetch failed — per-provider failures are
+ * logged and skipped, never 500s).
+ */
+import { embeddingModelCatalog } from "@/src/server";
+
+export const dynamic = "force-dynamic";
+
+export async function GET() {
+ const models = await embeddingModelCatalog();
+ return Response.json(models);
+}
\ No newline at end of file
diff --git a/components/settings/appearance-section.tsx b/components/settings/appearance-section.tsx
index 6b12247..18bd4fd 100644
--- a/components/settings/appearance-section.tsx
+++ b/components/settings/appearance-section.tsx
@@ -139,9 +139,9 @@ export function AppearanceSection({
}
const LADDER: readonly {
- key: keyof GraphSettings;
+ key: "enabled" | "embedding" | "clustering" | "labeling";
label: string;
- needs: keyof GraphSettings | null;
+ needs: "enabled" | "embedding" | "clustering" | "labeling" | null;
}[] = [
{ key: "enabled", label: "Graph", needs: null },
{ key: "embedding", label: "Embedding", needs: "enabled" },
diff --git a/config.ts b/config.ts
index 49057b1..1dfe46b 100644
--- a/config.ts
+++ b/config.ts
@@ -26,11 +26,6 @@ export const PATHS = {
/** Chat sessions (AI SDK UIMessage transcripts, one JSON file per chat). */
chats: path.join(DATA_ROOT, "chats"),
graph: path.join(DATA_ROOT, "graph"),
- /** transformers.js model cache (server-side embeddings, ~300MB).
- * null in dev = keep the package default (the model is already
- * downloaded there); under LH_DATA_DIR the packaged app must never
- * try to cache inside its own bundle. */
- modelCache: process.env.LH_DATA_DIR ? path.join(DATA_ROOT, "models") : null,
} as const;
// ─── Models ────────────────────────────────────────────────────────────────
diff --git a/next-env.d.ts b/next-env.d.ts
index a419cbe..ce4e94a 100644
--- a/next-env.d.ts
+++ b/next-env.d.ts
@@ -1,7 +1,7 @@
///
///
-import "./.next/dev/types/routes.d.ts";
-import "./.next/dev/types/root-params.d.ts";
+import "./.next/types/routes.d.ts";
+import "./.next/types/root-params.d.ts";
// NOTE: This file should not be edited
// see https://nextjs.org/docs/app/api-reference/config/typescript for more information.
diff --git a/next.config.ts b/next.config.ts
index 373738f..d7b3b5a 100644
--- a/next.config.ts
+++ b/next.config.ts
@@ -12,7 +12,13 @@ const nextConfig: NextConfig = {
// INTO the standalone bundle. A shipped desktop app would carry the
// developer's session data inside it.
outputFileTracingExcludes: {
- "*": ["data/**/*"],
+ "*": [
+ "data/**/*",
+ // Wave 6 (2026-09-23): the local transformers embeddings died — any
+ // @huggingface copy (or its ~300MB model cache, if one ever
+ // reappears) must never sweep into the standalone bundle again.
+ "node_modules/@huggingface/**/*",
+ ],
},
// Empirically verified gaps (2026-09-17 standalone smoke): the tracer
// misses JSON loaded via `import ... with { type: "json" }` attributes —
@@ -31,21 +37,14 @@ const nextConfig: NextConfig = {
"node_modules/pdfjs-dist/standard_fonts/**/*",
"node_modules/@earendil-works/pi-ai/dist/providers/data/**/*",
"node_modules/@earendil-works/pi-agent-core/dist/**/*.json",
- // onnxruntime-node: the .node binding was traced, but its
- // sibling dylib (libonnxruntime.*.dylib, dlopen'd via @rpath)
- // was not — dlopen fails at module load.
- "node_modules/onnxruntime-node/bin/**/*",
],
},
// Framework-free core lives in src/ (plain TS, imported by routes and CLI alike).
// The pi engine must stay external: its providers are runtime-loaded Node
// code (undici streams, catalog data) that breaks when bundled into routes.
- // transformers.js (embeddings) is runtime-loaded ONNX — same reason as
- // the pi engine: bundling onnxruntime-node breaks route builds.
serverExternalPackages: [
"@earendil-works/pi-ai",
"@earendil-works/pi-agent-core",
- "@huggingface/transformers",
"pdfjs-dist", // sources v0: bundling breaks its node fake-worker path
],
};
diff --git a/package-lock.json b/package-lock.json
index 785ac63..3d56219 100644
--- a/package-lock.json
+++ b/package-lock.json
@@ -11,7 +11,6 @@
"@ai-sdk/react": "^4.0.79",
"@earendil-works/pi-agent-core": "^0.85.1",
"@earendil-works/pi-ai": "^0.85.1",
- "@huggingface/transformers": "^4.2.0",
"@mozilla/readability": "^0.6.0",
"@radix-ui/react-use-controllable-state": "^1.2.6",
"@rive-app/react-webgl2": "^4.32.1",
@@ -2231,582 +2230,6 @@
}
}
},
- "node_modules/@huggingface/jinja": {
- "version": "0.5.10",
- "resolved": "https://registry.npmjs.org/@huggingface/jinja/-/jinja-0.5.10.tgz",
- "integrity": "sha512-SgS1D1bglQ94ceD4ZCL6eayUDy9uV1xuyk61OjgSxU5GJh7upqZCKII0JoTYMc6wWsg3JUgaPRX0ElQzXPk3Cw==",
- "license": "MIT",
- "engines": {
- "node": ">=18"
- }
- },
- "node_modules/@huggingface/tokenizers": {
- "version": "0.1.3",
- "resolved": "https://registry.npmjs.org/@huggingface/tokenizers/-/tokenizers-0.1.3.tgz",
- "integrity": "sha512-8rF/RRT10u+kn7YuUbUg0OF30K8rjTc78aHpxT+qJ1uWSqxT1MHi8+9ltwYfkFYJzT/oS+qw3JVfHtNMGAdqyA==",
- "license": "Apache-2.0"
- },
- "node_modules/@huggingface/transformers": {
- "version": "4.2.0",
- "resolved": "https://registry.npmjs.org/@huggingface/transformers/-/transformers-4.2.0.tgz",
- "integrity": "sha512-8BRCoBMH0XsWaEIamuR0LrJGAfftgHAfb2Vrffy0VKlSAE/MnUJ5/h/zTfEP3fDIft+nk7TqB8xXEyABGitBjQ==",
- "license": "Apache-2.0",
- "dependencies": {
- "@huggingface/jinja": "^0.5.6",
- "@huggingface/tokenizers": "^0.1.3",
- "onnxruntime-node": "1.24.3",
- "onnxruntime-web": "1.26.0-dev.20260416-b7804b056c",
- "sharp": "^0.34.5"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-darwin-arm64": {
- "version": "0.34.5",
- "resolved": "https://registry.npmjs.org/@img/sharp-darwin-arm64/-/sharp-darwin-arm64-0.34.5.tgz",
- "integrity": "sha512-imtQ3WMJXbMY4fxb/Ndp6HBTNVtWCUI0WdobyheGf5+ad6xX8VIDO8u2xE4qc/fr08CKG/7dDseFtn6M6g/r3w==",
- "cpu": [
- "arm64"
- ],
- "license": "Apache-2.0",
- "optional": true,
- "os": [
- "darwin"
- ],
- "engines": {
- "node": "^18.17.0 || ^20.3.0 || >=21.0.0"
- },
- "funding": {
- "url": "https://opencollective.com/libvips"
- },
- "optionalDependencies": {
- "@img/sharp-libvips-darwin-arm64": "1.2.4"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-darwin-x64": {
- "version": "0.34.5",
- "resolved": "https://registry.npmjs.org/@img/sharp-darwin-x64/-/sharp-darwin-x64-0.34.5.tgz",
- "integrity": "sha512-YNEFAF/4KQ/PeW0N+r+aVVsoIY0/qxxikF2SWdp+NRkmMB7y9LBZAVqQ4yhGCm/H3H270OSykqmQMKLBhBJDEw==",
- "cpu": [
- "x64"
- ],
- "license": "Apache-2.0",
- "optional": true,
- "os": [
- "darwin"
- ],
- "engines": {
- "node": "^18.17.0 || ^20.3.0 || >=21.0.0"
- },
- "funding": {
- "url": "https://opencollective.com/libvips"
- },
- "optionalDependencies": {
- "@img/sharp-libvips-darwin-x64": "1.2.4"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-libvips-darwin-arm64": {
- "version": "1.2.4",
- "resolved": "https://registry.npmjs.org/@img/sharp-libvips-darwin-arm64/-/sharp-libvips-darwin-arm64-1.2.4.tgz",
- "integrity": "sha512-zqjjo7RatFfFoP0MkQ51jfuFZBnVE2pRiaydKJ1G/rHZvnsrHAOcQALIi9sA5co5xenQdTugCvtb1cuf78Vf4g==",
- "cpu": [
- "arm64"
- ],
- "license": "LGPL-3.0-or-later",
- "optional": true,
- "os": [
- "darwin"
- ],
- "funding": {
- "url": "https://opencollective.com/libvips"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-libvips-darwin-x64": {
- "version": "1.2.4",
- "resolved": "https://registry.npmjs.org/@img/sharp-libvips-darwin-x64/-/sharp-libvips-darwin-x64-1.2.4.tgz",
- "integrity": "sha512-1IOd5xfVhlGwX+zXv2N93k0yMONvUlANylbJw1eTah8K/Jtpi15KC+WSiaX/nBmbm2HxRM1gZ0nSdjSsrZbGKg==",
- "cpu": [
- "x64"
- ],
- "license": "LGPL-3.0-or-later",
- "optional": true,
- "os": [
- "darwin"
- ],
- "funding": {
- "url": "https://opencollective.com/libvips"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-libvips-linux-arm": {
- "version": "1.2.4",
- "resolved": "https://registry.npmjs.org/@img/sharp-libvips-linux-arm/-/sharp-libvips-linux-arm-1.2.4.tgz",
- "integrity": "sha512-bFI7xcKFELdiNCVov8e44Ia4u2byA+l3XtsAj+Q8tfCwO6BQ8iDojYdvoPMqsKDkuoOo+X6HZA0s0q11ANMQ8A==",
- "cpu": [
- "arm"
- ],
- "libc": [
- "glibc"
- ],
- "license": "LGPL-3.0-or-later",
- "optional": true,
- "os": [
- "linux"
- ],
- "funding": {
- "url": "https://opencollective.com/libvips"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-libvips-linux-arm64": {
- "version": "1.2.4",
- "resolved": "https://registry.npmjs.org/@img/sharp-libvips-linux-arm64/-/sharp-libvips-linux-arm64-1.2.4.tgz",
- "integrity": "sha512-excjX8DfsIcJ10x1Kzr4RcWe1edC9PquDRRPx3YVCvQv+U5p7Yin2s32ftzikXojb1PIFc/9Mt28/y+iRklkrw==",
- "cpu": [
- "arm64"
- ],
- "libc": [
- "glibc"
- ],
- "license": "LGPL-3.0-or-later",
- "optional": true,
- "os": [
- "linux"
- ],
- "funding": {
- "url": "https://opencollective.com/libvips"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-libvips-linux-ppc64": {
- "version": "1.2.4",
- "resolved": "https://registry.npmjs.org/@img/sharp-libvips-linux-ppc64/-/sharp-libvips-linux-ppc64-1.2.4.tgz",
- "integrity": "sha512-FMuvGijLDYG6lW+b/UvyilUWu5Ayu+3r2d1S8notiGCIyYU/76eig1UfMmkZ7vwgOrzKzlQbFSuQfgm7GYUPpA==",
- "cpu": [
- "ppc64"
- ],
- "libc": [
- "glibc"
- ],
- "license": "LGPL-3.0-or-later",
- "optional": true,
- "os": [
- "linux"
- ],
- "funding": {
- "url": "https://opencollective.com/libvips"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-libvips-linux-riscv64": {
- "version": "1.2.4",
- "resolved": "https://registry.npmjs.org/@img/sharp-libvips-linux-riscv64/-/sharp-libvips-linux-riscv64-1.2.4.tgz",
- "integrity": "sha512-oVDbcR4zUC0ce82teubSm+x6ETixtKZBh/qbREIOcI3cULzDyb18Sr/Wcyx7NRQeQzOiHTNbZFF1UwPS2scyGA==",
- "cpu": [
- "riscv64"
- ],
- "libc": [
- "glibc"
- ],
- "license": "LGPL-3.0-or-later",
- "optional": true,
- "os": [
- "linux"
- ],
- "funding": {
- "url": "https://opencollective.com/libvips"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-libvips-linux-s390x": {
- "version": "1.2.4",
- "resolved": "https://registry.npmjs.org/@img/sharp-libvips-linux-s390x/-/sharp-libvips-linux-s390x-1.2.4.tgz",
- "integrity": "sha512-qmp9VrzgPgMoGZyPvrQHqk02uyjA0/QrTO26Tqk6l4ZV0MPWIW6LTkqOIov+J1yEu7MbFQaDpwdwJKhbJvuRxQ==",
- "cpu": [
- "s390x"
- ],
- "libc": [
- "glibc"
- ],
- "license": "LGPL-3.0-or-later",
- "optional": true,
- "os": [
- "linux"
- ],
- "funding": {
- "url": "https://opencollective.com/libvips"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-libvips-linux-x64": {
- "version": "1.2.4",
- "resolved": "https://registry.npmjs.org/@img/sharp-libvips-linux-x64/-/sharp-libvips-linux-x64-1.2.4.tgz",
- "integrity": "sha512-tJxiiLsmHc9Ax1bz3oaOYBURTXGIRDODBqhveVHonrHJ9/+k89qbLl0bcJns+e4t4rvaNBxaEZsFtSfAdquPrw==",
- "cpu": [
- "x64"
- ],
- "libc": [
- "glibc"
- ],
- "license": "LGPL-3.0-or-later",
- "optional": true,
- "os": [
- "linux"
- ],
- "funding": {
- "url": "https://opencollective.com/libvips"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-libvips-linuxmusl-arm64": {
- "version": "1.2.4",
- "resolved": "https://registry.npmjs.org/@img/sharp-libvips-linuxmusl-arm64/-/sharp-libvips-linuxmusl-arm64-1.2.4.tgz",
- "integrity": "sha512-FVQHuwx1IIuNow9QAbYUzJ+En8KcVm9Lk5+uGUQJHaZmMECZmOlix9HnH7n1TRkXMS0pGxIJokIVB9SuqZGGXw==",
- "cpu": [
- "arm64"
- ],
- "libc": [
- "musl"
- ],
- "license": "LGPL-3.0-or-later",
- "optional": true,
- "os": [
- "linux"
- ],
- "funding": {
- "url": "https://opencollective.com/libvips"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-libvips-linuxmusl-x64": {
- "version": "1.2.4",
- "resolved": "https://registry.npmjs.org/@img/sharp-libvips-linuxmusl-x64/-/sharp-libvips-linuxmusl-x64-1.2.4.tgz",
- "integrity": "sha512-+LpyBk7L44ZIXwz/VYfglaX/okxezESc6UxDSoyo2Ks6Jxc4Y7sGjpgU9s4PMgqgjj1gZCylTieNamqA1MF7Dg==",
- "cpu": [
- "x64"
- ],
- "libc": [
- "musl"
- ],
- "license": "LGPL-3.0-or-later",
- "optional": true,
- "os": [
- "linux"
- ],
- "funding": {
- "url": "https://opencollective.com/libvips"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-linux-arm": {
- "version": "0.34.5",
- "resolved": "https://registry.npmjs.org/@img/sharp-linux-arm/-/sharp-linux-arm-0.34.5.tgz",
- "integrity": "sha512-9dLqsvwtg1uuXBGZKsxem9595+ujv0sJ6Vi8wcTANSFpwV/GONat5eCkzQo/1O6zRIkh0m/8+5BjrRr7jDUSZw==",
- "cpu": [
- "arm"
- ],
- "libc": [
- "glibc"
- ],
- "license": "Apache-2.0",
- "optional": true,
- "os": [
- "linux"
- ],
- "engines": {
- "node": "^18.17.0 || ^20.3.0 || >=21.0.0"
- },
- "funding": {
- "url": "https://opencollective.com/libvips"
- },
- "optionalDependencies": {
- "@img/sharp-libvips-linux-arm": "1.2.4"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-linux-arm64": {
- "version": "0.34.5",
- "resolved": "https://registry.npmjs.org/@img/sharp-linux-arm64/-/sharp-linux-arm64-0.34.5.tgz",
- "integrity": "sha512-bKQzaJRY/bkPOXyKx5EVup7qkaojECG6NLYswgktOZjaXecSAeCWiZwwiFf3/Y+O1HrauiE3FVsGxFg8c24rZg==",
- "cpu": [
- "arm64"
- ],
- "libc": [
- "glibc"
- ],
- "license": "Apache-2.0",
- "optional": true,
- "os": [
- "linux"
- ],
- "engines": {
