BYOK provider embeddings (wave 6 chunk B): kill local transformers

Replace the @huggingface/transformers local embedder (~316MB ONNX cache)
with an EmbeddingPort seam: graph.embeddingModel (nullable "provider:id"
slug) selects an OpenRouter/OpenAI/Gemini adapter, resolved fresh per
call from settings + the auth store so key rotations land immediately.

- src/server/embeddings.ts rewritten: slug grammar, injected-fetch
  adapters (OpenRouter input_type, Gemini taskType batching, OpenAI
  index-ordered rows), honest resolution (null = skip-with-info, set
  model with missing key = honest error), embedNewNodes with model-change
  re-embed wipe + ghost pruning + usage steps, federated catalog
  (OpenRouter /api/v1/embeddings/models — VERIFIED live, the inverse
  path 404s; OpenAI text-embedding- filter; Gemini embedContent filter).
- GET /api/models/embeddings: federated catalog, empty when no keys.
- Extraction tail records stages.embedding usage into the run's money
  channel; EMBEDDING_PRICES overlay in core/prices.ts (outside the
  sync-generated block), callCost falls back to it; cost-summary folds
  the fourth stage; graph-context injection resolves its embedder per
  run, fails honestly when unconfigured, records query tokens.
- Settings: GraphSettings.embeddingModel (null factory), section parser
  validates slug shape (id may contain colons — OpenRouter :free
  suffixes, live catalog fact).
- Removal: @huggingface/transformers uninstalled, PATHS.modelCache and
  onnx tracing entries deleted, @huggingface tracing-excludes guard
  added, stale sharp/libvips comments updated to historical.

Live-verified on port 3004: catalog federates 36 rows (33 OpenRouter +
3 OpenAI), embedNewNodes embedded 10 nodes via the free liquid/lfm-2.5
model (dim 1024, 435 prompt tokens, 1 call, $0), settings PUT rejects
bad slugs with 400.

Gates: typecheck, lint, 895/895 tests, build.
This commit is contained in:
amosblomqvist
2026-09-23 03:53:57 +03:00
parent a6338511d3
commit 0a4a9a11de
29 changed files with 1233 additions and 841 deletions
+7 -8
View File
@@ -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
],
};