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:
amosblomqvist
+8
-45
@@ -38,7 +38,7 @@
|
||||
* adapters in.
|
||||
*/
|
||||
|
||||
import { createHash, randomBytes } from "node:crypto";
|
||||
import { randomBytes } from "node:crypto";
|
||||
import { isToolUIPart, type UIMessage } from "ai";
|
||||
import type { CoverageEntry } from "./contracts/graph.ts";
|
||||
import type {
|
||||
@@ -54,7 +54,7 @@ import type {
|
||||
UnderstandingLevel,
|
||||
} from "./contracts.ts";
|
||||
import { MIN_CLUSTER_SIZE } from "./clusters.ts";
|
||||
import { birthSessionPartition } from "./session-clusters.ts";
|
||||
import { birthMappingIndex, birthSessionOf, birthSessionPartition } from "./session-clusters.ts";
|
||||
import type { QuestionAnswerData } from "./question-core.ts";
|
||||
import type { ChatStore, GraphStore } from "./ports.ts";
|
||||
|
||||
@@ -333,16 +333,6 @@ function quizEvent(
|
||||
|
||||
// ─── derivation (reads only — everything below is recomputable) ─────────────
|
||||
|
||||
/** The content identity of a community: "clu_" + sha256 of the sorted
|
||||
* member ids (12 hex). Deterministic — the same member set always mints
|
||||
* the same id — so re-naming races and idempotent re-runs dedupe at the
|
||||
* store seam (appendClusterLabel). Lives here (server-only core), not in
|
||||
* clusters.ts, because clusters.ts is barrel-exported and must stay
|
||||
* browser-safe (no node:crypto). */
|
||||
export function clusterContentId(members: readonly string[]): string {
|
||||
return "clu_" + createHash("sha256").update([...members].sort().join("\n")).digest("hex").slice(0, 12);
|
||||
}
|
||||
|
||||
export interface DerivedGraph {
|
||||
nodes: GraphNode[];
|
||||
edges: GraphEdge[];
|
||||
@@ -394,34 +384,6 @@ export function getGraph(graphStore: GraphStore): DerivedGraph {
|
||||
return { nodes: [...byId.values()], edges: merged, events: graphStore.readEvents() };
|
||||
}
|
||||
|
||||
const QUIZ_EVENT_KINDS: ReadonlySet<string> = new Set(["correct", "miss", "dont-know"]);
|
||||
|
||||
/**
|
||||
* The latest quiz outcome per node — a raw EVENT FACT, not a node state
|
||||
* (the transitional node-state classes were removed 2026-09-08: nothing
|
||||
* colors nodes by quiz results anymore). Its last consumer, the
|
||||
* graph-as-context selection, died in wave 7 (the injection is gone —
|
||||
* the prober reads its map through tools now); the event fact stays as
|
||||
* raw ledger truth. Nodes with no quiz events have no entry.
|
||||
*/
|
||||
export function latestQuizOutcomes(nodes: GraphNode[], events: LedgerEvent[]): Map<string, LedgerEventKind> {
|
||||
const latest = new Map<string, { at: string; kind: LedgerEventKind; index: number }>();
|
||||
events.forEach((event, index) => {
|
||||
if (event.nodeId === null) return;
|
||||
if (!QUIZ_EVENT_KINDS.has(event.kind)) return;
|
||||
const current = latest.get(event.nodeId);
|
||||
if (!current || event.at > current.at || (event.at === current.at && index > current.index)) {
|
||||
latest.set(event.nodeId, { at: event.at, kind: event.kind, index });
|
||||
}
|
||||
});
|
||||
const out = new Map<string, LedgerEventKind>();
|
||||
for (const node of nodes) {
|
||||
const last = latest.get(node.id);
|
||||
if (last) out.set(node.id, last.kind);
|
||||
}
|
||||
return out;
|
||||
}
|
||||
|
||||
// ─── the /api/graph payload ──────────────────────────────────────────────────
|
||||
|
||||
/** Everything the home graph view needs, in one fetch (shape: contracts). */
|
||||
@@ -505,7 +467,7 @@ export function graphSnapshot(deps: GraphDeps): GraphSnapshot {
|
||||
// presentation rule (a region needs >= 3 propositions for a hull). A
|
||||
// birth session whose record is gone (deleted chat) keeps its members
|
||||
// but renders unlabeled — honest, never guessed.
|
||||
const communities = birthSessionPartition(nodes);
|
||||
const communities = birthSessionPartition(nodes, deps.graphStore.readMappings());
|
||||
const clusters: Cluster[] = communities
|
||||
.filter((community) => community.members.length >= MIN_CLUSTER_SIZE)
|
||||
.map((community) => ({
|
||||
@@ -562,7 +524,9 @@ export interface GraphSessionEntry {
|
||||
* first (undatable records sink, in stable id order). */
|
||||
export function graphSessionIndex(deps: GraphDeps): GraphSessionEntry[] {
|
||||
const counts = new Map<string, number>();
|
||||
for (const cluster of birthSessionPartition(getGraph(deps.graphStore).nodes)) {
|
||||
const born = getGraph(deps.graphStore);
|
||||
const mappingFallback = birthMappingIndex(deps.graphStore.readMappings());
|
||||
for (const cluster of birthSessionPartition(born.nodes, deps.graphStore.readMappings())) {
|
||||
counts.set(cluster.id, cluster.members.length);
|
||||
}
|
||||
const chats = new Map(deps.chatStore.listChats().map((chat) => [chat.id, chat]));
|
||||
@@ -619,9 +583,8 @@ export interface GraphSessionProposition {
|
||||
* ledger order (the same tie rule the snapshot's nodeObservations
|
||||
* uses). Members sorted by node id — deterministic. */
|
||||
export function graphSessionPropositions(deps: GraphDeps, sessionId: string): GraphSessionProposition[] {
|
||||
const born = getGraph(deps.graphStore).nodes.filter(
|
||||
(node) => node.provenance[0] !== undefined && node.provenance[0]!.chatId === sessionId,
|
||||
);
|
||||
const mappingFallback = birthMappingIndex(deps.graphStore.readMappings());
|
||||
const born = getGraph(deps.graphStore).nodes.filter((node) => birthSessionOf(node, mappingFallback) === sessionId);
|
||||
const latest = new Map<string, { at: string; note: string; index: number }>();
|
||||
deps.graphStore.readEvents().forEach((event, index) => {
|
||||
if (event.kind !== "observation" || event.nodeId === null || event.chatId !== sessionId) return;
|
||||
|
||||
Reference in New Issue
Block a user