- "node": "^18.17.0 || ^20.3.0 || >=21.0.0"
- },
- "funding": {
- "url": "https://opencollective.com/libvips"
- },
- "optionalDependencies": {
- "@img/sharp-libvips-linux-arm64": "1.2.4"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-linux-ppc64": {
- "version": "0.34.5",
- "resolved": "https://registry.npmjs.org/@img/sharp-linux-ppc64/-/sharp-linux-ppc64-0.34.5.tgz",
- "integrity": "sha512-7zznwNaqW6YtsfrGGDA6BRkISKAAE1Jo0QdpNYXNMHu2+0dTrPflTLNkpc8l7MUP5M16ZJcUvysVWWrMefZquA==",
- "cpu": [
- "ppc64"
- ],
- "libc": [
- "glibc"
- ],
- "license": "Apache-2.0",
- "optional": true,
- "os": [
- "linux"
- ],
- "engines": {
- "node": "^18.17.0 || ^20.3.0 || >=21.0.0"
- },
- "funding": {
- "url": "https://opencollective.com/libvips"
- },
- "optionalDependencies": {
- "@img/sharp-libvips-linux-ppc64": "1.2.4"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-linux-riscv64": {
- "version": "0.34.5",
- "resolved": "https://registry.npmjs.org/@img/sharp-linux-riscv64/-/sharp-linux-riscv64-0.34.5.tgz",
- "integrity": "sha512-51gJuLPTKa7piYPaVs8GmByo7/U7/7TZOq+cnXJIHZKavIRHAP77e3N2HEl3dgiqdD/w0yUfiJnII77PuDDFdw==",
- "cpu": [
- "riscv64"
- ],
- "libc": [
- "glibc"
- ],
- "license": "Apache-2.0",
- "optional": true,
- "os": [
- "linux"
- ],
- "engines": {
- "node": "^18.17.0 || ^20.3.0 || >=21.0.0"
- },
- "funding": {
- "url": "https://opencollective.com/libvips"
- },
- "optionalDependencies": {
- "@img/sharp-libvips-linux-riscv64": "1.2.4"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-linux-s390x": {
- "version": "0.34.5",
- "resolved": "https://registry.npmjs.org/@img/sharp-linux-s390x/-/sharp-linux-s390x-0.34.5.tgz",
- "integrity": "sha512-nQtCk0PdKfho3eC5MrbQoigJ2gd1CgddUMkabUj+rBevs8tZ2cULOx46E7oyX+04WGfABgIwmMC0VqieTiR4jg==",
- "cpu": [
- "s390x"
- ],
- "libc": [
- "glibc"
- ],
- "license": "Apache-2.0",
- "optional": true,
- "os": [
- "linux"
- ],
- "engines": {
- "node": "^18.17.0 || ^20.3.0 || >=21.0.0"
- },
- "funding": {
- "url": "https://opencollective.com/libvips"
- },
- "optionalDependencies": {
- "@img/sharp-libvips-linux-s390x": "1.2.4"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-linux-x64": {
- "version": "0.34.5",
- "resolved": "https://registry.npmjs.org/@img/sharp-linux-x64/-/sharp-linux-x64-0.34.5.tgz",
- "integrity": "sha512-MEzd8HPKxVxVenwAa+JRPwEC7QFjoPWuS5NZnBt6B3pu7EG2Ge0id1oLHZpPJdn3OQK+BQDiw9zStiHBTJQQQQ==",
- "cpu": [
- "x64"
- ],
- "libc": [
- "glibc"
- ],
- "license": "Apache-2.0",
- "optional": true,
- "os": [
- "linux"
- ],
- "engines": {
- "node": "^18.17.0 || ^20.3.0 || >=21.0.0"
- },
- "funding": {
- "url": "https://opencollective.com/libvips"
- },
- "optionalDependencies": {
- "@img/sharp-libvips-linux-x64": "1.2.4"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-linuxmusl-arm64": {
- "version": "0.34.5",
- "resolved": "https://registry.npmjs.org/@img/sharp-linuxmusl-arm64/-/sharp-linuxmusl-arm64-0.34.5.tgz",
- "integrity": "sha512-fprJR6GtRsMt6Kyfq44IsChVZeGN97gTD331weR1ex1c1rypDEABN6Tm2xa1wE6lYb5DdEnk03NZPqA7Id21yg==",
- "cpu": [
- "arm64"
- ],
- "libc": [
- "musl"
- ],
- "license": "Apache-2.0",
- "optional": true,
- "os": [
- "linux"
- ],
- "engines": {
- "node": "^18.17.0 || ^20.3.0 || >=21.0.0"
- },
- "funding": {
- "url": "https://opencollective.com/libvips"
- },
- "optionalDependencies": {
- "@img/sharp-libvips-linuxmusl-arm64": "1.2.4"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-linuxmusl-x64": {
- "version": "0.34.5",
- "resolved": "https://registry.npmjs.org/@img/sharp-linuxmusl-x64/-/sharp-linuxmusl-x64-0.34.5.tgz",
- "integrity": "sha512-Jg8wNT1MUzIvhBFxViqrEhWDGzqymo3sV7z7ZsaWbZNDLXRJZoRGrjulp60YYtV4wfY8VIKcWidjojlLcWrd8Q==",
- "cpu": [
- "x64"
- ],
- "libc": [
- "musl"
- ],
- "license": "Apache-2.0",
- "optional": true,
- "os": [
- "linux"
- ],
- "engines": {
- "node": "^18.17.0 || ^20.3.0 || >=21.0.0"
- },
- "funding": {
- "url": "https://opencollective.com/libvips"
- },
- "optionalDependencies": {
- "@img/sharp-libvips-linuxmusl-x64": "1.2.4"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-wasm32": {
- "version": "0.34.5",
- "resolved": "https://registry.npmjs.org/@img/sharp-wasm32/-/sharp-wasm32-0.34.5.tgz",
- "integrity": "sha512-OdWTEiVkY2PHwqkbBI8frFxQQFekHaSSkUIJkwzclWZe64O1X4UlUjqqqLaPbUpMOQk6FBu/HtlGXNblIs0huw==",
- "cpu": [
- "wasm32"
- ],
- "license": "Apache-2.0 AND LGPL-3.0-or-later AND MIT",
- "optional": true,
- "dependencies": {
- "@emnapi/runtime": "^1.7.0"
- },
- "engines": {
- "node": "^18.17.0 || ^20.3.0 || >=21.0.0"
- },
- "funding": {
- "url": "https://opencollective.com/libvips"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-win32-arm64": {
- "version": "0.34.5",
- "resolved": "https://registry.npmjs.org/@img/sharp-win32-arm64/-/sharp-win32-arm64-0.34.5.tgz",
- "integrity": "sha512-WQ3AgWCWYSb2yt+IG8mnC6Jdk9Whs7O0gxphblsLvdhSpSTtmu69ZG1Gkb6NuvxsNACwiPV6cNSZNzt0KPsw7g==",
- "cpu": [
- "arm64"
- ],
- "license": "Apache-2.0 AND LGPL-3.0-or-later",
- "optional": true,
- "os": [
- "win32"
- ],
- "engines": {
- "node": "^18.17.0 || ^20.3.0 || >=21.0.0"
- },
- "funding": {
- "url": "https://opencollective.com/libvips"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-win32-ia32": {
- "version": "0.34.5",
- "resolved": "https://registry.npmjs.org/@img/sharp-win32-ia32/-/sharp-win32-ia32-0.34.5.tgz",
- "integrity": "sha512-FV9m/7NmeCmSHDD5j4+4pNI8Cp3aW+JvLoXcTUo0IqyjSfAZJ8dIUmijx1qaJsIiU+Hosw6xM5KijAWRJCSgNg==",
- "cpu": [
- "ia32"
- ],
- "license": "Apache-2.0 AND LGPL-3.0-or-later",
- "optional": true,
- "os": [
- "win32"
- ],
- "engines": {
- "node": "^18.17.0 || ^20.3.0 || >=21.0.0"
- },
- "funding": {
- "url": "https://opencollective.com/libvips"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/@img/sharp-win32-x64": {
- "version": "0.34.5",
- "resolved": "https://registry.npmjs.org/@img/sharp-win32-x64/-/sharp-win32-x64-0.34.5.tgz",
- "integrity": "sha512-+29YMsqY2/9eFEiW93eqWnuLcWcufowXewwSNIT6UwZdUUCrM3oFjMWH/Z6/TMmb4hlFenmfAVbpWeup2jryCw==",
- "cpu": [
- "x64"
- ],
- "license": "Apache-2.0 AND LGPL-3.0-or-later",
- "optional": true,
- "os": [
- "win32"
- ],
- "engines": {
- "node": "^18.17.0 || ^20.3.0 || >=21.0.0"
- },
- "funding": {
- "url": "https://opencollective.com/libvips"
- }
- },
- "node_modules/@huggingface/transformers/node_modules/sharp": {
- "version": "0.34.5",
- "resolved": "https://registry.npmjs.org/sharp/-/sharp-0.34.5.tgz",
- "integrity": "sha512-Ou9I5Ft9WNcCbXrU9cMgPBcCK8LiwLqcbywW3t4oDV37n1pzpuNLsYiAV8eODnjbtQlSDwZ2cUEeQz4E54Hltg==",
- "hasInstallScript": true,
- "license": "Apache-2.0",
- "dependencies": {
- "@img/colour": "^1.0.0",
- "detect-libc": "^2.1.2",
- "semver": "^7.7.3"
- },
- "engines": {
- "node": "^18.17.0 || ^20.3.0 || >=21.0.0"
- },
- "funding": {
- "url": "https://opencollective.com/libvips"
- },
- "optionalDependencies": {
- "@img/sharp-darwin-arm64": "0.34.5",
- "@img/sharp-darwin-x64": "0.34.5",
- "@img/sharp-libvips-darwin-arm64": "1.2.4",
- "@img/sharp-libvips-darwin-x64": "1.2.4",
- "@img/sharp-libvips-linux-arm": "1.2.4",
- "@img/sharp-libvips-linux-arm64": "1.2.4",
- "@img/sharp-libvips-linux-ppc64": "1.2.4",
- "@img/sharp-libvips-linux-riscv64": "1.2.4",
- "@img/sharp-libvips-linux-s390x": "1.2.4",
- "@img/sharp-libvips-linux-x64": "1.2.4",
- "@img/sharp-libvips-linuxmusl-arm64": "1.2.4",
- "@img/sharp-libvips-linuxmusl-x64": "1.2.4",
- "@img/sharp-linux-arm": "0.34.5",
- "@img/sharp-linux-arm64": "0.34.5",
- "@img/sharp-linux-ppc64": "0.34.5",
- "@img/sharp-linux-riscv64": "0.34.5",
- "@img/sharp-linux-s390x": "0.34.5",
- "@img/sharp-linux-x64": "0.34.5",
- "@img/sharp-linuxmusl-arm64": "0.34.5",
- "@img/sharp-linuxmusl-x64": "0.34.5",
- "@img/sharp-wasm32": "0.34.5",
- "@img/sharp-win32-arm64": "0.34.5",
- "@img/sharp-win32-ia32": "0.34.5",
- "@img/sharp-win32-x64": "0.34.5"
- }
- },
"node_modules/@humanfs/core": {
"version": "0.19.2",
"resolved": "https://registry.npmjs.org/@humanfs/core/-/core-0.19.2.tgz",
@@ -2895,6 +2318,7 @@
"resolved": "https://registry.npmjs.org/@img/colour/-/colour-1.1.0.tgz",
"integrity": "sha512-Td76q7j57o/tLVdgS746cYARfSyxk8iEfRxewL9h4OMzYhbW4TAcppl0mT4eyqXddh6L/jwoM75mo7ixa/pCeQ==",
"license": "MIT",
+ "optional": true,
"engines": {
"node": ">=18"
}
@@ -7355,15 +6779,6 @@
"acorn": "^6.0.0 || ^7.0.0 || ^8.0.0"
}
},
- "node_modules/adm-zip": {
- "version": "0.5.18",
- "resolved": "https://registry.npmjs.org/adm-zip/-/adm-zip-0.5.18.tgz",
- "integrity": "sha512-ufJnssQGbxzLNS1Ho9bCtX4rQKCCvoVuDLHoJyc3F9dOGDB4BkWs2Ci0kv53lqocAEQ/Cbi+I2XCsNYGqVYqng==",
- "license": "MIT",
- "engines": {
- "node": ">=12.0"
- }
- },
"node_modules/agent-base": {
"version": "7.1.4",
"resolved": "https://registry.npmjs.org/agent-base/-/agent-base-7.1.4.tgz",
@@ -7987,7 +7402,9 @@
"resolved": "https://registry.npmjs.org/boolean/-/boolean-3.2.0.tgz",
"integrity": "sha512-d0II/GO9uf9lfUHH2BQsjxzRJZBdsjgsBiW4BvhWk/3qoKwQFjIDVN19PfX8F2D/r9PCMTtLWjYVCFrpeYUzsw==",
"deprecated": "Package no longer supported. Contact Support at https://www.npmjs.com/support for more info.",
- "license": "MIT"
+ "dev": true,
+ "license": "MIT",
+ "optional": true
},
"node_modules/bowser": {
"version": "2.14.1",
@@ -9335,6 +8752,7 @@
"version": "1.1.4",
"resolved": "https://registry.npmjs.org/define-data-property/-/define-data-property-1.1.4.tgz",
"integrity": "sha512-rBMvIzlpA8v6E+SJZoo++HAYqsLrkg7MSfIinMPFhmkorw7X+dOXVJQs+QT69zGkzMyfDnIMN2Wid1+NbL3T+A==",
+ "dev": true,
"license": "MIT",
"dependencies": {
"es-define-property": "^1.0.0",
@@ -9352,6 +8770,7 @@
"version": "1.2.1",
"resolved": "https://registry.npmjs.org/define-properties/-/define-properties-1.2.1.tgz",
"integrity": "sha512-8QmQKqEASLd5nx0U1B1okLElbUuuttJ/AnYmRXbbbGDWh6uS208EjD4Xqq/I9wK7u0v6O08XhTWnt5XtEbR6Dg==",
+ "dev": true,
"license": "MIT",
"dependencies": {
"define-data-property": "^1.0.1",
@@ -9397,6 +8816,7 @@
"version": "2.1.2",
"resolved": "https://registry.npmjs.org/detect-libc/-/detect-libc-2.1.2.tgz",
"integrity": "sha512-Btj2BOOO83o3WyH59e8MgXsxEQVcarkUOpEYrubB0urwnN10yQ364rsiByU11nZlqWYZm05i/of7io4mzihBtQ==",
+ "devOptional": true,
"license": "Apache-2.0",
"engines": {
"node": ">=8"
@@ -9406,7 +8826,9 @@
"version": "2.1.0",
"resolved": "https://registry.npmjs.org/detect-node/-/detect-node-2.1.0.tgz",
"integrity": "sha512-T0NIuQpnTvFDATNuHN5roPwSBG83rFsuO+MXXH9/3N1eFbn4wcPjttvjMLEPWJ0RGUYgQE7cGgS3tNxbqCGM7g==",
- "license": "MIT"
+ "dev": true,
+ "license": "MIT",
+ "optional": true
},
"node_modules/detect-node-es": {
"version": "1.1.0",
@@ -10118,6 +9540,7 @@
"version": "1.0.1",
"resolved": "https://registry.npmjs.org/es-define-property/-/es-define-property-1.0.1.tgz",
"integrity": "sha512-e3nRfgfUZ4rNGL232gUgX06QNyyez04KdjFrF+LTRoOXmrOgFKDg4BCdsjW8EnT69eqdYGmRpJwiPVYNrCaW3g==",
+ "dev": true,
"license": "MIT",
"engines": {
"node": ">= 0.4"
@@ -10127,6 +9550,7 @@
"version": "1.3.0",
"resolved": "https://registry.npmjs.org/es-errors/-/es-errors-1.3.0.tgz",
"integrity": "sha512-Zf5H2Kxt2xjTvbJvP2ZWLEICxA6j+hAmMzIlypy4xcBg1vKVnx89Wy0GbS+kf5cwCVFFzdCFh2XSCFNULS6csw==",
+ "dev": true,
"license": "MIT",
"engines": {
"node": ">= 0.4"
@@ -10211,7 +9635,9 @@
"version": "4.1.1",
"resolved": "https://registry.npmjs.org/es6-error/-/es6-error-4.1.1.tgz",
"integrity": "sha512-Um/+FxMr9CISWh0bi5Zv0iOD+4cFh5qLeks1qhAopKVAJw3drgKbKySikp7wGhDL0HPeaja0P5ULZrxLkniUVg==",
- "license": "MIT"
+ "dev": true,
+ "license": "MIT",
+ "optional": true
},
"node_modules/esbuild": {
"version": "0.28.2",
@@ -10947,12 +10373,6 @@
"node": ">=16"
}
},
- "node_modules/flatbuffers": {
- "version": "25.9.23",
- "resolved": "https://registry.npmjs.org/flatbuffers/-/flatbuffers-25.9.23.tgz",
- "integrity": "sha512-MI1qs7Lo4Syw0EOzUl0xjs2lsoeqFku44KpngfIduHBYvzm8h2+7K8YMQh1JtVVVrUvhLpNwqVi4DERegUJhPQ==",
- "license": "Apache-2.0"
- },
"node_modules/flatted": {
"version": "3.4.4",
"resolved": "https://registry.npmjs.org/flatted/-/flatted-3.4.4.tgz",
@@ -11333,7 +10753,9 @@
"version": "3.0.0",
"resolved": "https://registry.npmjs.org/global-agent/-/global-agent-3.0.0.tgz",
"integrity": "sha512-PT6XReJ+D07JvGoxQMkT6qji/jVNfX/h364XHZOWeRzy64sSFr+xJ5OX7LI3b4MPQzdL4H8Y8M0xzPpsVMwA8Q==",
+ "dev": true,
"license": "BSD-3-Clause",
+ "optional": true,
"dependencies": {
"boolean": "^3.0.1",
"es6-error": "^4.1.1",
@@ -11363,6 +10785,7 @@
"version": "1.0.4",
"resolved": "https://registry.npmjs.org/globalthis/-/globalthis-1.0.4.tgz",
"integrity": "sha512-DpLKbNU4WylpxJykQujfCcwYWiV/Jhm50Goo0wrVILAv5jOr9d+H+UR3PhSCD2rCCEIg0uc+G+muBTwD54JhDQ==",
+ "dev": true,
"license": "MIT",
"dependencies": {
"define-properties": "^1.2.1",
@@ -11405,6 +10828,7 @@
"version": "1.2.0",
"resolved": "https://registry.npmjs.org/gopd/-/gopd-1.2.0.tgz",
"integrity": "sha512-ZUKRh6/kUFoAiTAtTYPZJ3hw9wNxx+BIBOijnlG9PnrJsCcSjs1wyyD6vJpaYtgnzDrKYRSqf3OO6Rfa93xsRg==",
+ "dev": true,
"license": "MIT",
"engines": {
"node": ">= 0.4"
@@ -11446,12 +10870,6 @@
"dev": true,
"license": "ISC"
},
