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:
@@ -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<number | null> = [extDollars, audDollars, embDollars];
|
||||
const runDollars = allStages.every((d) => d === null)
|
||||
? null
|
||||
: allStages.reduce<number>((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,
|
||||
};
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user