Birth-session clustering + the prober graph-tools data seam (wave 7 chunk A)
Embeddings are dying (chunk B removes the machinery); the clusters they
used to carry become the session that created them — derived on read.
- New src/core/session-clusters.ts: birthSessionPartition groups merged
nodes by their FIRST SURVIVING provenance point's chatId (owner-locked
2026-09-23). Deletion is self-healing by construction: stripped-birth
survivors re-attribute to their earliest remaining contributor, and
empty-provenance nodes stay unclustered. Notes imports are birth-sessions
too (owner ruling) — their label is the file path.
- graphSnapshot: clusters = the birth partition filtered >= MIN_CLUSTER_SIZE
(the hull presentation rule), id = session id, label = session name (chat
title / file path; a deleted record renders unlabeled). The persisted
cluster-labelings join dies; no LLM naming pass needed anymore.
- settleGraphLayout derives the same partition from readNodes — drops its
readEmbeddings dep. One cluster concept everywhere.
- Prober data seam (core/graph.ts, pure ports-driven like the snapshot):
graphSessionIndex (every birth session: id, name, chat|file kind,
createdAt/updatedAt, birth-proposition count, recency-ordered) and
graphSessionPropositions (a session's birth propositions with the
extractor's latest understanding level and THAT event's own timestamp —
owner ruling: quiz outcomes are ledger evidence, they never move the
evaluation date). Teacher's tool handlers consume these in-process.
- New agent.graphTools subsection { enabled?: boolean } (owner ruling:
the toggle gates prober tool REGISTRATION — agent capability, agent
section, its own subsection, NOT the tool-toggles map; absent = ON).
Lenient sanitizer, strict settings-body parser, passthrough resolution,
and graphToolsEnabled(effective) = graph.enabled && toggle for Teacher's
registry wiring.
Gates: tsc clean, eslint clean, 923/923 tests, next build compiles.
Live-verified on the worktree dev data: 10 nodes → 2 clusters labeled
with their chat titles; session index + propositions carry levels and
their own timestamps.
This commit is contained in:
amosblomqvist
+129
-17
@@ -51,8 +51,10 @@ import type {
|
||||
GraphSnapshot,
|
||||
LedgerEvent,
|
||||
LedgerEventKind,
|
||||
UnderstandingLevel,
|
||||
} from "./contracts.ts";
|
||||
import { matchClusterLabelings, MIN_CLUSTER_SIZE } from "./clusters.ts";
|
||||
import { MIN_CLUSTER_SIZE } from "./clusters.ts";
|
||||
import { birthSessionPartition } from "./session-clusters.ts";
|
||||
import type { QuestionAnswerData } from "./question-core.ts";
|
||||
import type { ChatStore, GraphStore } from "./ports.ts";
|
||||
|
||||
@@ -496,23 +498,20 @@ export function graphSnapshot(deps: GraphDeps): GraphSnapshot {
|
||||
(nodeObservations[nodeId] ??= {})[chatId] = note;
|
||||
}
|
||||
|
||||
// Semantic topic communities (DECIDED 2026-09-13, replacing structural
|
||||
// Louvain): average-linkage clustering over embeddings — related
|
||||
// topics, not reasoning chains. Edge-orphans join topics by meaning;
|
||||
// stragglers stay loose (filtered at the presentation threshold
|
||||
// below). The partition is computed ONCE per embedding batch by the
|
||||
// embedder (the agglomerative pass is ~1.5s at current scale) and
|
||||
// PERSISTED in the embedding ledger — reads just load it. Nodes whose
|
||||
// embedding hasn't landed yet simply sit unclustered until the next
|
||||
// read after the embedder runs.
|
||||
const communities = deps.graphStore.readEmbeddings().clusters;
|
||||
const claims = matchClusterLabelings(communities, deps.graphStore.readClusterLabels());
|
||||
// BIRTH-SESSION CLUSTERS (wave 7, owner-locked 2026-09-23): embeddings
|
||||
// are dead — a cluster is the SESSION THAT CREATED ITS PROPOSITIONS,
|
||||
// derived on read from provenance (core/session-clusters.ts). The label
|
||||
// is the session's NAME (chat title / file path): no LLM naming pass, no
|
||||
// persisted partition to invalidate. MIN_CLUSTER_SIZE stays the hull
|
||||
// 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 clusters: Cluster[] = communities
|
||||
.map((community, index) => ({ community, claim: claims[index] }))
|
||||
.filter(({ community }) => community.members.length >= MIN_CLUSTER_SIZE)
|
||||
.map(({ community, claim }) => ({
|
||||
id: claim?.id ?? clusterContentId(community.members),
|
||||
label: claim?.label ?? null,
|
||||
.filter((community) => community.members.length >= MIN_CLUSTER_SIZE)
|
||||
.map((community) => ({
|
||||
id: community.id,
|
||||
label: sessions[community.id] ?? fileSources[community.id] ?? null,
|
||||
members: community.members,
|
||||
}));
|
||||
|
||||
@@ -533,5 +532,118 @@ export function graphSnapshot(deps: GraphDeps): GraphSnapshot {
|
||||
};
|
||||
}
|
||||
|
||||
// ─── Prober graph tools — the data seam (wave 7, owner-locked 2026-09-23) ───
|
||||
|
||||
/** One session in the prober's graph view: every provenance anchor the
|
||||
* graph can name — a real chat (deep-linkable) or an imported notes file
|
||||
* (owner ruling 2026-09-23: files are birth-sessions too, kind "file").