- "node_modules/guid-typescript": {
- "version": "1.0.9",
- "resolved": "https://registry.npmjs.org/guid-typescript/-/guid-typescript-1.0.9.tgz",
- "integrity": "sha512-Y8T4vYhEfwJOTbouREvG+3XDsjr8E3kIr7uf+JZ0BYloFsttiHU0WfvANVsR7TxNUJa/WpCnw/Ino/p+DeBhBQ==",
- "license": "ISC"
- },
"node_modules/hachure-fill": {
"version": "0.5.2",
"resolved": "https://registry.npmjs.org/hachure-fill/-/hachure-fill-0.5.2.tgz",
@@ -11485,6 +10903,7 @@
"version": "1.0.2",
"resolved": "https://registry.npmjs.org/has-property-descriptors/-/has-property-descriptors-1.0.2.tgz",
"integrity": "sha512-55JNKuIW+vq4Ke1BjOTjM2YctQIvCT7GFzHwmfZPGo5wnrgkid0YQtnAleFSqumZm4az3n2BS+erby5ipJdgrg==",
+ "dev": true,
"license": "MIT",
"dependencies": {
"es-define-property": "^1.0.0"
@@ -12708,7 +12127,9 @@
"version": "5.0.1",
"resolved": "https://registry.npmjs.org/json-stringify-safe/-/json-stringify-safe-5.0.1.tgz",
"integrity": "sha512-ZClg6AaYvamvYEE82d3Iyd3vSSIjQ+odgjaTzRuO3s7toCdFKczob2i0zCh7JE8kWn17yvAWhUVxvqGwUalsRA==",
- "license": "ISC"
+ "dev": true,
+ "license": "ISC",
+ "optional": true
},
"node_modules/json5": {
"version": "1.0.2",
@@ -13229,7 +12650,9 @@
"version": "3.0.0",
"resolved": "https://registry.npmjs.org/matcher/-/matcher-3.0.0.tgz",
"integrity": "sha512-OkeDaAZ/bQCxeFAozM55PKcKU0yJMPGifLwV4Qgjitu+5MoAfSQN4lsLJeXZ1b8w0x+/Emda6MZgXS1jvsapng==",
+ "dev": true,
"license": "MIT",
+ "optional": true,
"dependencies": {
"escape-string-regexp": "^4.0.0"
},
@@ -13241,7 +12664,9 @@
"version": "4.0.0",
"resolved": "https://registry.npmjs.org/escape-string-regexp/-/escape-string-regexp-4.0.0.tgz",
"integrity": "sha512-TtpcNJ3XAzx3Gq8sWRzJaVajRs0uVxA2YAkdb1jm2YkPz4G6egUFAyA3n5vtEIZefPk5Wa4UXbKuS5fKkJWdgA==",
+ "dev": true,
"license": "MIT",
+ "optional": true,
"engines": {
"node": ">=10"
},
@@ -14870,6 +14295,7 @@
"version": "1.1.1",
"resolved": "https://registry.npmjs.org/object-keys/-/object-keys-1.1.1.tgz",
"integrity": "sha512-NuAESUOUMrlIXOfHKzD6bpPu3tYt3xvjNdRIQ+FeT0lNb4K8WR70CaDxhuNguS2XG+GjkyMwOzsN5ZktImfhLA==",
+ "dev": true,
"license": "MIT",
"engines": {
"node": ">= 0.4"
@@ -14992,49 +14418,6 @@
"regex-recursion": "^6.0.2"
}
},
- "node_modules/onnxruntime-common": {
- "version": "1.24.3",
- "resolved": "https://registry.npmjs.org/onnxruntime-common/-/onnxruntime-common-1.24.3.tgz",
- "integrity": "sha512-GeuPZO6U/LBJXvwdaqHbuUmoXiEdeCjWi/EG7Y1HNnDwJYuk6WUbNXpF6luSUY8yASul3cmUlLGrCCL1ZgVXqA==",
- "license": "MIT"
- },
- "node_modules/onnxruntime-node": {
- "version": "1.24.3",
- "resolved": "https://registry.npmjs.org/onnxruntime-node/-/onnxruntime-node-1.24.3.tgz",
- "integrity": "sha512-JH7+czbc8ALA819vlTgcV+Q214/+VjGeBHDjX81+ZCD0PCVCIFGFNtT0V4sXG/1JXypKPgScQcB3ij/hk3YnTg==",
- "hasInstallScript": true,
- "license": "MIT",
- "os": [
- "win32",
- "darwin",
- "linux"
- ],
- "dependencies": {
- "adm-zip": "^0.5.16",
- "global-agent": "^3.0.0",
- "onnxruntime-common": "1.24.3"
- }
- },
- "node_modules/onnxruntime-web": {
- "version": "1.26.0-dev.20260416-b7804b056c",
- "resolved": "https://registry.npmjs.org/onnxruntime-web/-/onnxruntime-web-1.26.0-dev.20260416-b7804b056c.tgz",
- "integrity": "sha512-MD6Ss4GSpQBo6zqoJzyT9LRbKYs7x/JVN23FT24EcEvlqF4VuzPOeH6X38orZPKHQDbprn7K+SBpu0/mj2CQiw==",
- "license": "MIT",
- "dependencies": {
- "flatbuffers": "^25.1.24",
- "guid-typescript": "^1.0.9",
- "long": "^5.2.3",
- "onnxruntime-common": "1.24.0-dev.20251116-b39e144322",
- "platform": "^1.3.6",
- "protobufjs": "^7.2.4"
- }
- },
- "node_modules/onnxruntime-web/node_modules/onnxruntime-common": {
- "version": "1.24.0-dev.20251116-b39e144322",
- "resolved": "https://registry.npmjs.org/onnxruntime-common/-/onnxruntime-common-1.24.0-dev.20251116-b39e144322.tgz",
- "integrity": "sha512-BOoomdHYmNRL5r4iQ4bMvsl2t0/hzVQ3OM3PHD0gxeXu1PmggqBv3puZicEUVOA3AtHHYmqZtjMj9FOfGrATTw==",
- "license": "MIT"
- },
"node_modules/openai": {
"version": "6.40.0",
"resolved": "https://registry.npmjs.org/openai/-/openai-6.40.0.tgz",
@@ -15336,12 +14719,6 @@
"url": "https://paulmillr.com/funding/"
}
},
- "node_modules/platform": {
- "version": "1.3.6",
- "resolved": "https://registry.npmjs.org/platform/-/platform-1.3.6.tgz",
- "integrity": "sha512-fnWVljUchTro6RiCFvCXBbNhJc2NijN7oIQxbwsyL0buWJPG85v81ehlHI9fXrJsMNgTofEoWIQeClKpgxFLrg==",
- "license": "MIT"
- },
"node_modules/plist": {
"version": "3.1.0",
"resolved": "https://registry.npmjs.org/plist/-/plist-3.1.0.tgz",
@@ -16334,7 +15711,9 @@
"version": "2.15.4",
"resolved": "https://registry.npmjs.org/roarr/-/roarr-2.15.4.tgz",
"integrity": "sha512-CHhPh+UNHD2GTXNYhPWLnU8ONHdI+5DI+4EYIAOaiD63rHeYlZvyh8P+in5999TTSFgUYuKUAjzRI4mdh/p+2A==",
+ "dev": true,
"license": "BSD-3-Clause",
+ "optional": true,
"dependencies": {
"boolean": "^3.0.1",
"detect-node": "^2.0.4",
@@ -16516,6 +15895,7 @@
"version": "7.8.5",
"resolved": "https://registry.npmjs.org/semver/-/semver-7.8.5.tgz",
"integrity": "sha512-Y7/KDsb8LjooZpwaqGyulO6DQlksgCncchHGk+sZIY4SBvUocMBEFH5Ur1fI4dV+Jvl0w6cjvucaIi40puRioA==",
+ "devOptional": true,
"license": "ISC",
"bin": {
"semver": "bin/semver.js"
@@ -16528,13 +15908,17 @@
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/semver-compare/-/semver-compare-1.0.0.tgz",
"integrity": "sha512-YM3/ITh2MJ5MtzaM429anh+x2jiLVjqILF4m4oyQB18W7Ggea7BfqdH/wGMK7dDiMghv/6WG7znWMwUDzJiXow==",
- "license": "MIT"
+ "dev": true,
+ "license": "MIT",
+ "optional": true
},
"node_modules/serialize-error": {
"version": "7.0.1",
"resolved": "https://registry.npmjs.org/serialize-error/-/serialize-error-7.0.1.tgz",
"integrity": "sha512-8I8TjW5KMOKsZQTvoxjuSIa7foAwPWGOts+6o7sgjz41/qMD9VQHEDxi6PBvK2l0MXUmqZyNpUK+T2tQaaElvw==",
+ "dev": true,
"license": "MIT",
+ "optional": true,
"dependencies": {
"type-fest": "^0.13.1"
},
@@ -16820,7 +16204,9 @@
"version": "1.1.3",
"resolved": "https://registry.npmjs.org/sprintf-js/-/sprintf-js-1.1.3.tgz",
"integrity": "sha512-Oo+0REFV59/rz3gfJNKQiBlwfHaSESl1pcGyABQsnnIfWOFt6JNj5gCog2U6MLZ//IGYD+nA8nI+mTShREReaA==",
- "license": "BSD-3-Clause"
+ "dev": true,
+ "license": "BSD-3-Clause",
+ "optional": true
},
"node_modules/stable-hash-x": {
"version": "0.2.0",
@@ -17510,7 +16896,9 @@
"version": "0.13.1",
"resolved": "https://registry.npmjs.org/type-fest/-/type-fest-0.13.1.tgz",
"integrity": "sha512-34R7HTnG0XIJcBSn5XhDd7nNFPRcXYRZrBB2O2jdKqYODldSzBAqzsWoZYYvduky73toYS/ESqxPvkDf/F0XMg==",
+ "dev": true,
"license": "(MIT OR CC0-1.0)",
+ "optional": true,
"engines": {
"node": ">=10"
},
diff --git a/package.json b/package.json
index 20406e6..3dad78d 100644
--- a/package.json
+++ b/package.json
@@ -20,7 +20,6 @@
"@ai-sdk/react": "^4.0.79",
"@earendil-works/pi-agent-core": "^0.85.1",
"@earendil-works/pi-ai": "^0.85.1",
- "@huggingface/transformers": "^4.2.0",
"@mozilla/readability": "^0.6.0",
"@radix-ui/react-use-controllable-state": "^1.2.6",
"@rive-app/react-webgl2": "^4.32.1",
diff --git a/scripts/embed-graph.ts b/scripts/embed-graph.ts
index 04514a0..60f7a9e 100644
--- a/scripts/embed-graph.ts
+++ b/scripts/embed-graph.ts
@@ -1,20 +1,35 @@
/**
- * Embed the whole graph (backfill / cold start): one-time pass that
- * fills the embedding ledger for every node — the same embedNewNodes the
- * post-merge hook runs, just with an empty (or stale-model) ledger so
- * every node is "new". First run downloads the model weights (~300MB)
- * to the local HF cache; subsequent runs embed only what's missing.
+ * Embed the whole graph (backfill / cold start / model change): one-time
+ * pass that fills the embedding ledger for every node — the same
+ * embedNewNodes the post-merge hook runs, just with an empty (or
+ * stale-model) ledger so every node is "new".
+ *
+ * BYOK (wave 6, 2026-09-23): vectors come from the configured provider
+ * (graph.embeddingModel, keys from the auth store) — this script resolves
+ * the live state up front so an unconfigured machine says so before
+ * anything bills. A model CHANGE re-embeds everything (ledger staleness).
*
* npx tsx scripts/embed-graph.ts
*/
+import { embedNewNodes, embeddingPort } from "../src/server/embeddings.ts";
import { graphStore } from "../src/store/graph.ts";
-import { embedNewNodes, EMBEDDING_MODEL, EMBEDDING_DIM } from "../src/server/embeddings.ts";
async function main() {
+ const resolved = embeddingPort();
+ if (!resolved.ok) {
+ console.error(`[embed] cannot run — ${resolved.reason}`);
+ process.exit(1);
+ }
const t0 = Date.now();
- console.log(`[embed] model: ${EMBEDDING_MODEL} (dim ${EMBEDDING_DIM}, q8)`);
- const { embedded, total } = await embedNewNodes(graphStore);
- console.log(`[embed] embedded ${embedded} nodes → ledger holds ${total} vectors (${((Date.now() - t0) / 1000).toFixed(1)}s)`);
+ console.log(`[embed] model: ${resolved.port.model} (provider embeddings, batch 32)`);
+ const { embedded, total, usage } = await embedNewNodes(graphStore);
+ console.log(
+ `[embed] embedded ${embedded} nodes → ledger holds ${total} vectors (${((Date.now() - t0) / 1000).toFixed(1)}s)`,
+ );
+ if (usage) {
+ const tokens = usage.steps.reduce((sum, s) => sum + (s.inputTokens ?? 0), 0);
+ console.log(`[embed] embedding spend: ${tokens} prompt tokens over ${usage.steps.length} call(s)`);
+ }
}
main().catch((err) => {
diff --git a/src/agent/subagents/extraction.ts b/src/agent/subagents/extraction.ts
index 9beea12..84bef25 100644
--- a/src/agent/subagents/extraction.ts
+++ b/src/agent/subagents/extraction.ts
@@ -505,8 +505,14 @@ export interface RunningExtraction {
phase: ExtractionPhase;
startedAt: number;
/** Live per-stage usage, accumulated as steps bill (the dock's cost /
- * context-window blobs read this through /api/graph/status). */
- usage: { extractor?: ExtractionStageUsage; auditor?: ExtractionStageUsage };
+ * context-window blobs read this through /api/graph/status). Wave 6:
+ * the provider-embedding tail became a billable stage — recorded from
+ * the embedder's reported usage when present. */
+ usage: {
+ extractor?: ExtractionStageUsage;
+ auditor?: ExtractionStageUsage;
+ embedding?: ExtractionStageUsage;
+ };
/** True-cancellation handle (the dock's abort button): one controller per
* run, shared across phases; abort() cancels the in-flight model call. */
controller: AbortController;
@@ -574,9 +580,12 @@ export interface ExtractionModels {
export interface ExtractionPipelineDeps extends GraphDeps, ExtractionModels {
/** The post-merge embedding batch (semantic clusters run on it).
* INJECTED by the composition root (the agent layer never imports
- * the server layer — architecture law): production passes the real
- * local-model embedder (server/embeddings.ts embedNewNodes), tests
- * fake it. Failure inside it is non-fatal by contract. */
+ * the server layer — architecture law): production passes the
+ * provider-embedder batch (server/embeddings.ts embedNewNodes — BYOK
+ * wave 6; null model = it skips itself with an info log), tests fake
+ * it. Failure inside it is non-fatal by contract. When the result
+ * carries a `usage` stage (the EmbedBatchResult contract), it is
+ * recorded into the run's money-channel capture. */
embedder: (graphStore: GraphStore) => Promise;
}
@@ -664,6 +673,27 @@ export function createExtractionPipeline(deps: ExtractionPipelineDeps): Extracti
run.usage[stage]!.steps.push(usage);
}
+ /** The embedding tail's failure log (non-fatal by contract). */
+ function recordEmbedFailure(chatId: string): (err: unknown) => undefined {
+ return (err) => {
+ console.error(`[extraction ${chatId}] embedding failed (non-fatal):`, err);
+ return undefined;
+ };
+ }
+
+ /** Wave 6: fold the provider-embedding tail's reported usage into the
+ * run's capture — one ExtractionStageUsage per run (the embedder
+ * already aggregated its API calls into steps). Absent/skipped/failed
+ * embeds contribute nothing (a run that embedded nothing stays
+ * two-stage, like the whole local-embedder era). */
+ function captureEmbedUsage(chatId: string, result: unknown): void {
+ const stage = (result as { usage?: ExtractionStageUsage } | undefined)?.usage;
+ if (!stage) return;
+ const run = runningExtractions.get(chatId);
+ if (!run) return;
+ run.usage.embedding = stage;
+ }
+
async function extract(chatId: string, view: string): Promise {
const signal = runningExtractions.get(chatId)?.controller.signal;
@@ -739,6 +769,7 @@ export function createExtractionPipeline(deps: ExtractionPipelineDeps): Extracti
stages: {
extractor: run.usage.extractor ?? { model: "unknown", steps: [] },
auditor: run.usage.auditor ?? { model: "unknown", steps: [] },
+ ...(run.usage.embedding ? { embedding: run.usage.embedding } : {}),
},
};
if (run.kind === "notes") graphStore.appendSourceUsage(chatId, entry);
@@ -830,9 +861,7 @@ export function createExtractionPipeline(deps: ExtractionPipelineDeps): Extracti
// MEANING, so embed the new propositions BEFORE the settle and
// the namer look at clusters. Failure is non-fatal — clustering
// runs without the new nodes until the next merge retries.
