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
+6 -3
View File
@@ -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) ─────────────────────