Wave 7 close-out: the embedding ledger seam dies; notes birth via mapping lines
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 )
This commit is contained in:
+8
-66
@@ -1,73 +1,16 @@
|
||||
/**
|
||||
* Community detection tests (vision §1, DECIDED 2026-09-13) — pure
|
||||
* structural Louvain over follows+supports, deterministic via seed.
|
||||
* Assertions are on SHAPE and MEMBER SETS, never community indices
|
||||
* (indices reshuffle; member sets are what labelings key to).
|
||||
* Cluster presentation-rule tests. Wave 7 killed the semantic detection
|
||||
* AND the LLM label matcher (birth-session clusters, session-name labels —
|
||||
* core/session-clusters.ts has its own suite); what remains pinned here
|
||||
* is the render threshold and the hull-color spread the UI leans on.
|
||||
*/
|
||||
import { strict as assert } from "node:assert";
|
||||
import { describe, test } from "node:test";
|
||||
import { matchClusterLabelings, MIN_CLUSTER_SIZE, type Community } from "../src/core/clusters.ts";
|
||||
import { MIN_CLUSTER_SIZE } from "../src/core/clusters.ts";
|
||||
import { clusterHue } from "../components/cluster-geometry.ts";
|
||||
import type { ClusterLabeling } from "../src/core/contracts.ts";
|
||||
|
||||
const ids = (n: number, prefix = "n") => [...Array(n).keys()].map((i) => `${prefix}${i}`);
|
||||
|
||||
/** A clique on the given ids. */
|
||||
const clique = (nodeIds: string[]) =>
|
||||
nodeIds.flatMap((a, i) => nodeIds.slice(i + 1).map((b) => ({ from: a, to: b })));
|
||||
|
||||
const labeling = (id: string, core: string[], createdAt = "2026-09-01T00:00:00.000Z"): ClusterLabeling => ({
|
||||
id,
|
||||
label: `label-${id}`,
|
||||
core,
|
||||
createdAt,
|
||||
});
|
||||
|
||||
describe("matchClusterLabelings", () => {
|
||||
test("claims a labeling while at least half its core survives in the community", () => {
|
||||
const community: Community = { members: ["a", "b", "c", "d", "e"] };
|
||||
const records = [labeling("clu_1", ["a", "b", "x", "y"])]; // 2 of 4 survive — exactly half
|
||||
const [claim] = matchClusterLabelings([community], records);
|
||||
assert.equal(claim?.id, "clu_1");
|
||||
// One fewer survivor: under half → relabel.
|
||||
const [dead] = matchClusterLabelings([{ members: ["a", "c", "d", "e", "f"] }], records);
|
||||
assert.equal(dead, null);
|
||||
});
|
||||
|
||||
test("single successor: a split core keeps its label in only one community", () => {
|
||||
const records = [labeling("clu_1", ["a", "b", "c", "d"])];
|
||||
const left: Community = { members: ["a", "b", "z"] }; // 2 of 4 — half
|
||||
const right: Community = { members: ["c", "d", "w"] }; // 2 of 4 — half
|
||||
// Tie: larger overlap wins; equal → both eligible, greedy takes first come.
|
||||
const claims = matchClusterLabelings([left, right], records);
|
||||
const claimed = claims.filter((c) => c !== null);
|
||||
assert.equal(claimed.length, 1);
|
||||
assert.equal(claimed[0]?.id, "clu_1");
|
||||
});
|
||||
|
||||
test("greedy: the best-overlapping community wins the record", () => {
|
||||
const records = [labeling("clu_1", ["a", "b", "c", "d"])];
|
||||
const weak: Community = { members: ["a", "b", "q", "r", "s"] }; // 2/4
|
||||
const strong: Community = { members: ["a", "b", "c", "x", "y"] }; // 3/4
|
||||
const claims = matchClusterLabelings([weak, strong], records);
|
||||
assert.equal(claims[0], null);
|
||||
assert.equal(claims[1]?.id, "clu_1");
|
||||
});
|
||||
|
||||
test("one record per community; newest record breaks ties", () => {
|
||||
const oldR = labeling("clu_old", ["a", "b"], "2026-09-01T00:00:00.000Z");
|
||||
const newR = labeling("clu_new", ["a", "b"], "2026-09-02T00:00:00.000Z");
|
||||
const community: Community = { members: ["a", "b", "c"] };
|
||||
const [claim] = matchClusterLabelings([community], [oldR, newR]);
|
||||
assert.equal(claim?.id, "clu_new");
|
||||
});
|
||||
|
||||
test("no labelings: every community unclaimed; empty communities array ok", () => {
|
||||
assert.deepEqual(matchClusterLabelings([{ members: ["a", "b"] }], []), [null]);
|
||||
assert.deepEqual(matchClusterLabelings([], [labeling("clu_1", ["a"])]), []);
|
||||
});
|
||||
|
||||
test("MIN_CLUSTER_SIZE is 3 (the render/naming threshold)", () => {
|
||||
describe("MIN_CLUSTER_SIZE", () => {
|
||||
test("is 3 (the render threshold — below this, no hull)", () => {
|
||||
assert.equal(MIN_CLUSTER_SIZE, 3);
|
||||
});
|
||||
});
|
||||
@@ -81,5 +24,4 @@ describe("clusterHue", () => {
|
||||
assert.ok(hues.size > 20, `expected spread, got ${hues.size} distinct hues for 40 ids`);
|
||||
for (const h of hues) assert.ok(h >= 0 && h < 360);
|
||||
});
|
||||
});
|
||||
|
||||
});
|
||||
Reference in New Issue
Block a user