- await embed(graphStore).catch((err) => {
- console.error(`[extraction ${chatId}] embedding failed (non-fatal):`, err);
- });
+ await captureEmbedUsage(chatId, await embed(graphStore).catch(recordEmbedFailure(chatId)));
// Option A: the layout ledger evolves with the merge (sync — the
// next snapshot fetch must already reflect the new nodes).
settleGraphLayout(graphStore);
@@ -963,9 +992,7 @@ export function createExtractionPipeline(deps: ExtractionPipelineDeps): Extracti
// (topics from meaning), then the settle, then the namer —
// under their own phase, exactly like the chat path.
setPhase(id, "embedding", "notes", input.filePath);
- await embed(graphStore).catch((err) => {
- console.error(`[extraction ${id}] embedding failed (non-fatal):`, err);
- });
+ await captureEmbedUsage(id, await embed(graphStore).catch(recordEmbedFailure(id)));
// Option A: same post-merge settle as the chat path.
settleGraphLayout(graphStore);
persistRunUsage(id, Math.round(performance.now() - t0), stats);
diff --git a/src/agent/subagents/graph-context.ts b/src/agent/subagents/graph-context.ts
index 034d41c..d3cef03 100644
--- a/src/agent/subagents/graph-context.ts
+++ b/src/agent/subagents/graph-context.ts
@@ -12,9 +12,10 @@
* quiz/ask calls, so delivery lands mid-probing, before plan_init — where
* prior knowledge matters most.
*
- * No model call, no usage: the job's only cost is one embedding pass over
- * the warm singleton (tens–~200ms) plus a brute-force cosine scan. It still
- * carries a JobRecord (kind "graph-context") so the dock shows it, and it
+ * No teacher-model call: the job's only model spend is ONE embedding
+ * query (the local embedder was free, provider ones are not — wave 6
+ * records its prompt tokens on the job record). It still carries a
+ * JobRecord (kind "graph-context") so the dock shows it, and it
* registers its AbortController so the dock's END kills it — but an abort
* steers NOTHING: nothing was ever promised in the lesson (the injection is
* server-initiated scaffolding, unlike a teacher-dispatched sub-agent).
@@ -27,6 +28,7 @@
*/
import {
+ accumulateJobUsage,
buildGraphContextSteer,
steerDelivered,
type JobRecord,
@@ -41,20 +43,25 @@ import type { UIMessage } from "ai";
import { registerJobAbort, unregisterJobAbort } from "./aborts.ts";
import type { ChatStore, GraphStore, JobStore } from "../../core/ports.ts";
-/** The embedder as the runner needs it: the model/dim the ledger must
- * match (parity: one vector space) + the query seam. Injected so tests
- * run without the transformer model. */
+/** The embedder as the runner needs it (BYOK wave 6): the model slug the
+ * ledger must match (parity: one vector space) + the query seam.
+ * Resolved FRESH per run by the composition root (deps.embedder) so a
+ * settings PUT or a key save between dispatch and spawn lands; null
+ * model = no embedding configured — the run skips honestly. The query
+ * carries its prompt-token count so the job records its spend (the
+ * local embedder was free; provider ones are not). */
export interface GraphContextEmbedder {
- model: string;
- dim: number;
- embedQuery: (text: string) => Promise;
+ model: string | null;
+ embedQuery: (text: string) => Promise<{ vector: number[]; promptTokens?: number }>;
}
export interface GraphContextDeps {
chatStore: Pick;
jobStore: Pick;
graphStore: Pick;
- embedder: GraphContextEmbedder;
+ /** The embedder RESOLVER (wave 6): called once at run start — fresh
+ * setting + key reads each run. null = no embedding model configured. */
+ embedder: () => GraphContextEmbedder | null;
/** The wake seam — jobs.ts deliverJobResult (resolves on delivery). */
deliver: (steer: SteerMessage) => Promise;
}
@@ -126,7 +133,7 @@ export function startGraphContextInjection(deps: GraphContextDeps, chatId: strin
* crash-recovery respawn seam: a job record orphaned "running" by a
* process crash re-runs from here (the record is the only input needed). */
export async function runGraphContextJob(deps: GraphContextDeps, jobId: string): Promise {
- const { chatStore, jobStore, graphStore, embedder, deliver } = deps;
+ const { chatStore, jobStore, graphStore, deliver } = deps;
const job = jobStore.getJob(jobId);
if (!job || job.status !== "running") return;
@@ -135,6 +142,13 @@ export async function runGraphContextJob(deps: GraphContextDeps, jobId: string):
};
const chat = chatStore.getChat(job.chatId);
if (!chat) return fail(`chat not found: ${job.chatId}`);
+ // BYOK (wave 6): fresh resolution per run; null = honestly off (the
+ // dispatch gate already skips unconfigured sessions — this only fires
+ // on a config change racing a respawn, and the error says exactly why).
+ const embedder = deps.embedder();
+ if (!embedder || embedder.model === null) {
+ return fail("no embedding model configured — injection skipped (graph.embeddingModel is null)");
+ }
const topic = topicOf(chat.messages);
if (topic === null) return fail("no injectable topic (session past its start)");
const budget = effectiveContextBudget(chat.settings);
@@ -146,19 +160,39 @@ export async function runGraphContextJob(deps: GraphContextDeps, jobId: string):
try {
jobStore.updateJob(jobId, { activity: "embedding topic" });
const ledger = graphStore.readEmbeddings();
- if (ledger.model !== embedder.model || ledger.dim !== embedder.dim) {
- return fail("embeddings ledger is stale (model/dim mismatch) — injection skipped");
+ // Staleness is the MODEL identity (wave 6): a given model serves one
+ // dim by default, so model parity is space parity; the dim is checked
+ // defensively against the served vector below.
+ if (ledger.model !== embedder.model) {
+ return fail("embeddings ledger is stale (model mismatch) — injection skipped");
}
if (Object.keys(ledger.vectors).length === 0) {
return fail("the knowledge graph has no embeddings yet — nothing to inject");
}
const query = await embedder.embedQuery(topic);
if (controller.signal.aborted) return;
+ // The defensive dim half of the old parity check: a provider-side dim
+ // change (rare) must fail the query, never silently mismatch.
+ if (query.vector.length !== ledger.dim) {
+ return fail(
+ `embedding dim mismatch: query is ${query.vector.length}, ledger holds ${ledger.dim}`,
+ );
+ }
+ // Money channel (wave 6): the one embedding call's prompt tokens fold
+ // into the job record — priced via the EMBEDDING_PRICES overlay.
+ if (query.promptTokens !== undefined) {
+ jobStore.updateJob(jobId, {
+ usage: accumulateJobUsage(job.usage, embedder.model, {
+ inputTokens: query.promptTokens,
+ outputTokens: 0,
+ }),
+ });
+ }
jobStore.updateJob(jobId, { activity: "selecting propositions" });
const data = selectGraphContext({
chatId: job.chatId,
- query,
+ query: query.vector,
vectors: ledger.vectors,
nodes: graphStore.readNodes(),
events: graphStore.readEvents(),
diff --git a/src/agent/subagents/headless.ts b/src/agent/subagents/headless.ts
index 4652f6b..b94ba55 100644
--- a/src/agent/subagents/headless.ts
+++ b/src/agent/subagents/headless.ts
@@ -205,11 +205,13 @@ function svgViewport(svg: string, opts: RenderSvgOptions): { width: number; heig
* are an arbitrary SPLIT of one zlib stream, so merging them is the more
* standard shape, byte-identical stream, zero re-encoding.
*
- * Pure Node on purpose (no sharp): the process already loads transformers'
- * nested sharp + libvips, and importing the root sharp (Next's optional
- * dependency) put a SECOND libvips into the process — macOS's ObjC runtime
- * warns (duplicate GNotificationCenterDelegate, "mysterious crashes").
- * One native image lib per process; app code carries none. */
+ * Pure Node on purpose (no sharp): historically the process already carried
+ * a native image lib via @huggingface/transformers' nested sharp + libvips,
+ * and importing the root sharp (Next's optional dependency) put a SECOND
+ * libvips into the process — macOS's ObjC runtime warns (duplicate
+ * GNotificationCenterDelegate, "mysterious crashes"). The transformers
+ * embedder died with wave 6 (2026-09-23) but the rule lives on: one native
+ * image lib per process; app code carries none. */
export function providerSafePng(png: Buffer): Buffer {
const SIG_LEN = 8;
if (png.length < SIG_LEN + 12 || png.subarray(0, SIG_LEN).toString("hex") !== "89504e470d0a1a0a") return png;
diff --git a/src/core/contracts/chat.ts b/src/core/contracts/chat.ts
index d3f170b..6537a05 100644
--- a/src/core/contracts/chat.ts
+++ b/src/core/contracts/chat.ts
@@ -108,6 +108,10 @@ export interface ExtractionRunUsage {
stages: {
extractor: ExtractionStageUsage;
auditor: ExtractionStageUsage;
+ /** Wave 6 (2026-09-23): the provider-embedding tail — present only
+ * when an embedding model is configured and the run embedded
+ * (local embeddings were free, so this post-dates them). */
+ embedding?: ExtractionStageUsage;
};
}
diff --git a/src/core/cost-summary.ts b/src/core/cost-summary.ts
index 2c29ff5..6270a7a 100644
--- a/src/core/cost-summary.ts
+++ b/src/core/cost-summary.ts
@@ -55,10 +55,12 @@ export interface GraphCostSummary {
totalDollars: number;
/** Runs where EVERY stage was unpriced (totalDollars excludes them). */
unpricedRuns: number;
- /** The three billable pipeline stages (merger/embedder are free). */
+ /** The billable pipeline stages (wave 6: the embedder became one —
+ * provider embeddings cost money; merger is the only free stage). */
stages: {
extraction: StageCost;
audit: StageCost;
+ embedding: StageCost;
naming: StageCost;
};
/** Newest first, capped at `recentCap` (default 10). */
@@ -113,6 +115,7 @@ function mergeTokens(into: CallUsage, steps: readonly CallUsage[]): void {
export function graphCostSummary(input: CostSummaryInput): GraphCostSummary {
const extraction = emptyStage();
const audit = emptyStage();
+ const embedding = emptyStage();
const naming = emptyStage();
const runs: RecentRun[] = [];
@@ -131,10 +134,25 @@ export function graphCostSummary(input: CostSummaryInput): GraphCostSummary {
if (audDollars === null) audit.unpricedRuns++;
else audit.dollars += audDollars;
- // Run-level: null only when BOTH stages are unpriced.
- const priced = extDollars ?? 0;
- const runDollars = extDollars === null && audDollars === null ? null : priced + (audDollars ?? 0);
- const allSteps = [...stages.extractor.steps, ...stages.auditor.steps];
+ // Wave 6: the embedding tail — present only when an embedding model
+ // ran (absent stage = the run embedded nothing, never "free").
+ let embDollars: number | null = null;
+ let embSteps: CallUsage[] = [];
+ if (stages.embedding) {
+ embedding.runs++;
+ embSteps = stages.embedding.steps;
+ mergeTokens(embedding.tokens, embSteps);
+ embDollars = stageDollars(stages.embedding.model, embSteps);
+ if (embDollars === null) embedding.unpricedRuns++;
+ else embedding.dollars += embDollars;
+ }
+
+ // Run-level: null only when EVERY stage is unpriced.
+ const allStages: Array = [extDollars, audDollars, embDollars];
+ const runDollars = allStages.every((d) => d === null)
+ ? null
+ : allStages.reduce((a, d) => a + (d ?? 0), 0);
+ const allSteps = [...stages.extractor.steps, ...stages.auditor.steps, ...embSteps];
runs.push({
startedAt: run.startedAt,
at: run.at,
@@ -177,9 +195,9 @@ export function graphCostSummary(input: CostSummaryInput): GraphCostSummary {
// A run is "unpriced" when it billed nothing countable at all.
const unpricedRuns = runs.filter((r) => r.dollars === null).length;
return {
- totalDollars: extraction.dollars + audit.dollars + naming.dollars,
+ totalDollars: extraction.dollars + audit.dollars + embedding.dollars + naming.dollars,
unpricedRuns,
- stages: { extraction, audit, naming },
+ stages: { extraction, audit, embedding, naming },
runs: capped,
};
}
diff --git a/src/core/ports.ts b/src/core/ports.ts
index 683a9e1..93df26f 100644
--- a/src/core/ports.ts
+++ b/src/core/ports.ts
@@ -243,3 +243,49 @@ export interface AuthStore {
/** Remove one VAR if present (absent = no-op, still a silent success). */
deleteAuthVar(name: string): void;
}
+
+// ─── EmbeddingPort — BYOK provider embeddings (wave 6, 2026-09-23) ───────────
+
+/**
+ * The provider-embedding seam (the local transformers embedder died with
+ * this wave): vectors come from the user's keyed provider — OpenRouter,
+ * OpenAI, or Google — named by graph.embeddingModel ("provider:id", null =
+ * honestly off: embedding/clustering/injection skip with an info log).
+ *
+ * Owner decisions (2026-09-23) baked in:
+ * - The adapters are resolved FRESH per call from the setting + the auth
+ * store (key rotations land immediately — the search port's treatment).
+ * - Vectors are stored as the provider returns them (default dims, no
+ * truncation, no normalization); the ledger is self-describing on
+ * model + dim, and any model change voids it (full re-embed).
+ * - Usage (prompt tokens) flows back to the money channel: adapters
+ * report it, the caller records it as a CallUsage step.
+ *
+ * Pure types only (browser-safe): the adapters are server-side
+ * (src/server/embeddings.ts) and arrive as injected dependencies.
+ */
+
+/** Which side of retrieval the text is — providers bill identically but
+ * quality-optimize differently (OpenRouter's input_type, Gemini's
+ * taskType); every input in one call shares the task. */
+export type EmbeddingTask = "document" | "query";
+
+/** One embedding batch's result: vectors in input order, the model's
+ * identity + dim (the ledger stamps), and the provider-reported prompt
+ * token count (undefined = provider didn't report; cost stays honest
+ * "—" via the existing unpriced path). */
+export interface EmbeddingResult {
+ vectors: number[][];
+ /** The full "provider:id" slug — ledger/cost keys use it verbatim. */
+ model: string;
+ dim: number;
+ promptTokens?: number;
+}
+
+/** A live provider embedding adapter. `embed` throws on failure (adapters
+ * map HTTP errors to clear Error messages); callers treat failure as
+ * non-fatal per the extraction contract. */
+export interface EmbeddingPort {
+ model: string;
+ embed(texts: readonly string[], task: EmbeddingTask): Promise;
+}
diff --git a/src/core/prices.ts b/src/core/prices.ts
index 8123082..3babfa4 100644
--- a/src/core/prices.ts
+++ b/src/core/prices.ts
@@ -2752,6 +2752,30 @@ export const CONTEXT_LIMITS: Record = {
// ─── Pure helpers (folds + cost inference) ───────────────────────────────────
+// ─── Embedding prices (wave 6, 2026-09-23) ─────────────────────────────────
+
+/** Hand-maintained BYOK embedding prices, USD per 1M INPUT tokens — the
+ * sync script never touches this block (pi-ai's catalogs carry no
+ * embedding models, so the generated PRICES table has none of these).
+ * VERIFIED against provider pricing pages 2026-09-23: OpenAI's model
+ * docs ($0.02 3-small / $0.13 3-large / $0.10 ada-002), Google's pricing
+ * page ($0.15 gemini-embedding-001 / $0.20 Gemini Embedding 2 text),
+ * OpenRouter passes provider pricing through. output: 0 — embeddings
+ * emit no output tokens. Unlisted models stay unpriced ("—", never
+ * zero); tokens still get captured. */
+export const EMBEDDING_PRICES: Record = {
+ "openai:text-embedding-3-small": { input: 0.02, output: 0 },
+ "openai:text-embedding-3-large": { input: 0.13, output: 0 },
+ "openai:text-embedding-ada-002": { input: 0.1, output: 0 },
+ "google:gemini-embedding-001": { input: 0.15, output: 0 },
+ "google:gemini-embedding-2": { input: 0.2, output: 0 },
+ "openrouter:openai/text-embedding-3-small": { input: 0.02, output: 0 },
+ "openrouter:openai/text-embedding-3-large": { input: 0.13, output: 0 },
+ "openrouter:openai/text-embedding-ada-002": { input: 0.1, output: 0 },
+ "openrouter:google/gemini-embedding-001": { input: 0.15, output: 0 },
+};
+
+
/** Sum a list of per-step usages into one CallUsage. A field stays
* undefined when EVERY step left it unreported — absent is not zero. */
export function sumSteps(steps: readonly CallUsage[]): CallUsage {
@@ -2773,7 +2797,8 @@ export function callCost(
usage: { inputTokens?: number; outputTokens?: number; cacheReadTokens?: number; cacheWriteTokens?: number },
model: string,
): number | null {
- const price = PRICES[model];
+ // Wave 6: the hand-maintained embedding overlay backs the lookup too.
