Part 1 — the ledger + remnants interlude (master-dispatched, owner ruling
2026-09-23: nothing configures the graph beyond chat models):
- The embedding ledger surface is gone: readEmbeddings/writeEmbeddings
ports, the EmbeddingsLedger contract, EMBEDDINGS_FILE (config, store
impls, graphRevision source list), and graph-deletion's vector-pruning
step. On-disk data files stay untouched (inert history).
- The extraction embedder seam dies wholesale: ExtractionPipelineDeps
drops the embedder dep (chat-handler + backfill/import-notes stubs go
with it), the 'embedding' phase leaves ExtractionPhase, the usage
capture/persist helpers die, and stages.embedding leaves
ExtractionRunUsage (historical records keep their shape — reads are
lenient). Extraction is two stages again, like the local-embedder era.
- Consumer-less remnants: latestQuizOutcomes + QUIZ_EVENT_KINDS,
clusterContentId, matchClusterLabelings + Community + ClusterLabeling,
the readClusterLabels/appendClusterLabel port seams + store impls +
LEDGER_FILES.clusterLabels. NamingRunUsage/readNamingRuns STAY
(standing ruling — the cost pill renders historical naming spend);
clusterHue + MIN_CLUSTER_SIZE stay (live).
- The 'labeler' role dies: BACKGROUND_MODEL_ROLES, ROLE_SLOT, ModelRole,
the catalog pin projections, and the UI roster strings. RolePins keys
shrink with the union.
The notes birth fallback (owner-approved 2026-09-23, surfaced by the
interlude's live smoke: production notes imports create provenance-EMPTY
nodes (importNotes passes messages: null — the file's anchor is the
mapping line), so the provenance-only birth rule left every imported
file unclustered and invisible to the prober's session list, against the
locked file-birth ruling. A provenance-empty node now births under its
FIRST mapping line's chatId (ledger order); only notes-born nodes ever
hit the fallback (chat nodes always carry provenance; a re-encountered
node's link-append re-opens the provenance rule). Deletion-safe: mapping
lines of deleted chats are stripped alongside their provenance.
Live-verified on port 3004: a fresh notes import clusters under its
src_ id with the file path as the label, end to end with no embedder.
845/845 tests, typecheck/lint/build green.
EOF
)
The owner's wave-7 ruling: embeddings die entirely (git history is the
stash); clustering is birth-session derived (chunk A, 950ddfd), labels
are session names, and the prober's graph tools replace injection.
- settings: GraphSettings collapses to { enabled } — embedding,
embeddingModel, clustering, labeling all die. Migration story: stale
record keys are UNREAD and dropped by the sanitizer's reconstruction;
the next graph-section PUT (replace-whole) persists the collapsed
shape. The settings-panel GraphSection renders one master row.
- deleted: src/server/embeddings.ts (adapters, resolveEmbeddingPortFor,
embedNewNodes, embeddingPort, embeddingModelCatalog), the
GET /api/models/embeddings route, scripts/embed-graph.ts, tests for
all three, and the /api/models/embeddings picker surfaces in the UI.
- prices: EMBEDDING_PRICES overlay + callCost fallback die. cost-summary:
the embedding stage fold dies — back to three stages (extraction/
audit/naming) per the owner ruling; historical stages.embedding spend
in old run records is simply not displayed.
- ports: EmbeddingPort/EmbeddingResult/EmbeddingTask die. The embeddings
LEDGER surface (readEmbeddings/writeEmbeddings + EmbeddingsLedger +
EMBEDDINGS_FILE + graph-deletion's vector pruning) STAYS — inert data,
kept only so graph-context.ts compiles until Teacher's pass removes
it; the seam dies in the follow-up interlude.
- chat-handler (approved cross-lane unwiring, wave-6 precedent): the
extraction pipeline's embedder becomes a documented no-op (nothing
embedded, nothing spent, ledger untouched) until Teacher's pass
removes the phase; the graph-context injection dispatch gate, the
graphContext deps wiring, the setContextRespawn seam, and
turn-service's triggerGraphContext are gone — injection is dead
code pending Teacher's file deletions.
- scripts: backfill-graph/import-notes pass the same no-op embedder;
replay-layout derives clusters from birthSessionPartition (the same
partition the real settle uses) instead of the embeddings ledger.
- settings-body: parseGraphSettingsBody reads the master switch only —
old-shape keys in a body are ignored, not rejected; bad shapes 400.
- next.config: the @huggingface tracing-exclusion guards die with the
last reference.
Cross-lane flags: extraction.ts/graph-context.ts keep stale embed
comments + the embed phase until Teacher's full pass (their parallel
interlude owns those files — zero overlap kept by design);
semantic-clusters.ts + its test stay one more round (extraction.test.ts,
Teacher's file, still imports it — they delete it with the namer cases);
ChatSettings.graphContextTokens + the graph-context-control UI stay
until Teacher+UI.
Gates: tsc clean, eslint clean, 885/885 tests, build compiles.
Live-verified on the port-3004 dev tree: PUT /api/settings/graph with
dead keys collapses on write, bad shapes 400, GET reads {enabled: true},
/api/models/embeddings 404s.
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).
amosblomqvist