sorokin.oleg.edu/learnharness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 6 Wiki Activity

W8: graph-as-context injection + exact-match merge

Browse Source
This commit is contained in:
Amos
2026-08-22 11:41:50 +03:00
parent 53be8a2834
commit 806e1405d5
6 changed files with 687 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/core/graph.ts
+47 -12
View File
@@ -4,7 +4,10 @@
*
* emitChat(chatId) folds ONE chat into the global graph — naive union,
* deterministic, no LLM:
* plan-tree nodes → GraphNodes (statement = title, aliases empty)
* plan-tree nodes → GraphNodes (statement = title, aliases empty;
* W8: a title exactly matching an existing statement
* or alias — case-insensitive, trimmed — maps onto the
* existing node instead of appending a duplicate)
* plan-tree edges → `requires` GraphEdges (from = prerequisite)
* answered quizzes → ledger events (probe-* before the first plan_init
* output, check / dont-know after; ref = toolCallId)
@@ -23,6 +26,11 @@ import type { QuestionAnswerData } from "./question-core.ts";
import { getChat, listChats } from "../store/chats.ts";
import { graphLedgers, newGraphNodeId } from "../store/graph.ts";
/** The ledger surface emitChat needs (the real one is src/store/graph.ts).
* Injectable so tests can fold fixtures into an in-memory ledger instead of
* the live data/graph files. */
export type GraphLedgers = typeof graphLedgers;
// ─── transcript scanning ─────────────────────────────────────────────────────
/** A flattened, order-preserving view of every tool part in a transcript. */
@@ -91,8 +99,11 @@ export interface EmissionStats {
* Fold one chat into the graph ledgers. Idempotent — safe to call after every
* turn (chat-handler onFinish) and again on catch-up (GET /api/graph). Sync
* and fast: a handful of small-file reads plus one append per new record.
*
* `ledgers` is injectable for tests (in-memory ledger); production always
* uses the live store.
*/
export function emitChat(chatId: string): EmissionStats {
export function emitChat(chatId: string, ledgers: GraphLedgers = graphLedgers): EmissionStats {
const record = getChat(chatId);
if (!record) return { nodes: 0, edges: 0, events: 0 };
const stats: EmissionStats = { nodes: 0, edges: 0, events: 0 };
@@ -100,7 +111,7 @@ export function emitChat(chatId: string): EmissionStats {
// 1. This chat's existing mappings — the identity map is per-chat (v1 is
// naive union: two sessions' tree nodes never merge into one graph node).
const mapping = new Map<string, string>();
for (const m of graphLedgers.readMappings()) {
for (const m of ledgers.readMappings()) {
if (m.chatId === chatId) mapping.set(m.treeNodeId, m.graphNodeId);
}
@@ -112,10 +123,33 @@ export function emitChat(chatId: string): EmissionStats {
const tree =
record.tree && record.tree.nodes.length > 0 ? record.tree : replayFinalTree(record.messages);
// 3. Tree nodes without a mapping → GraphNode + mapping.
// 3. Tree nodes without a mapping → GraphNode + mapping. W8 merge
// improvement: a title that EXACTLY matches (case-insensitive, trimmed) an
// existing node's statement or alias maps onto that node instead of
// appending a duplicate — the mapping line is still appended so provenance
// stays honest. Fuzzy/embedding matching stays deferred (vision §1
// consolidation pipeline).
const norm = (s: string): string => s.trim().toLowerCase();
const existingByTitle = new Map<string, string>();
for (const node of ledgers.readNodes()) {
const statementKey = norm(node.statement);
if (statementKey && !existingByTitle.has(statementKey)) existingByTitle.set(statementKey, node.id);
for (const alias of node.aliases) {
const aliasKey = norm(alias);
if (aliasKey && !existingByTitle.has(aliasKey)) existingByTitle.set(aliasKey, node.id);
}
}
const now = new Date().toISOString();
for (const node of tree.nodes) {
if (mapping.has(node.id)) continue;
const titleKey = norm(node.title);
const existingId = titleKey ? existingByTitle.get(titleKey) : undefined;
if (existingId !== undefined) {
// Exact match: reuse the node, record the mapping, append nothing.
ledgers.appendMapping({ chatId, treeNodeId: node.id, graphNodeId: existingId });
mapping.set(node.id, existingId);
continue;
}
const graphNode: GraphNode = {
id: newGraphNodeId(),
// statement is the title; the summary stays out (contracts).
@@ -124,8 +158,9 @@ export function emitChat(chatId: string): EmissionStats {
kind: "truth",
createdAt: now,
};
graphLedgers.appendNode(graphNode);
graphLedgers.appendMapping({ chatId, treeNodeId: node.id, graphNodeId: graphNode.id });
ledgers.appendNode(graphNode);
ledgers.appendMapping({ chatId, treeNodeId: node.id, graphNodeId: graphNode.id });
existingByTitle.set(titleKey, graphNode.id);
mapping.set(node.id, graphNode.id);
stats.nodes++;
}
@@ -134,7 +169,7 @@ export function emitChat(chatId: string): EmissionStats {
// whole ledger: an existing assertion just gains this chatId as
// provenance (appended as a new line; reads merge).
const asserted = new Map<string, Set<string>>();
for (const line of graphLedgers.readEdges()) {
for (const line of ledgers.readEdges()) {
const key = `${line.from}\u0000${line.to}\u0000${line.type}`;
let provenance = asserted.get(key);
if (!provenance) {
@@ -150,7 +185,7 @@ export function emitChat(chatId: string): EmissionStats {
const key = `${from}\u0000${to}\u0000requires`;
const provenance = asserted.get(key);
if (provenance?.has(chatId)) continue; // already asserted by this chat
graphLedgers.appendEdge({ from, to, type: "requires", provenance: [chatId] });
ledgers.appendEdge({ from, to, type: "requires", provenance: [chatId] });
if (provenance) provenance.add(chatId);
else asserted.set(key, new Set([chatId]));
stats.edges++;
@@ -161,7 +196,7 @@ export function emitChat(chatId: string): EmissionStats {
// chat-scoped (a quiz toolCallId or taught:<treeNodeId>) — a ref already
// in the ledger means this turn was folded before.
const seenRefs = new Set<string>();
for (const event of graphLedgers.readEvents()) {
for (const event of ledgers.readEvents()) {
if (event.chatId === chatId && event.ref) seenRefs.add(event.ref);
}
let planSeen = false;
@@ -173,7 +208,7 @@ export function emitChat(chatId: string): EmissionStats {
if (part.name === "quiz" && part.state === "output-available") {
const event = quizEvent(part, chatId, mapping, planSeen, now);
if (event?.ref !== undefined && !seenRefs.has(event.ref)) {
graphLedgers.appendEvent(event);
ledgers.appendEvent(event);
seenRefs.add(event.ref);
stats.events++;
}
@@ -185,7 +220,7 @@ export function emitChat(chatId: string): EmissionStats {
if (result?.ok && typeof input?.id === "string") {
const ref = `taught:${input.id}`;
if (!seenRefs.has(ref)) {
graphLedgers.appendEvent({
ledgers.appendEvent({
nodeId: mapping.get(input.id) ?? null,
kind: "taught",
chatId,
@@ -200,7 +235,7 @@ export function emitChat(chatId: string): EmissionStats {
}
// 6. Checkpoint: this chat is folded through its current updatedAt.
graphLedgers.appendCheckpoint({ chatId, foldedAt: record.updatedAt });
ledgers.appendCheckpoint({ chatId, foldedAt: record.updatedAt });
return stats;
}