+ const price = PRICES[model] ?? EMBEDDING_PRICES[model];
if (!price) return null;
if (usage.inputTokens === undefined || usage.outputTokens === undefined) return null;
const cacheRead = usage.cacheReadTokens ?? 0;
diff --git a/src/core/settings-resolution.ts b/src/core/settings-resolution.ts
index c399767..95596b0 100644
--- a/src/core/settings-resolution.ts
+++ b/src/core/settings-resolution.ts
@@ -201,6 +201,9 @@ export function resolveSettings(record: UserSettings | null): EffectiveSettings
embedding: graph.embedding ?? FACTORY_SETTINGS.graph.embedding,
clustering: graph.clustering ?? FACTORY_SETTINGS.graph.clustering,
labeling: graph.labeling ?? FACTORY_SETTINGS.graph.labeling,
+ // BYOK (wave 6): null is the factory floor and a VALID resolved
+ // value — ?? only fills the absent case, null passes through.
+ embeddingModel: graph.embeddingModel ?? FACTORY_SETTINGS.graph.embeddingModel,
},
};
}
diff --git a/src/core/settings.ts b/src/core/settings.ts
index 6741232..6481f25 100644
--- a/src/core/settings.ts
+++ b/src/core/settings.ts
@@ -251,6 +251,13 @@ export interface GraphSettings {
clustering?: boolean;
/** The LLM cluster-namer (needs clustering). */
labeling?: boolean;
+ /** BYOK embeddings (wave 6, 2026-09-23): the provider embedding model
+ * as a "provider:id" slug (openrouter:…, openai:…, google:…). null =
+ * no model — embedding/clustering/injection skip honestly (info log,
+ * graph stays textual); no factory floor exists. Keys live in the auth
+ * store, resolved fresh per call. A model CHANGE re-embeds everything
+ * (the ledger's staleness semantics). */
+ embeddingModel?: string | null;
}
/** THE record. Every section optional (delta); unknown top-level keys are
@@ -303,7 +310,7 @@ export const FACTORY_SETTINGS: FactorySettings = {
sessionNameSerif: true,
mdRendering: { headingWeight: 900, boldColor: null, italicColor: null },
},
- graph: { enabled: true, embedding: true, clustering: true, labeling: true },
+ graph: { enabled: true, embedding: true, clustering: true, labeling: true, embeddingModel: null },
};
// ─── Sanitizer ─────────────────────────────────────────────────────────────
@@ -453,6 +460,14 @@ function sanitizeGraph(raw: Record): GraphSettings {
if (clustering !== undefined) out.clustering = clustering;
const labeling = boolOrDrop(raw.labeling);
if (labeling !== undefined) out.labeling = labeling;
+ // BYOK embeddings (wave 6): null or a provider-qualified slug; anything
+ // else (bad type, bad shape) DROPS to absent — an invalid write never
+ // becomes a live model (the PUT parser 400s it first; this is the
+ // read-side belt-and-suspenders for hand-edited files).
+ if (raw.embeddingModel === null) out.embeddingModel = null;
+ else if (typeof raw.embeddingModel === "string" && /^\S+:\S+$/.test(raw.embeddingModel)) {
+ out.embeddingModel = raw.embeddingModel;
+ }
return out;
}
diff --git a/src/server/chat-handler.ts b/src/server/chat-handler.ts
index b2508c8..7d5f8ff 100644
--- a/src/server/chat-handler.ts
+++ b/src/server/chat-handler.ts
@@ -5,7 +5,7 @@ import { piEngineForSpec, type PiEngine } from "../agent/models.ts";
import { createJobRunner } from "../agent/subagents/runner.ts";
import { createExtractionPipeline } from "../agent/subagents/extraction.ts";
import { runGraphContextJob, type GraphContextDeps } from "../agent/subagents/graph-context.ts";
-import { EMBEDDING_DIM, EMBEDDING_MODEL, embedNewNodes, embedQuery } from "./embeddings.ts";
+import { embedNewNodes, embeddingPort } from "./embeddings.ts";
import type { ModelRole } from "../../config.ts";
import { claimSteers, deliverJobResult, setContextRespawn, setJobRespawn, setTurnRunner } from "./jobs.ts";
import { recordToPiMessages } from "./pi/record-adapter.ts";
@@ -63,8 +63,8 @@ const jobRunner = createJobRunner({
* (/api/graph/import) hit the same single-flight registry. */
export const extraction = createExtractionPipeline({
...stores,
- // The REAL embedder (local transformer model): post-merge embedding
- // batch — semantic clusters are computed and persisted here.
+ // The provider-embedder batch (BYOK wave 6): post-merge embedding —
+ // resolves the model fresh per call; null model = info-skip inside.
embedder: embedNewNodes,
// BYOK (owner, 2026-09-22): the extraction stages resolve the chain —
// role override → slot → NOTHING — read FRESH per stage call; an empty
@@ -75,14 +75,27 @@ export const extraction = createExtractionPipeline({
});
/** Graph context injection (vision-context-injection.md): the runner's
- * deps — same storage ports, the REAL embedder as the query seam (same
- * warm singleton as extraction, so vector-space parity holds by
- * construction), and the wake pipeline as the delivery seam. */
+ * deps — same storage ports, the provider-embedder RESOLVER as the query
+ * seam (BYOK wave 6: fresh setting + key reads per run, so vector-space
+ * parity with the ledger is checked against the CURRENT model; a key or
+ * settings PUT between dispatch and spawn lands), and the wake pipeline
+ * as the delivery seam. */
export const graphContext: GraphContextDeps = {
chatStore: stores.chatStore,
jobStore: stores.jobStore,
graphStore: stores.graphStore,
- embedder: { model: EMBEDDING_MODEL, dim: EMBEDDING_DIM, embedQuery },
+ embedder: () => {
+ const resolved = embeddingPort();
+ if (!resolved.ok) return null;
+ const port = resolved.port;
+ return {
+ model: port.model,
+ embedQuery: async (text: string) => {
+ const result = await port.embed([text], "query");
+ return { vector: result.vectors[0]!, promptTokens: result.promptTokens };
+ },
+ };
+ },
deliver: deliverJobResult,
};
@@ -221,7 +234,10 @@ export async function handleChatRequest(
// GRAPH GATES (settings-storage wave, 2026-09-19): the read channel
// needs BOTH the master switch and the embedding rung (injection is a
// vector query); with graph off there is no context job at all.
- if (graphContextEnabled(effective.graph)) {
+ // BYOK (wave 6): an unconfigured embedding model means no vectors to
+ // query — the dispatch skips honestly (the runner's own resolution is
+ // the belt-and-suspenders for respawn races).
+ if (graphContextEnabled(effective.graph) && effective.graph.embeddingModel !== null) {
triggerGraphContext(graphContext, chatId);
}
diff --git a/src/server/embeddings.ts b/src/server/embeddings.ts
index 4f83884..d09fd71 100644
--- a/src/server/embeddings.ts
+++ b/src/server/embeddings.ts
@@ -1,94 +1,293 @@
/**
- * THE EMBEDDER (DECIDED 2026-09-13): semantic topic clustering needs
- * vectors, and vectors need a model running ON the user's machine — no
- * external services, no API bills, no network dependency for re-embedding.
+ * BYOK PROVIDER EMBEDDINGS (wave 6, 2026-09-23): the local transformers
+ * embedder is dead — vectors now come from the user's keyed provider
+ * (OpenRouter / OpenAI / Google), named by graph.embeddingModel
+ * ("provider:id", null = honestly off; skip with an info log, the graph
+ * stays textual — owner ruling 2026-09-23).
*
- * Runtime: in-process transformers.js (@huggingface/transformers v4 over
- * onnxruntime-node — native Apple Silicon acceleration). The model
- * weights download ONCE to the local HF cache on first run (~300MB).
+ * Owner decisions baked in:
+ * - NO factory model (BYOK, like the model slots): null is the floor.
+ * - Adapters resolve FRESH per call from the setting + the auth store
+ * (the search port's treatment — key rotations land immediately); a
+ * key missing for a SET model is an honest error, never a fallback.
+ * - Vectors stored as the provider returns them (default dims, no
+ * truncation, no normalization). The ledger is self-describing on
+ * model + dim; a model change voids it (full re-embed, minutes at
+ * current scale — the local embedder's same staleness rule).
+ * - Usage (prompt tokens) flows to the money channel: every API call
+ * reports one CallUsage step (outputTokens: 0 — embeddings emit no
+ * output; priced via the hand-maintained EMBEDDING_PRICES overlay).
*
- * Model: EmbeddingGemma-300M (q8) — best quality-per-megabyte small
- * embedding model as of late 2025 (MTEB-en 68.36), built for on-device
- * use, with MRL truncation so we store 512 of its 768 dims. Every input
- * uses the model card's document format ("title: none | text: …"),
- * consistently — mixing prefixed and unprefixed inputs degrades quality.
- *
- * Model swaps re-embed EVERYTHING: vectors from different models live in
- * incompatible spaces. The ledger records model + dim; a mismatch marks
- * the whole ledger stale and this module re-embeds from scratch (minutes
- * at current scale).
+ * The adapters are injected-fetch dependencies so tests never touch the
+ * network; wire protocols VERIFIED against provider docs 2026-09-23:
+ * - OpenRouter: POST /api/v1/embeddings (Bearer), input_type
+ * search_document|search_query; catalog GET /api/v1/embeddings/models
+ * (VERIFIED live 2026-09-23 — the inverse path /api/v1/models/
+ * embeddings 404s).
+ * - OpenAI: POST /v1/embeddings (Bearer); catalog GET /v1/models.
+ * - Google: POST /v1beta/models/{m}:batchEmbedContents (x-goog-api-key),
+ * taskType RETRIEVAL_DOCUMENT|RETRIEVAL_QUERY; catalog GET /v1beta/models
+ * filtered on supportedGenerationMethods ∋ embedContent.
*/
-import * as fs from "node:fs";
-import { env, pipeline, type FeatureExtractionPipeline } from "@huggingface/transformers";
-import { PATHS } from "../../config.ts";
-import type { EmbeddingsLedger, GraphNode } from "../core/contracts.ts";
+
+import type { CallUsage, EmbeddingsLedger, GraphNode } from "../core/contracts.ts";
+import type { ExtractionStageUsage } from "../core/contracts/chat.ts";
+import type { EmbeddingPort, EmbeddingResult, EmbeddingTask } from "../core/ports.ts";
import { semanticClusters, SEMANTIC_SIM_THRESHOLD } from "../core/semantic-clusters.ts";
+import { keyValue } from "./keys.ts";
+import { effectiveSettings } from "./stores.ts";
-export const EMBEDDING_MODEL = "onnx-community/embeddinggemma-300m-ONNX";
-/** MRL truncation of the native 768 — negligible quality loss, half the
- * ledger size (2026-09-13 researcher sweep). */
-export const EMBEDDING_DIM = 512;
-/** Batch size bounds peak memory; propositions are tiny so 32 per call
- * keeps the pipeline warm without thrashing. */
+/** The wire-callable shape the adapters close over (tests inject a stub). */
+type FetchLike = (input: string, init: RequestInit) => Promise;
+
+/** One provider embedding API call — kept small enough to never trip
+ * per-request input limits (propositions are tiny; 32 was the local
+ * embedder's batch and it stays). */
const EMBED_BATCH = 32;
+/** Per-request timeout: a hung provider call must not hang an extraction
+ * run (the wave-1 hung-job lesson). */
+const REQUEST_TIMEOUT_MS = 60_000;
-// Model cache routing (Electron seam, 2026-09-17): the default cacheDir
-// lives inside node_modules — read-only inside a packaged .app bundle.
-// When LH_DATA_DIR is set the cache follows the data seam (userData);
-// in dev it stays at the package default (the model is already there).
-if (PATHS.modelCache) {
- fs.mkdirSync(PATHS.modelCache, { recursive: true });
- env.cacheDir = PATHS.modelCache;
+/** The providers this wave ships + their auth vars (the curated key
+ * catalog, same ids the auth store and /api/keys use). */
+const PROVIDER_KEYS = {
+ openrouter: "OPENROUTER_API_KEY",
+ openai: "OPENAI_API_KEY",
+ google: "GEMINI_API_KEY",
+} as const;
+export type EmbeddingProviderId = keyof typeof PROVIDER_KEYS;
+
+/** "provider:id" → {provider, id}; null when malformed (no guessing). */
+export function parseEmbeddingModelSlug(slug: string): { provider: EmbeddingProviderId; id: string } | null {
+ const colon = slug.indexOf(":");
+ if (colon <= 0 || colon === slug.length - 1) return null;
+ const provider = slug.slice(0, colon) as EmbeddingProviderId;
+ if (!(provider in PROVIDER_KEYS)) return null;
+ return { provider, id: slug.slice(colon + 1) };
}
-let pipelinePromise: Promise | null = null;
+// ─── Adapters (one per provider; pure injected-fetch factories) ──────────────
-function getPipeline(): Promise {
- pipelinePromise ??= pipeline("feature-extraction", EMBEDDING_MODEL, { dtype: "q8" });
- return pipelinePromise;
+/** Shared: HTTP-error → clear Error (the search adapters' mapping). */
+async function demandOk(resp: Response, label: string): Promise {
+ if (resp.ok) return;
+ const body = await resp.text();
+ throw new Error(`${label} API ${resp.status}: ${body.slice(0, 200)}`);
}
-/** EmbeddingGemma's required document format (model card). */
-function embedInput(statement: string): string {
- return `title: none | text: ${statement}`;
+/** Shared: normalize a provider's {embedding, index} rows to input order. */
+function rowsInOrder(
+ data: Array<{ embedding?: unknown; index?: unknown }>,
+ count: number,
+ label: string,
+): number[][] {
+ const byIndex = new Map();
+ for (const row of data) {
+ if (
+ Array.isArray(row.embedding) &&
+ row.embedding.every((x) => typeof x === "number") &&
+ typeof row.index === "number"
+ ) {
+ byIndex.set(row.index, row.embedding as number[]);
+ }
+ }
+ const out: number[][] = [];
+ for (let i = 0; i < count; i++) {
+ const vec = byIndex.get(i);
+ if (!vec) throw new Error(`${label} API returned ${byIndex.size}/${count} vectors`);
+ out.push(vec);
+ }
+ return out;
}
-/** EmbeddingGemma's retrieval-QUERY format (model card) — the topic side of
- * graph context injection (vision-context-injection.md). Role-asymmetric
- * BY DESIGN: queries and documents use different trained templates; the
- * requirement is same model + same truncation (one vector space), each
- * side in the format the model was trained for. */
-function queryInput(text: string): string {
- return `task: search result | query: ${text}`;
+/** One API call's money-channel step: embeddings emit no output, cache
+ * nothing, reason never — the fields exist (CallUsage requires them) as
+ * absent-is-not-zero undefineds. */
+function embeddingStep(promptTokens: number): CallUsage {
+ return {
+ inputTokens: promptTokens,
+ outputTokens: 0,
+ cacheReadTokens: undefined,
+ cacheWriteTokens: undefined,
+ reasoningTokens: undefined,
+ };
}
-/** Embed one retrieval query (the session's topic) — same warm singleton,
- * same 512-dim MRL truncation as the ledger. The one embedding call the
- * injection job makes; tens–~200ms warm. */
-export async function embedQuery(text: string): Promise {
- const extractor = await getPipeline();
- const output = await extractor([queryInput(text)], { pooling: "mean", normalize: true });
- return truncateNormalize((output.tolist() as number[][])[0]!);
+/** OpenRouter: POST https://openrouter.ai/api/v1/embeddings — Bearer auth,
+ * input_type hints the retrieval side (verified against the docs 2026-09-23). */
+export function openrouterEmbeddingProvider(model: string, apiKey: string, fetchFn: FetchLike = fetch): EmbeddingPort {
+ const parsed = parseEmbeddingModelSlug(model);
+ if (!parsed) throw new Error(`invalid embedding model slug: ${model}`);
+ return {
+ model,
+ async embed(texts: readonly string[], task: EmbeddingTask): Promise {
+ const resp = await fetchFn("https://openrouter.ai/api/v1/embeddings", {
+ method: "POST",
+ headers: { "content-type": "application/json", authorization: `Bearer ${apiKey}` },
+ body: JSON.stringify({
+ model: parsed.id,
+ input: texts,
+ input_type: task === "query" ? "search_query" : "search_document",
+ }),
+ signal: AbortSignal.timeout(REQUEST_TIMEOUT_MS),
+ });
+ await demandOk(resp, "OpenRouter embeddings");
+ const data = (await resp.json()) as {
+ data?: Array<{ embedding?: unknown; index?: unknown }>;
+ usage?: { prompt_tokens?: number };
+ };
+ return {
+ vectors: rowsInOrder(data.data ?? [], texts.length, "OpenRouter embeddings"),
+ model,
+ dim: 0, // filled by the caller from the first vector (below)
+ promptTokens: data.usage?.prompt_tokens,
+ };
+ },
+ };
}
-/** Truncate an L2-normalized vector to EMBEDDING_DIM (MRL: leading dims
- * carry most of the signal) and re-normalize so cosine = dot product. */
-function truncateNormalize(vec: readonly number[]): number[] {
- const out = vec.slice(0, EMBEDDING_DIM);
- let mag = 0;
- for (const x of out) mag += x * x;
- mag = Math.sqrt(mag);
- return mag > 0 ? out.map((x) => x / mag) : out;
+/** OpenAI: POST https://api.openai.com/v1/embeddings — Bearer auth; the
+ * response's usage carries prompt_tokens (verified 2026-09-23). */
+export function openaiEmbeddingProvider(model: string, apiKey: string, fetchFn: FetchLike = fetch): EmbeddingPort {
+ const parsed = parseEmbeddingModelSlug(model);
+ if (!parsed) throw new Error(`invalid embedding model slug: ${model}`);
+ return {
+ model,
+ async embed(texts: readonly string[], task: EmbeddingTask): Promise {
+ // OpenAI's embeddings API takes no task hint (one format per
+ // model); the argument exists for seam parity and is unused here.
