Files
learnharness/package.json
T
amosblomqvist f5edc7f0a5 Semantic topic clusters: local embeddings replace Louvain
Louvain only ever found the reasoning chains (the graph is disconnected
by nature — every connected component became its own cluster) and
edge-orphans could never join anything. Clusters are now RELATED TOPICS:
propositions grouped by meaning.

- Embedder (src/server/embeddings.ts): in-process transformers.js v4
  running EmbeddingGemma-300M q8 (MTEB 68.4, ~300MB one-time download),
  MRL-truncated to 512d, "title: none | text:" prefix on 100% of inputs,
  L2-normalized so cosine = dot. Model/dim mismatch voids the ledger
  (full re-embed). Injected at the composition root — the agent layer
  never imports the server layer (architecture law).
- Ledger (data/graph/embeddings.json): model + dim + vectors + the
  persisted cluster partition. Reclustering runs at the END of every
  embedding batch (post-merge hook, both front doors) — never per read
  (the agglomerative pass is ~1.5s at 338 nodes).
- Clustering (src/core/semantic-clusters.ts): hand-rolled average-linkage
  agglomerative over cosine (npm HDBSCAN is an abandoned alpha). Stragglers
  stay singletons by default; attachStragglers is the all-in toggle.
  Threshold 0.60 swept on the real graph: 26 topics, 74/90 edge-orphans
  land in real topics, 10 stragglers.
- Consumers (snapshot, settle, namer, replay) read the persisted
  partition — one cluster concept everywhere; core-survival label
  matching unchanged (20/26 topics kept labels).
- Louvain retired: detectCommunities + graphology* deps deleted
  (graphology-louvain had leaked into the client bundle since the
  clusters wave); scripts/bench-graph.ts (dead FA2 bench) removed.
- scripts/embed-graph.ts: backfill/cold-start (338 nodes in 150s
  including the one-time model download).
2026-09-13 14:29:16 +03:00

75 lines
2.1 KiB
JSON

{
"name": "learning-harness",
"version": "0.2.0",
"description": "A standalone learning harness: a teacher agent (AI SDK) with quiz/ask interactions, session artifacts, and a derived knowledge graph of what the learner knows.",
"type": "module",
"private": true,
"scripts": {
"dev": "next dev",
"build": "next build",
"start": "next start",
"test": "NODE_ENV=test tsx --test tests/*.test.ts tests/*.test.tsx",
"lint": "eslint .",
"typecheck": "tsc --noEmit"
},
"dependencies": {
"@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",
"@streamdown/cjk": "^1.0.3",
"@streamdown/code": "^1.1.1",
"@streamdown/math": "^1.0.2",
"@streamdown/mermaid": "^1.0.2",
"@xyflow/react": "^12.11.3",
"ai": "^7.0.76",
"ansi-to-react": "^6.2.6",
"class-variance-authority": "^0.7.1",
"clsx": "^2.1.1",
"cmdk": "^1.1.1",
"d3-force": "^3.0.0",
"d3-selection": "^3.0.0",
"d3-zoom": "^3.0.0",
"embla-carousel-react": "^8.6.0",
"katex": "^0.16.47",
"linkedom": "^0.18.13",
"lucide-react": "^1.33.0",
"media-chrome": "^4.19.2",
"mermaid": "^11.17.0",
"motion": "^13.1.1",
"nanoid": "^6.0.1",
"next": "^16.3.2",
"next-themes": "^0.4.6",
"puppeteer-core": "^25.8.0",
"radix-ui": "^1.6.7",
"react": "^19.2.8",
"react-dom": "^19.2.8",
"react-jsx-parser": "^2.4.1",
"remark-breaks": "^4.0.0",
"streamdown": "^2.5.0",
"tailwind-merge": "^3.6.0",
"tokenlens": "^1.3.1",
"turndown": "^7.2.4",
"use-stick-to-bottom": "^1.1.6",
"zod": "^4.4.3"
},
"devDependencies": {
"@next/eslint-plugin-next": "^16.3.3",
"@tailwindcss/postcss": "^4.3.3",
"@types/node": "^24.0.0",
"@types/react": "^19.2.18",
"@types/react-dom": "^19.2.4",
"@types/turndown": "^5.0.6",
"@typescript-eslint/parser": "^8.68.0",
"eslint": "^9.39.5",
"eslint-import-resolver-typescript": "^4.4.5",
"eslint-plugin-import": "^2.32.0",
"tailwindcss": "^4.3.3",
"tsx": "^4.19.0",
"typescript": "^5.6.0"
}
}