|
||||
* The prober's session-list tool renders these; the per-session view is
|
||||
* graphSessionPropositions below. Pure derivation over the same ports
|
||||
* the snapshot reads — Teacher's tool handlers call these in-process. */
|
||||
export interface GraphSessionEntry {
|
||||
/** chatId or notes source id ("src_…") — the birth-session key. */
|
||||
id: string;
|
||||
/** The chat's title, or the file's path — the cluster label's source. */
|
||||
name: string;
|
||||
/** A real chat (its record still exists) or an imported notes file. */
|
||||
kind: "chat" | "file";
|
||||
/** When the session began: the chat's createdAt, or the file's
|
||||
* importedAt. null when no record can date it. */
|
||||
createdAt: string | null;
|
||||
/** Most recent activity: the chat's updatedAt, or the file's
|
||||
* importedAt. null when no record can date it. */
|
||||
updatedAt: string | null;
|
||||
/** How many propositions were BORN in this session (birth-session
|
||||
* clustering's count — shared/re-encountered nodes count for their
|
||||
* birth session only). */
|
||||
propositions: number;
|
||||
}
|
||||
|
||||
/** The prober's session list: every birth session, most-recently-active
|
||||
* 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)) {
|
||||
counts.set(cluster.id, cluster.members.length);
|
||||
}
|
||||
const chats = new Map(deps.chatStore.listChats().map((chat) => [chat.id, chat]));
|
||||
const sources = new Map(deps.graphStore.readSources().map((s) => [s.id, s]));
|
||||
const entries: GraphSessionEntry[] = [];
|
||||
for (const [id, propositions] of counts) {
|
||||
const chat = chats.get(id); if (chat) {
|
||||
entries.push({
|
||||
id,
|
||||
name: chat.title,
|
||||
kind: "chat",
|
||||
createdAt: chat.createdAt,
|
||||
updatedAt: chat.updatedAt,
|
||||
propositions,
|
||||
});
|
||||
continue;
|
||||
}
|
||||
const source = sources.get(id);
|
||||
entries.push({
|
||||
id,
|
||||
name: source?.filePath ?? id,
|
||||
kind: "file",
|
||||
createdAt: source?.importedAt ?? null,
|
||||
updatedAt: source?.importedAt ?? null,
|
||||
propositions,
|
||||
});
|
||||
}
|
||||
return entries.sort(
|
||||
(a, b) =>
|
||||
(b.updatedAt ?? "").localeCompare(a.updatedAt ?? "") ||
|
||||
(b.createdAt ?? "").localeCompare(a.createdAt ?? "") ||
|
||||
(a.id < b.id ? -1 : 1),
|
||||
);
|
||||
}
|
||||
|
||||
/** One birth proposition of one session, for the prober's per-session
|
||||
* view. `understanding` is the extractor's latest observation for
|
||||
* (node, session) — the named-word scale (solid/shaky/accepted/resisted/
|
||||
* not yet engaged) — and `evaluatedAt` is THAT event's own timestamp
|
||||
* (owner ruling 2026-09-23: quiz outcomes are evidence in the ledger,
|
||||
* but they never move the evaluation date — the level's event does). */
|
||||
export interface GraphSessionProposition {
|
||||
nodeId: string;
|
||||
/** The compact handle — the same name the canvas shows. */
|
||||
name: string;
|
||||
understanding: UnderstandingLevel | null;
|
||||
/** The `at` of the event that minted `understanding`; null when the
|
||||
* session never evaluated this proposition. */
|
||||
evaluatedAt: string | null;
|
||||
}
|
||||
|
||||
/** The propositions BORN in one session, with the session's latest
|
||||
* understanding of each. Latest observation wins by `at`, then by
|
||||
* 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 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;
|
||||
if (!event.note) 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, note: event.note, index });
|
||||
}
|
||||
});
|
||||
return born
|
||||
.map((node) => {
|
||||
const observation = latest.get(node.id);
|
||||
return {
|
||||
nodeId: node.id,
|
||||
name: node.name,
|
||||
understanding: (observation?.note as UnderstandingLevel | undefined) ?? null,
|
||||
evaluatedAt: observation?.at ?? null,
|
||||
};
|
||||
})
|
||||
.sort((a, b) => (a.nodeId < b.nodeId ? -1 : 1));
|
||||
}
|
||||
|
||||
// Re-export: the contract owns the shape; legacy importers still reach it.
|
||||
export type { EmissionStats };
|
||||
|
||||
Reference in New Issue
Block a user