+ void task;
+ const resp = await fetchFn("https://api.openai.com/v1/embeddings", {
+ method: "POST",
+ headers: { "content-type": "application/json", authorization: `Bearer ${apiKey}` },
+ body: JSON.stringify({ model: parsed.id, input: texts }),
+ signal: AbortSignal.timeout(REQUEST_TIMEOUT_MS),
+ });
+ await demandOk(resp, "OpenAI embeddings");
+ const data = (await resp.json()) as {
+ data?: Array<{ embedding?: unknown; index?: unknown }>;
+ usage?: { prompt_tokens?: number };
+ };
+ return {
+ vectors: rowsInOrder(data.data ?? [], texts.length, "OpenAI embeddings"),
+ model,
+ dim: 0,
+ promptTokens: data.usage?.prompt_tokens,
+ };
+ },
+ };
+}
+
+/** Google: POST …/models/{m}:batchEmbedContents — x-goog-api-key, one
+ * request per text with taskType RETRIEVAL_QUERY|RETRIEVAL_DOCUMENT
+ * (verified against the Gemini API docs 2026-09-23). */
+export function googleEmbeddingProvider(model: string, apiKey: string, fetchFn: FetchLike = fetch): EmbeddingPort {
+ const parsed = parseEmbeddingModelSlug(model);
+ if (!parsed) throw new Error(`invalid embedding model slug: ${model}`);
+ return {
+ model,
+ async embed(texts: readonly string[], task: EmbeddingTask): Promise {
+ const resp = await fetchFn(
+ `https://generativelanguage.googleapis.com/v1beta/models/${encodeURIComponent(parsed.id)}:batchEmbedContents`,
+ {
+ method: "POST",
+ headers: { "content-type": "application/json", "x-goog-api-key": apiKey },
+ body: JSON.stringify({
+ requests: texts.map((text) => ({
+ model: `models/${parsed.id}`,
+ content: { parts: [{ text }] },
+ taskType: task === "query" ? "RETRIEVAL_QUERY" : "RETRIEVAL_DOCUMENT",
+ })),
+ }),
+ signal: AbortSignal.timeout(REQUEST_TIMEOUT_MS),
+ },
+ );
+ await demandOk(resp, "Google embeddings");
+ const data = (await resp.json()) as {
+ embeddings?: Array<{ values?: unknown }>;
+ /** embedContent responses carry usageMetadata; the batch
+ * shape may too — parsed opportunistically, never guessed. */
+ usageMetadata?: { promptTokenCount?: number };
+ };
+ const vectors = (data.embeddings ?? []).map((row, i) => {
+ if (!Array.isArray(row.values) || !row.values.every((x) => typeof x === "number")) {
+ throw new Error(`Google embeddings API returned a bad vector at index ${i}`);
+ }
+ return row.values as number[];
+ });
+ if (vectors.length !== texts.length) {
+ throw new Error(`Google embeddings API returned ${vectors.length}/${texts.length} vectors`);
+ }
+ return { vectors, model, dim: 0, promptTokens: data.usageMetadata?.promptTokenCount };
+ },
+ };
+}
+
+// ─── Resolution (fresh per call — the search port's treatment) ───────────────
+
+/** The resolved state: a live port, or the honest reason it isn't. */
+export type EmbeddingResolution =
+ | { ok: true; port: EmbeddingPort }
+ | { ok: false; reason: string };
+
+/** Pure resolution from a setting slug + a key lookup (testable): null
+ * slug = off; a set slug with no key = honest unavailability. */
+export function resolveEmbeddingPortFor(
+ slug: string | null | undefined,
+ keyOf: (envVar: string) => string | undefined,
+ fetchFn?: FetchLike,
+): EmbeddingResolution {
+ if (slug === null || slug === undefined || slug === "") {
+ return { ok: false, reason: "no embedding model configured (graph.embeddingModel is null)" };
+ }
+ const parsed = parseEmbeddingModelSlug(slug);
+ if (!parsed) {
+ return { ok: false, reason: `invalid embedding model slug: ${slug}` };
+ }
+ const apiKey = keyOf(PROVIDER_KEYS[parsed.provider]);
+ if (!apiKey) {
+ return {
+ ok: false,
+ reason: `embedding model is set to "${slug}" but its ${PROVIDER_KEYS[parsed.provider]} key is missing`,
+ };
+ }
+ const factory =
+ parsed.provider === "openrouter"
+ ? openrouterEmbeddingProvider
+ : parsed.provider === "openai"
+ ? openaiEmbeddingProvider
+ : googleEmbeddingProvider;
+ return { ok: true, port: factory(slug, apiKey, fetchFn) };
+}
+
+/** The LIVE resolution — reads the settings record + auth store fresh on
+ * every call, so a settings PUT or a key save lands on the next call. */
+export function embeddingPort(): EmbeddingResolution {
+ return resolveEmbeddingPortFor(effectiveSettings().graph.embeddingModel, keyValue);
+}
+
+// ─── The post-merge batch (the extraction pipeline's embedding tail) ────────
+
+/** What the embedding tail reports back: counts for logs, the skip reason
+ * when nothing ran (owner ruling: null model = info skip, not error), and
+ * the money-channel stage when it billed (one CallUsage step per API call,
+ * outputTokens: 0 — priced via EMBEDDING_PRICES). */
+export interface EmbedBatchResult {
+ embedded: number;
+ total: number;
+ skipped?: string;
+ usage?: ExtractionStageUsage;
}
/**
* Embed every node the ledger is missing — the post-merge hook (new
* propositions only, typically a handful) AND the cold-start backfill
- * (empty ledger = every node) in one function. Model/dim mismatch voids
- * the ledger first (full re-embed). Also prunes vectors for nodes that
- * no longer exist. Writes the whole ledger and returns counts for logs.
- * Non-fatal by contract: the caller treats failure as "clustering runs
- * without the new nodes until the next merge retries".
+ * (empty ledger = every node) in one function. A model change voids the
+ * ledger first (full re-embed — vectors from different models live in
+ * incompatible spaces). Also prunes vectors for nodes that no longer
+ * exist, then re-clusters ONCE per batch (consumers read the persisted
+ * partition). Non-fatal by contract: the caller treats failure as
+ * "clustering runs without the new nodes until the next merge retries".
*/
export async function embedNewNodes(
graphStore: {
@@ -96,10 +295,21 @@ export async function embedNewNodes(
readEmbeddings(): EmbeddingsLedger;
writeEmbeddings(ledger: EmbeddingsLedger): void;
},
-): Promise<{ embedded: number; total: number }> {
+ /** Test seam: the live resolution by default; tests inject a scripted
+ * port (they never read the machine's settings/auth files). */
+ resolvePort: () => EmbeddingResolution = embeddingPort,
+): Promise {
+ const resolved = resolvePort();
const ledger = graphStore.readEmbeddings();
- const stale = ledger.model !== EMBEDDING_MODEL || ledger.dim !== EMBEDDING_DIM;
+ if (!resolved.ok) {
+ console.info(`[embeddings] skipped — ${resolved.reason}`);
+ return { embedded: 0, total: Object.keys(ledger.vectors).length, skipped: resolved.reason };
+ }
+ const port = resolved.port;
+ const stale = ledger.model !== port.model;
const vectors: Record = stale ? {} : { ...ledger.vectors };
+ const steps: NonNullable["steps"] = [];
+ let dim = ledger.dim;
// Node LINES may repeat an id — dedupe, first defines (getGraph rule).
const seen = new Set();
@@ -110,18 +320,20 @@ export async function embedNewNodes(
if (!vectors[node.id]) todo.push(node);
}
- if (todo.length > 0) {
- const extractor = await getPipeline();
- for (let i = 0; i < todo.length; i += EMBED_BATCH) {
- const batch = todo.slice(i, i + EMBED_BATCH);
- const output = await extractor(batch.map((n) => embedInput(n.statement)), {
- pooling: "mean",
- normalize: true,
- });
- const rows = output.tolist() as number[][];
- for (let j = 0; j < batch.length; j++) {
- vectors[batch[j]!.id] = truncateNormalize(rows[j]!);
- }
+ for (let i = 0; i < todo.length; i += EMBED_BATCH) {
+ const batch = todo.slice(i, i + EMBED_BATCH);
+ const result = await port.embed(
+ batch.map((n) => n.statement),
+ "document",
+ );
+ for (let j = 0; j < batch.length; j++) {
+ vectors[batch[j]!.id] = result.vectors[j]!;
+ }
+ if (result.vectors[0]) dim = result.vectors[0].length;
+ if (result.promptTokens !== undefined) {
+ // outputTokens: 0 — embeddings emit no output; callCost needs it
+ // defined to price the input at all.
+ steps.push(embeddingStep(result.promptTokens));
}
}
@@ -135,20 +347,112 @@ export async function embedNewNodes(
}
// RECLUSTER AT THE END OF THE BATCH (user-decided 2026-09-13): the
- // agglomerative pass is ~1.5s at current scale, so it runs HERE —
- // once per embedding batch — and consumers (snapshot, settle, namer)
- // read the persisted partition instead of recomputing per read.
+ // agglomerative pass runs HERE — once per embedding batch — and
+ // consumers (snapshot, settle, namer) read the persisted partition.
const clusters = semanticClusters(vectors, { similarityThreshold: SEMANTIC_SIM_THRESHOLD });
const wrote = todo.length > 0 || pruned > 0 || stale || ledger.clusters.length !== clusters.length;
if (wrote) {
graphStore.writeEmbeddings({
- model: EMBEDDING_MODEL,
- dim: EMBEDDING_DIM,
+ model: port.model,
+ dim,
vectors,
clusters,
updatedAt: new Date().toISOString(),
});
}
- return { embedded: todo.length, total: Object.keys(vectors).length };
+ return {
+ embedded: todo.length,
+ total: Object.keys(vectors).length,
+ usage: steps.length > 0 ? { model: port.model, steps } : undefined,
+ };
+}
+// ─── The federated embedding catalog (wave 6, owner ruling 2026-09-23) ──────
+
+/** One catalog row: provider-qualified id (the setting's exact slug
+ * format) + display name. */
+export interface EmbeddingCatalogModel {
+ /** The full "provider:id" slug — what graph.embeddingModel stores. */
+ id: string;
+ /** Human label for the picker (the provider's name, when given). */
+ name: string;
+}
+
+/** The embedding models of every KEYED provider, fetched live (the
+ * chat-models picker is a static pi-ai catalog, but pi-ai carries no
+ * embedding models — so this endpoint federates the providers' own
+ * lists). A provider without a key contributes nothing; a provider whose
+ * catalog call fails is skipped with an error log (never poisons the
+ * rest, never fails the endpoint). Empty array = nothing keyed. */
+export async function embeddingModelCatalog(
+ fetchFn: FetchLike = fetch,
+ /** Test seam: the live key lookup by default; tests inject scripted
+ * keys (they never read the machine's auth file). */
+ keyOf: (id: string) => string | undefined = keyValue,
+): Promise {
+ const out: EmbeddingCatalogModel[] = [];
+ const fetchJson = async (url: string, headers: Record): Promise => {
+ const resp = await fetchFn(url, { headers, signal: AbortSignal.timeout(REQUEST_TIMEOUT_MS) });
+ await demandOk(resp, "Embeddings catalog");
+ return resp.json();
+ };
+
+ // OpenRouter: GET /api/v1/embeddings/models — the dedicated embedding
+ // list (VERIFIED live 2026-09-23: the inverse path /api/v1/models/
+ // embeddings 404s; this one returns {data: [{id, name, …}]}). Paginated
+ // — limit=500 covers the whole list at current size (33).
+ if (keyOf(PROVIDER_KEYS.openrouter)) {
+ try {
+ const data = (await fetchJson("https://openrouter.ai/api/v1/embeddings/models?limit=500", {
+ authorization: `Bearer ${keyOf(PROVIDER_KEYS.openrouter)}`,
+ })) as { data?: Array<{ id?: unknown; name?: unknown }> };
+ for (const m of data.data ?? []) {
+ if (typeof m.id !== "string" || !m.id) continue;
+ out.push({ id: `openrouter:${m.id}`, name: typeof m.name === "string" && m.name ? m.name : m.id });
+ }
+ } catch (err) {
+ console.error("[embeddings] OpenRouter catalog fetch failed:", err);
+ }
+ }
+
+ // OpenAI: GET /v1/models — no embedding-only list, so filter the
+ // generic one on the embedding naming convention.
+ if (keyOf(PROVIDER_KEYS.openai)) {
+ try {
+ const data = (await fetchJson("https://api.openai.com/v1/models", {
+ authorization: `Bearer ${keyOf(PROVIDER_KEYS.openai)}`,
+ })) as { data?: Array<{ id?: unknown }> };
+ for (const m of data.data ?? []) {
+ if (typeof m.id !== "string" || !/^text-embedding-/.test(m.id)) continue;
+ out.push({ id: `openai:${m.id}`, name: m.id });
+ }
+ } catch (err) {
+ console.error("[embeddings] OpenAI catalog fetch failed:", err);
+ }
+ }
+
+ // Google: GET /v1beta/models — filter on the methods the model
+ // actually serves (embedContent present).
+ if (keyOf(PROVIDER_KEYS.google)) {
+ try {
+ const data = (await fetchJson("https://generativelanguage.googleapis.com/v1beta/models?pageSize=1000", {
+ "x-goog-api-key": keyOf(PROVIDER_KEYS.google)!,
+ })) as {
+ models?: Array<{ name?: unknown; displayName?: unknown; supportedGenerationMethods?: unknown }>;
+ };
+ for (const m of data.models ?? []) {
+ if (typeof m.name !== "string" || !m.name.startsWith("models/")) continue;
+ if (!Array.isArray(m.supportedGenerationMethods) || !m.supportedGenerationMethods.includes("embedContent")) continue;
+ const id = m.name.slice("models/".length);
+ out.push({
+ id: `google:${id}`,
+ name: typeof m.displayName === "string" && m.displayName ? m.displayName : id,
+ });
+ }
+ } catch (err) {
+ console.error("[embeddings] Google catalog fetch failed:", err);
+ }
+ }
+
+ return out;
}
diff --git a/src/server/index.ts b/src/server/index.ts
index fd23306..ebf64d0 100644
--- a/src/server/index.ts
+++ b/src/server/index.ts
@@ -6,6 +6,7 @@
export * from "./chat-handler.ts";
export * from "./chats.ts";
+export * from "./embeddings.ts";
export * from "./graph.ts";
export * from "./commit-positions.ts";
export * from "./jobs.ts";
diff --git a/src/server/settings-body.ts b/src/server/settings-body.ts
index 9c5e91f..2f823d3 100644
--- a/src/server/settings-body.ts
+++ b/src/server/settings-body.ts
@@ -277,7 +277,11 @@ export function parseAppearanceSettingsBody(body: unknown): SettingsBodyResult {
const raw = asRecord(body);
if (!raw) return { ok: false, error: "Invalid JSON body" };
@@ -290,6 +294,25 @@ export function parseGraphSettingsBody(body: unknown): SettingsBodyResult {
assert.equal(s.unpricedRuns, 1); // run-level: only the both-stages run
});
+ test("the embedding stage (wave 6): folds when present, absent when the run embedded nothing", () => {
+ const EMBED_MODEL = "openai:text-embedding-3-small";
+ const embStep = callCost(step(5000, 0), EMBED_MODEL)!;
+ assert.ok(embStep > 0, "the overlay prices the known embedding models");
+ const withEmbed = extractionRun(100, PRICED, PRICED);
+ withEmbed.stages.embedding = { model: EMBED_MODEL, steps: [step(5000, 0)] };
+ const s = graphCostSummary({
+ chats: [{ title: "a", extractions: [withEmbed] }, { title: "b", extractions: [extractionRun(200, PRICED, PRICED)] }],
+ sources: [],
+ naming: [],
+ });
+ assert.equal(s.stages.embedding.runs, 1, "only the run that embedded");
+ assert.equal(s.stages.embedding.dollars, embStep);
+ assert.equal(s.stages.embedding.tokens.inputTokens, 5000);
+ assert.equal(s.stages.extraction.runs, 2, "the two-stage era still folds");
+ assert.equal(s.stages.extraction.runs, 2);
+ // Run-level: the embedding dollars ride the run's total.
+ const extStep = callCost(step(1000, 200), PRICED)!;
+ const audStep = callCost(step(2000, 100), PRICED)!;
+ assert.equal(s.runs.find((r) => r.startedAt === 100)!.dollars, extStep + audStep + embStep);
+ assert.equal(s.runs.find((r) => r.startedAt === 200)!.dollars, extStep + audStep);
+ assert.equal(s.totalDollars, (extStep + audStep) * 2 + embStep);
+ });
+
+ test("an UNPRICED embedding model stays honest: counted, never a silent zero; a priced sibling saves the run total", () => {
+ const unpricedEmbed = extractionRun(100, PRICED, "unknown-model");
+ unpricedEmbed.stages.embedding = { model: "some/new-embed", steps: [step(900, 0)] };
+ const s = graphCostSummary({ chats: [{ title: "x", extractions: [unpricedEmbed] }], sources: [], naming: [] });
+ assert.equal(s.stages.embedding.unpricedRuns, 1);
+ assert.equal(s.stages.embedding.dollars, 0);
+ assert.notEqual(s.runs[0]!.dollars, null, "the priced extractor saves the run total");
+ });
+
test("recent runs cap: newest survive", () => {
const extractions = [1, 2, 3, 4].map((n) => extractionRun(n * 100, PRICED, PRICED));
const s = graphCostSummary({
diff --git a/tests/data-dir-seam.test.ts b/tests/data-dir-seam.test.ts
index def0c06..f91b226 100644
--- a/tests/data-dir-seam.test.ts
+++ b/tests/data-dir-seam.test.ts
@@ -19,7 +19,7 @@ const REPO_ROOT = path.resolve(import.meta.dirname, "..");
const TSX_LOADER = path.join(REPO_ROOT, "node_modules", "tsx", "dist", "loader.mjs");
describe("LH_DATA_DIR seam", () => {
- it("relocates data/chats/graph + modelCache under LH_DATA_DIR, keeps prompts ROOT-anchored", async () => {
+ it("relocates data/chats/graph under LH_DATA_DIR, keeps prompts ROOT-anchored", async () => {
const dir = fs.mkdtempSync(path.join(os.tmpdir(), "lh-seam-"));
process.env.LH_DATA_DIR = dir;
try {
@@ -27,7 +27,6 @@ describe("LH_DATA_DIR seam", () => {
assert.equal(PATHS.data, dir, "PATHS.data resolves the env value (resolved absolute)");
assert.equal(PATHS.chats, path.join(dir, "chats"));
assert.equal(PATHS.graph, path.join(dir, "graph"));
- assert.equal(PATHS.modelCache, path.join(dir, "models"), "the HF model cache follows the seam");
assert.equal(
PATHS.teacherPrompt,
path.join(ROOT, "src", "agent", "system-prompt.md"),
@@ -41,12 +40,11 @@ describe("LH_DATA_DIR seam", () => {
it("unset = the repo data/ exactly as before (fresh child process, no env)", () => {
const out = execFileSync(
process.execPath,
- ["--import", TSX_LOADER, "--eval", `const m = await import(${JSON.stringify(path.join(REPO_ROOT, "config.ts"))}); console.log(JSON.stringify({ data: m.PATHS.data, chats: m.PATHS.chats, modelCache: m.PATHS.modelCache }));`],
+ ["--import", TSX_LOADER, "--eval", `const m = await import(${JSON.stringify(path.join(REPO_ROOT, "config.ts"))}); console.log(JSON.stringify({ data: m.PATHS.data, chats: m.PATHS.chats }));`],
{ cwd: REPO_ROOT, encoding: "utf-8" },
);
- const parsed = JSON.parse(out) as { data: string; chats: string | null; modelCache: string | null };
+ const parsed = JSON.parse(out) as { data: string; chats: string | null };
assert.equal(parsed.data, path.join(REPO_ROOT, "data"));
assert.equal(parsed.chats, path.join(REPO_ROOT, "data", "chats"));
- assert.equal(parsed.modelCache, null, "dev keeps the transformers package default cache");
});
});
\ No newline at end of file
diff --git a/tests/embeddings.test.ts b/tests/embeddings.test.ts
new file mode 100644
index 0000000..1990d7e
--- /dev/null
+++ b/tests/embeddings.test.ts
@@ -0,0 +1,401 @@
+/**
+ * BYOK provider embeddings (wave 6, 2026-09-23): the adapters' wire
+ * protocols (injected fetch — never the network), the slug/keys
+ * resolution rules (null = honestly off; a set model with a missing key
+ * is an honest error), the post-merge batch's staleness/re-embed/skip
+ * semantics (scripted port — never the machine's settings/auth files),
+ * and the federated catalog's federation rules.
+ */
+
+import assert from "node:assert/strict";
+import { describe, it } from "node:test";
+import { callCost, EMBEDDING_PRICES } from "../src/core/prices.ts";
+import {
+ embedNewNodes,
+ embeddingModelCatalog,
+ googleEmbeddingProvider,
+ openaiEmbeddingProvider,
+ openrouterEmbeddingProvider,
+ parseEmbeddingModelSlug,
+ resolveEmbeddingPortFor,
+ type EmbeddingResolution,
+} from "../src/server/embeddings.ts";
+import type { EmbeddingPort, EmbeddingTask } from "../src/core/ports.ts";
+import type { EmbeddingsLedger, GraphNode } from "../src/core/contracts/graph.ts";
+
+// ─── scripted fetch + in-memory graph (no fs, no network) ────────────────────
+
+type RecordedCall = { url: string; init: RequestInit };
+
+function jsonResponse(body: unknown, status = 200): Response {
+ return new Response(JSON.stringify(body), {
+ status,
+ headers: { "content-type": "application/json" },
+ });
+}
+
+function recordingFetch(
+ route: (url: string, body: unknown) => Response | Promise,
+): { calls: RecordedCall[]; fetch: (input: string, init: RequestInit) => Promise } {
+ const calls: RecordedCall[] = [];
+ const fetchFn = async (input: string, init: RequestInit): Promise => {
+ calls.push({ url: input, init });
+ const body = init.body ? (JSON.parse(String(init.body)) as unknown) : null;
+ return route(input, body);
+ };
+ return { calls, fetch: fetchFn };
+}
+
+function node(id: string, statement = `statement of ${id}`): GraphNode {
+ return { id, name: id, statement, aliases: [], provenance: [], createdAt: "2026-09-23T00:00:00.000Z" };
+}
+
+function fakeGraphStore(start?: Partial): {
+ ledger: EmbeddingsLedger;
+ writes: EmbeddingsLedger[];
+ store: {
+ readNodes(): GraphNode[];
+ readEmbeddings(): EmbeddingsLedger;
+ writeEmbeddings(ledger: EmbeddingsLedger): void;
+ };
+ nodes: GraphNode[];
+} {
+ const nodes = [node("n1", "alpha fact"), node("n2", "beta fact")];
+ const ledger: EmbeddingsLedger = {
+ model: start?.model ?? "test-embed",
+ dim: start?.dim ?? 2,
+ vectors: { ...start?.vectors },
+ clusters: [...start?.clusters ?? []],
+ updatedAt: start?.updatedAt ?? "2026-09-23T00:00:00.000Z",
+ };
+ const writes: EmbeddingsLedger[] = [];
+ return {
+ ledger,
+ writes,
+ nodes,
+ store: {
+ readNodes: () => nodes,
+ readEmbeddings: () => ledger,
+ writeEmbeddings: (next) => {
+ writes.push(next);
+ Object.assign(ledger, next);
+ },
+ },
+ };
+}
+
+/** A scripted port: unit vectors by text hash, records (texts, task) calls. */
+function scriptedPort(model = "openai:test-embed", dim = 2, tokensPerCall = 120): {
+ calls: Array<{ texts: string[]; task: EmbeddingTask }>;
+ port: EmbeddingPort;
+} {
+ const calls: Array<{ texts: string[]; task: EmbeddingTask }> = [];
+ return {
+ calls,
+ port: {
+ model,
+ async embed(texts, task) {
+ calls.push({ texts: [...texts], task });
+ return {
+ vectors: texts.map((_, i) => Array.from({ length: dim }, (_, j) => (j === i ? 1 : 0))),
+ model,
+ dim,
+ promptTokens: tokensPerCall,
+ };
+ },
+ },
+ };
+}
+
+const okPort = (port: EmbeddingPort): EmbeddingResolution => ({ ok: true, port });
+
+// ─── the money channel's embedding overlay ─────────────────────────────────
+
+describe("the embedding price overlay (hand-maintained, outside the sync block)", () => {
+ it("prices the known embedding models at their verified input rates", () => {
+ // USD per 1M input tokens, verified against provider pages 2026-09-23.
+ assert.equal(callCost({ inputTokens: 1_000_000, outputTokens: 0 }, "openai:text-embedding-3-small"), 0.02);
+ assert.equal(callCost({ inputTokens: 1_000_000, outputTokens: 0 }, "openai:text-embedding-3-large"), 0.13);
+ assert.equal(callCost({ inputTokens: 1_000_000, outputTokens: 0 }, "google:gemini-embedding-001"), 0.15);
+ assert.equal(callCost({ inputTokens: 1_000_000, outputTokens: 0 }, "google:gemini-embedding-2"), 0.2);
+ assert.equal(callCost({ inputTokens: 1_000_000, outputTokens: 0 }, "openrouter:openai/text-embedding-3-small"), 0.02);
+ });
+
+ it("unknown embedding models stay unpriced (—, never zero), tokens still captured", () => {
+ assert.equal(callCost({ inputTokens: 100, outputTokens: 0 }, "openrouter:mystery/embed"), null);
+ assert.equal(!("openrouter:mystery/embed" in EMBEDDING_PRICES), true);
+ });
+});
+
+// ─── the slug grammar ─────────────────────────────────────────────────────────
+
+describe("parseEmbeddingModelSlug", () => {
+ it("parses the three shipped providers", () => {
+ assert.deepEqual(parseEmbeddingModelSlug("openai:text-embedding-3-small"), { provider: "openai", id: "text-embedding-3-small" });
+ assert.deepEqual(parseEmbeddingModelSlug("openrouter:openai/text-embedding-3-large"), { provider: "openrouter", id: "openai/text-embedding-3-large" });
+ assert.deepEqual(parseEmbeddingModelSlug("google:gemini-embedding-001"), { provider: "google", id: "gemini-embedding-001" });
+ // OpenRouter ids may carry a :free suffix (live catalog fact) — the
+ // provider is the part before the FIRST colon.
+ assert.deepEqual(parseEmbeddingModelSlug("openrouter:liquid/lfm-2.5-embedding-350m:free"), { provider: "openrouter", id: "liquid/lfm-2.5-embedding-350m:free" });
+ });
+
+ it("rejects malformed slugs (no guessing)", () => {
+ assert.equal(parseEmbeddingModelSlug("text-embedding-3-small"), null, "no provider prefix");
+ assert.equal(parseEmbeddingModelSlug("anthropic:embed"), null, "unshipped provider");
+ assert.equal(parseEmbeddingModelSlug("openai:"), null, "empty id");
+ assert.equal(parseEmbeddingModelSlug(":id"), null, "empty provider");
+ });
+});
+
+// ─── resolution: BYOK honesty rules ───────────────────────────────────────────
+
+describe("resolveEmbeddingPortFor", () => {
+ it("null/absent setting = honestly off", () => {
+ for (const slug of [null, undefined, ""]) {
+ const res = resolveEmbeddingPortFor(slug, () => "key");
+ assert.equal(res.ok, false);
+ assert.match((res as { reason: string }).reason, /no embedding model configured/);
+ }
+ });
+
+ it("a set model with no key is an honest error naming the key", () => {
+ const res = resolveEmbeddingPortFor("openai:text-embedding-3-small", () => undefined);
+ assert.equal(res.ok, false);
+ assert.match((res as { reason: string }).reason, /OPENAI_API_KEY/);
+ });
+
+ it("an invalid slug never resolves", () => {
+ const res = resolveEmbeddingPortFor("bedrock:whatever", () => "key");
+ assert.equal(res.ok, false);
+ assert.match((res as { reason: string }).reason, /invalid embedding model slug/);
+ });
+
+ it("a keyed model resolves to its provider adapter", () => {
+ const res = resolveEmbeddingPortFor("openai:text-embedding-3-small", () => "sk-test");
+ assert.equal(res.ok, true);
+ assert.equal((res as { port: EmbeddingPort }).port.model, "openai:text-embedding-3-small");
+ });
+});
+
+// ─── the adapters' wire protocols (injected fetch) ────────────────────────────
+
+describe("openrouterEmbeddingProvider", () => {
+ it("POSTs /api/v1/embeddings with Bearer auth and the task input_type", async () => {
+ const { calls, fetch } = recordingFetch(() =>
+ jsonResponse({ data: [{ embedding: [1, 0], index: 0 }], usage: { prompt_tokens: 42 } }),
+ );
+ const port = openrouterEmbeddingProvider("openrouter:openai/text-embedding-3-small", "k", fetch);
+ const result = await port.embed(["hello"], "document");
+ assert.equal(calls.length, 1);
+ assert.equal(calls[0]!.url, "https://openrouter.ai/api/v1/embeddings");
+ assert.equal((calls[0]!.init.headers as Record).authorization, "Bearer k");
+ assert.deepEqual(JSON.parse(String(calls[0]!.init.body)), {
+ model: "openai/text-embedding-3-small",
+ input: ["hello"],
+ input_type: "search_document",
+ });
+ assert.deepEqual(result.vectors, [[1, 0]]);
+ assert.equal(result.promptTokens, 42);
+
+ await port.embed(["q"], "query");
+ assert.equal((JSON.parse(String(calls[1]!.init.body)) as { input_type: string }).input_type, "search_query");
+ });
+});
+
+describe("openaiEmbeddingProvider", () => {
+ it("POSTs /v1/embeddings, Bearer auth, no task hint; index ordering honored", async () => {
+ const { calls, fetch } = recordingFetch(() =>
+ jsonResponse({
+ data: [{ embedding: [0, 1], index: 1 }, { embedding: [1, 0], index: 0 }],
+ usage: { prompt_tokens: 7, total_tokens: 7 },
+ }),
+ );
+ const port = openaiEmbeddingProvider("openai:text-embedding-3-small", "sk", fetch);
+ const result = await port.embed(["a", "b"], "document");
+ assert.equal(calls[0]!.url, "https://api.openai.com/v1/embeddings");
+ assert.equal((calls[0]!.init.headers as Record).authorization, "Bearer sk");
+ const body = JSON.parse(String(calls[0]!.init.body)) as Record;
+ assert.deepEqual(body.input, ["a", "b"]);
+ assert.equal("input_type" in body, false, "OpenAI takes no task hint");
+ // Rows arrive out of order — the adapter must restore input order.
+ assert.deepEqual(result.vectors, [[1, 0], [0, 1]]);
+ assert.equal(result.promptTokens, 7);
+ });
+});
+
+describe("googleEmbeddingProvider", () => {
+ it("POSTs :batchEmbedContents with x-goog-api-key and per-text taskType", async () => {
+ const { calls, fetch } = recordingFetch((_url, body) => {
+ const n = ((body as { requests?: unknown[] } | null)?.requests ?? []).length;
+ return jsonResponse({ embeddings: Array.from({ length: n }, (_, i) => ({ values: i === 0 ? [1, 0] : [0, 1] })) });
+ });
+ const port = googleEmbeddingProvider("google:gemini-embedding-001", "gk", fetch);
+ const result = await port.embed(["a", "b"], "document");
+ assert.equal(calls[0]!.url, "https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents");
+ assert.equal((calls[0]!.init.headers as Record)["x-goog-api-key"], "gk");
+ assert.deepEqual(JSON.parse(String(calls[0]!.init.body)), {
+ requests: [
+ { model: "models/gemini-embedding-001", content: { parts: [{ text: "a" }] }, taskType: "RETRIEVAL_DOCUMENT" },
+ { model: "models/gemini-embedding-001", content: { parts: [{ text: "b" }] }, taskType: "RETRIEVAL_DOCUMENT" },
+ ],
+ });
+ assert.deepEqual(result.vectors, [[1, 0], [0, 1]]);
+ assert.equal(result.promptTokens, undefined, "batch responses carry no token count we can trust");
+
+ await port.embed(["q"], "query");
+ const second = JSON.parse(String(calls[1]!.init.body)) as { requests: Array<{ taskType: string }> };
+ assert.equal(second.requests[0]!.taskType, "RETRIEVAL_QUERY");
+ });
+
+ it("a short/missing vector is an honest error, never a silent misalignment", async () => {
+ const { fetch } = recordingFetch(() => jsonResponse({ embeddings: [{ values: [1, 0] }] }));
+ const port = googleEmbeddingProvider("google:gemini-embedding-001", "gk", fetch);
+ await assert.rejects(port.embed(["a", "b"], "document"), /1\/2 vectors/);
+ });
+});
+
+describe("adapter error mapping (all providers)", () => {
+ it("HTTP failures become clear Errors carrying the status", async () => {
+ for (const factory of [openrouterEmbeddingProvider, openaiEmbeddingProvider, googleEmbeddingProvider]) {
+ const { fetch } = recordingFetch(() => jsonResponse({ error: { message: "bad key" } }, 401));
+ const port = factory("openai:text-embedding-3-small", "k", fetch);
+ await assert.rejects(port.embed(["x"], "document"), /API 401/);
+ }
+ });
+});
+
+// ─── the post-merge batch (scripted port — the machine's files stay unread) ───
+
+describe("embedNewNodes (the extraction tail)", () => {
+ it("embeds missing nodes, stamps model/dim, records one usage step per API call", async () => {
+ const g = fakeGraphStore();
+ const scripted = scriptedPort("openai:text-embedding-3-small", 2, 120);
+ const result = await embedNewNodes(g.store, () => okPort(scripted.port));
+ assert.deepEqual(result, {
+ embedded: 2,
+ total: 2,
+ usage: {
+ model: "openai:text-embedding-3-small",
+ steps: [
+ { inputTokens: 120, outputTokens: 0, cacheReadTokens: undefined, cacheWriteTokens: undefined, reasoningTokens: undefined },
+ ],
+ },
+ });
+ assert.equal(g.writes.length, 1, "the ledger is written once per batch");
+ assert.equal(g.ledger.model, "openai:text-embedding-3-small");
+ assert.equal(g.ledger.dim, 2);
+ assert.ok(g.ledger.vectors.n1 && g.ledger.vectors.n2);
+ assert.deepEqual(scripted.calls[0]!.texts, ["alpha fact", "beta fact"]);
+ assert.equal(scripted.calls[0]!.task, "document");
+ assert.equal(result.usage?.steps.length, 1);
+ });
+
+ it("a MODEL CHANGE voids the ledger and re-embeds everything", async () => {
+ // The ledger holds a stale-model vector for a node that still exists.
+ const g = fakeGraphStore({ model: "openai:old-embed", vectors: { n1: [9, 9] } });
+ const scripted = scriptedPort("openai:new-embed", 2);
+ const result = await embedNewNodes(g.store, () => okPort(scripted.port));
+ assert.equal(result.embedded, 2, "the stale vector dies — BOTH nodes re-embed");
+ assert.deepEqual(scripted.calls[0]!.texts, ["alpha fact", "beta fact"]);
+ assert.equal(g.ledger.model, "openai:new-embed");
+ assert.ok(!g.ledger.vectors.n1!.every((x, i) => x === [9, 9][i]), "the old vector was replaced");
+ });
+
+ it("null model = info skip: nothing written, nothing embedded, the reason rides the result", async () => {
+ const g = fakeGraphStore({ vectors: { n1: [1, 0] } });
+ const result = await embedNewNodes(g.store, () => ({
+ ok: false,
+ reason: "no embedding model configured (graph.embeddingModel is null)",
+ }));
+ assert.deepEqual(result, { embedded: 0, total: 1, skipped: "no embedding model configured (graph.embeddingModel is null)" });
+ assert.equal(g.writes.length, 0, "a skipped batch never touches the ledger");
+ });
+
+ it("a set model with a missing key is the same skip path (its reason says so)", async () => {
+ const g = fakeGraphStore();
+ const result = await embedNewNodes(g.store, () => ({
+ ok: false,
+ reason: 'embedding model is set to "openai:x" but its OPENAI_API_KEY key is missing',
+ }));
+ assert.match(result.skipped ?? "", /OPENAI_API_KEY/);
+ });
+
+ it("prunes ghost vectors for nodes that no longer exist", async () => {
+ const g = fakeGraphStore({ vectors: { n1: [1, 0], ghost: [0, 1] } });
+ const scripted = scriptedPort(g.ledger.model, 2);
+ const result = await embedNewNodes(g.store, () => okPort(scripted.port));
+ assert.equal(result.embedded, 1, "n1 already has a vector; only n2 embeds");
+ assert.ok(!("ghost" in g.ledger.vectors), "the ghost vector is pruned");
+ });
+
+ it("batches at 32 (a 40-node backfill = two API calls)", async () => {
+ const many: GraphNode[] = Array.from({ length: 40 }, (_, i) => node(`n${i}`, `statement ${i}`));
+ const ledger: EmbeddingsLedger = { model: "m", dim: 2, vectors: {}, clusters: [], updatedAt: "" };
+ const writes: EmbeddingsLedger[] = [];
+ const scripted = scriptedPort("m", 2);
+ const result = await embedNewNodes(
+ {
+ readNodes: () => many,
+ readEmbeddings: () => ledger,
+ writeEmbeddings: (next) => writes.push(next),
+ },
+ () => okPort(scripted.port),
+ );
+ assert.equal(result.embedded, 40);
+ assert.equal(scripted.calls.length, 2);
+ assert.equal(scripted.calls[0]!.texts.length, 32);
+ assert.equal(scripted.calls[1]!.texts.length, 8);
+ assert.equal(writes.length, 1);
+ });
+});
+
+// ─── the federated catalog (scripted keys + fetch) ────────────────────────────
+
+describe("embeddingModelCatalog", () => {
+ it("no keys = empty catalog", async () => {
+ const models = await embeddingModelCatalog(
+ recordingFetch(() => jsonResponse({})).fetch,
+ () => undefined,
+ );
+ assert.deepEqual(models, []);
+ });
+
+ it("federates every keyed provider with its filter rules", async () => {
+ const { fetch, calls } = recordingFetch((url) => {
+ if (url.includes("openrouter.ai/api/v1/embeddings/models")) {
+ return jsonResponse({ data: [{ id: "openai/text-embedding-3-small", name: "Text Embedding 3 Small" }, { id: "other/embed" }] });
+ }
+ if (url.includes("api.openai.com")) {
+ return jsonResponse({ data: [{ id: "text-embedding-3-large" }, { id: "text-embedding-3-small" }, { id: "gpt-6-sol" }] });
+ }
+ if (url.includes("generativelanguage")) {
+ return jsonResponse({
+ models: [
+ { name: "models/gemini-embedding-001", displayName: "Gemini Embedding", supportedGenerationMethods: ["embedContent", "generateContent"] },
+ { name: "models/gemini-6-pro", supportedGenerationMethods: ["generateContent"] },
+ ],
+ });
+ }
+ return jsonResponse({});
+ });
+ const models = await embeddingModelCatalog(fetch, (id) => (id === "OPENROUTER_API_KEY" || id === "OPENAI_API_KEY" || id === "GEMINI_API_KEY" ? "k" : undefined));
+ assert.equal(calls[0]!.url, "https://openrouter.ai/api/v1/embeddings/models?limit=500", "the real catalog path (the inverse 404s — verified live)");
+ assert.deepEqual(models, [
+ { id: "openrouter:openai/text-embedding-3-small", name: "Text Embedding 3 Small" },
+ { id: "openrouter:other/embed", name: "other/embed" },
+ { id: "openai:text-embedding-3-large", name: "text-embedding-3-large" },
+ { id: "openai:text-embedding-3-small", name: "text-embedding-3-small" },
+ { id: "google:gemini-embedding-001", name: "Gemini Embedding" },
+ ]);
+ });
+
+ it("a failing provider never poisons the rest", async () => {
+ const { fetch } = recordingFetch((url) => {
+ if (url.includes("openrouter.ai")) return jsonResponse({}, 500); // their side broke
+ if (url.includes("api.openai.com")) return jsonResponse({ data: [{ id: "text-embedding-3-small" }] });
+ return jsonResponse({});
+ });
+ const models = await embeddingModelCatalog(fetch, (id) => (id === "OPENROUTER_API_KEY" || id === "OPENAI_API_KEY" ? "k" : undefined));
+ assert.deepEqual(models, [{ id: "openai:text-embedding-3-small", name: "text-embedding-3-small" }]);
+ });
+});
\ No newline at end of file
diff --git a/tests/graph-context-job.test.ts b/tests/graph-context-job.test.ts
index 8cad3ec..ec99a4e 100644
--- a/tests/graph-context-job.test.ts
+++ b/tests/graph-context-job.test.ts
@@ -15,7 +15,7 @@ import { after, describe, it } from "node:test";
import { deliverJobResult, setTurnRunner } from "../src/server/jobs.ts";
import { abortJob } from "../src/server/jobs.ts";
import { persistTurn } from "../src/server/turn-service.ts";
-import { startGraphContextInjection, runGraphContextJob, type GraphContextDeps } from "../src/agent/subagents/graph-context.ts";
+import { startGraphContextInjection, runGraphContextJob, type GraphContextDeps, type GraphContextEmbedder } from "../src/agent/subagents/graph-context.ts";
import { chatStore } from "../src/store/chats.ts";
import { jobStore } from "../src/store/jobs.ts";
import { PATHS } from "../config.ts";
@@ -104,17 +104,18 @@ function newTopicChat(label: string, settings?: Record): { id:
return { id: chat.id };
}
-/** The scripted embedder: deterministic query vectors, recorded topics. */
+/** The scripted embedder: deterministic query vectors, recorded topics.
+ * Wave 6 shape: the query carries its (absent) prompt-token count; the
+ * resolver seam wraps the static fake (fresh resolution per run). */
function fakeEmbedder(vec: number[] = unit(0)) {
const topics: string[] = [];
return {
topics,
embedder: {
model: "test-embed",
- dim: 8,
embedQuery: async (text: string) => {
topics.push(text);
- return vec;
+ return { vector: vec, promptTokens: undefined };
},
},
};
@@ -122,10 +123,10 @@ function fakeEmbedder(vec: number[] = unit(0)) {
function deps(
graph: Pick,
- embedder: GraphContextDeps["embedder"],
+ embedder: GraphContextEmbedder,
deliver: (steer: SteerMessage) => Promise,
): GraphContextDeps {
- return { chatStore, jobStore, graphStore: graph, embedder, deliver };
+ return { chatStore, jobStore, graphStore: graph, embedder: () => embedder, deliver };
}
describe("startGraphContextInjection — the one-shot gates", () => {
@@ -205,7 +206,9 @@ describe("runGraphContextJob — failure modes are honest errors, never phantom
trackChat(chat.id);
const job = jobStore.createJob({ kind: "graph-context", chatId, toolCallId: `ctx_${chatId}` });
trackJob(job.id);
- // Ledger stamped with a DIFFERENT model than the embedder.
+ // Ledger stamped with a DIFFERENT model than the embedder (wave 6:
+ // staleness is the model identity — dim is checked against the
+ // served vector below).
const d = deps(fakeGraphStore({ vectors: { n1: unit(0) }, model: "other-model" }), fakeEmbedder().embedder, async () => {});
await runGraphContextJob(d, job.id);
const got = jobStore.getJob(job.id)!;
@@ -280,8 +283,7 @@ describe("the injection + the wake pipeline (end to end, fake turn runner)", ()
});
const embedder = {
model: "test-embed",
- dim: 8,
- embedQuery: () => hanging.then(() => unit(0)),
+ embedQuery: () => hanging.then(() => ({ vector: unit(0), promptTokens: undefined })),
};
const fired: number[] = [];
setTurnRunner(async () => {
diff --git a/tests/headless-png.test.ts b/tests/headless-png.test.ts
index 1fa5b5d..307d988 100644
--- a/tests/headless-png.test.ts
+++ b/tests/headless-png.test.ts
@@ -11,9 +11,12 @@ import { providerSafePng } from "../src/agent/subagents/headless.ts";
* passed. providerSafePng merges the split back into the canonical ONE-IDAT
* form (PNG spec: the IDAT chunks are an arbitrary split of ONE zlib stream —
* the merged form carries the byte-identical stream). Pure Node on purpose:
- * the process already loads transformers' nested sharp/libvips; a second copy
- * (root sharp) triggered macOS's duplicate-libvips ObjC warning. These tests
- * pin the property with no native deps at all.
+ * historically the process already carried a native image lib via
+ * @huggingface/transformers' nested sharp/libvips, and a second copy (root
+ * sharp) triggered macOS's duplicate-libvips ObjC warning — the transformers
+ * embedder died with wave 6 (2026-09-23) but the no-native-deps rule lives
+ * on: app code carries no image library. These tests pin the property with
+ * no native deps at all.
*/
// ── a tiny PNG toolchain (spec-level, no image library) ─────────────────────
diff --git a/tests/settings-body.test.ts b/tests/settings-body.test.ts
index 5660cea..fa69652 100644
--- a/tests/settings-body.test.ts
+++ b/tests/settings-body.test.ts
@@ -156,6 +156,30 @@ describe("parseGraphSettingsBody", () => {
const r = parseGraphSettingsBody({ enabled: false, clustering: true, labeling: true });
assert.ok(r.ok);
});
+
+ it("embeddingModel (wave 6): null or a shipped-provider slug; anything else is a 400", () => {
+ const nulled = parseGraphSettingsBody({ embeddingModel: null });
+ assert.ok(nulled.ok);
+ assert.deepEqual(nulled.settings, { embeddingModel: null });
+ for (const slug of [
+ "openai:text-embedding-3-small",
+ "openrouter:openai/text-embedding-3-large",
+ "google:gemini-embedding-001",
+ // OpenRouter ids may carry a :free-style suffix — the provider is
+ // the part before the FIRST colon (live catalog fact, 2026-09-23).
+ "openrouter:liquid/lfm-2.5-embedding-350m:free",
+ ]) {
+ const r = parseGraphSettingsBody({ embeddingModel: slug });
+ assert.ok(r.ok, slug);
+ assert.deepEqual(r.settings, { embeddingModel: slug });
+ }
+ // Bad shapes never become a live model.
+ assert.equal(parseGraphSettingsBody({ embeddingModel: "text-embedding-3-small" }).ok, false, "no provider prefix");
+ assert.equal(parseGraphSettingsBody({ embeddingModel: "bedrock:whatever" }).ok, false, "unshipped provider");
+ assert.equal(parseGraphSettingsBody({ embeddingModel: "openai:" }).ok, false, "empty id");
+ assert.equal(parseGraphSettingsBody({ embeddingModel: 42 }).ok, false, "non-string");
+ assert.equal(parseGraphSettingsBody({ embeddingModel: "openai:has spaces" }).ok, false, "whitespace id");
+ });
});
describe("SETTINGS_SECTIONS (the route's section map)", () => {
diff --git a/tests/settings-resolution.test.ts b/tests/settings-resolution.test.ts
index 6efe0d8..f9eaa68 100644
--- a/tests/settings-resolution.test.ts
+++ b/tests/settings-resolution.test.ts
@@ -42,7 +42,7 @@ describe("resolveSettings", () => {
assert.equal(eff.appearance.proseFontSize, 16);
assert.equal(eff.appearance.sessionNameSerif, true);
assert.equal(eff.appearance.mdRendering.headingWeight, 900);
- assert.deepEqual(eff.graph, { enabled: true, embedding: true, clustering: true, labeling: true });
+ assert.deepEqual(eff.graph, { enabled: true, embedding: true, clustering: true, labeling: true, embeddingModel: null }); // BYOK wave 6: no factory embedding model
});
it("explicit record values win over every factory default", () => {
@@ -77,7 +77,7 @@ describe("resolveSettings", () => {
assert.equal(eff.appearance.mdRendering.headingWeight, 600);
// graph: enabled=false explicit; absent rungs stay factory-on (stored
// but inert — the ladder grays them out in the UI).
- assert.deepEqual(eff.graph, { enabled: false, embedding: true, clustering: true, labeling: true });
+ assert.deepEqual(eff.graph, { enabled: false, embedding: true, clustering: true, labeling: true, embeddingModel: null }); // wave 6: unset embeddingModel resolves to the null floor
});
it("partial role override: thinkingLevel alone borrows the SLOT's model (or nothing, without one)", () => {
@@ -224,15 +224,15 @@ describe("resolveConversationSpec (the turn gate's chain)", () => {
describe("the graph channel gates (the wave's seam honoring)", () => {
it("WRITE channel (extraction): dies with the master switch only", () => {
- assert.equal(extractionEnabled({ enabled: true, embedding: true, clustering: true, labeling: true }), true);
- assert.equal(extractionEnabled({ enabled: true, embedding: false, clustering: false, labeling: false }), true);
- assert.equal(extractionEnabled({ enabled: false, embedding: true, clustering: true, labeling: true }), false);
+ assert.equal(extractionEnabled({ enabled: true, embedding: true, clustering: true, labeling: true, embeddingModel: null }), true);
+ assert.equal(extractionEnabled({ enabled: true, embedding: false, clustering: false, labeling: false, embeddingModel: null }), true);
+ assert.equal(extractionEnabled({ enabled: false, embedding: true, clustering: true, labeling: true, embeddingModel: null }), false);
});
it("READ channel (graph-context): needs master AND the embedding rung", () => {
- assert.equal(graphContextEnabled({ enabled: true, embedding: true, clustering: false, labeling: false }), true);
- assert.equal(graphContextEnabled({ enabled: true, embedding: false, clustering: true, labeling: true }), false);
- assert.equal(graphContextEnabled({ enabled: false, embedding: true, clustering: true, labeling: true }), false);
+ assert.equal(graphContextEnabled({ enabled: true, embedding: true, clustering: false, labeling: false, embeddingModel: null }), true);
+ assert.equal(graphContextEnabled({ enabled: true, embedding: false, clustering: true, labeling: true, embeddingModel: null }), false);
+ assert.equal(graphContextEnabled({ enabled: false, embedding: true, clustering: true, labeling: true, embeddingModel: null }), false);
});
it("both gates ride resolveSettings' factory defaults (all on → both open)", () => {
diff --git a/tests/settings.test.ts b/tests/settings.test.ts
index 7f8fffa..71c29c7 100644
--- a/tests/settings.test.ts
+++ b/tests/settings.test.ts
@@ -21,7 +21,7 @@ describe("FACTORY_SETTINGS (the compiled factory layer)", () => {
it("pins the owner-decided defaults", () => {
assert.equal(CURRENT_SETTINGS_VERSION, 1);
assert.deepEqual(FACTORY_SETTINGS.general, { autoUpdate: true });
- assert.deepEqual(FACTORY_SETTINGS.graph, { enabled: true, embedding: true, clustering: true, labeling: true });
+ assert.deepEqual(FACTORY_SETTINGS.graph, { enabled: true, embedding: true, clustering: true, labeling: true, embeddingModel: null }); // BYOK wave 6: no factory embedding model
const a = FACTORY_SETTINGS.appearance;
assert.equal(a.mode, "dark");
assert.equal(a.background, null); // the mode's own default, not a factory hex