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

delete the mappings ledger — per-job in-memory resolution + notes fingerprint guard

Browse Source 
The persisted (chatId, sourceId)→node table was a shared namespace across
independent chunk/batch jobs: each chunk's extractor mints local ids fresh
(p1..pN), so later chunks collided with earlier ones — propositions silently
skipped as 'already resolved' (coverage checkpointed anyway: permanent silent
loss) and edges resolved onto the wrong nodes (the 'everything links to
everything' mush). Owner ruling 2026-09-29: mergeFindings resolves THIS job's
ids in memory, nothing persists between jobs; cross-job identity is the
auditor's linkTo verdicts alone.

- contracts: NodeMapping dies; NotesSource.contentFp — sha256 of the text at
  the last run, the re-import guard (unchanged re-import = TRUE no-op, no
  model calls, no usage; changed text re-runs; legacy unstamped sources
  re-run once)
- merger: job-local resolution map, in-submit duplicate ids skip once,
  edges resolve extractor-local ids only
- ports/store: appendMapping/readMappings, LEDGER_FILES.mappings,
  rewriteLedgers.mappings gone (stale data/graph/mappings.jsonl just stops
  being read)
- session-clusters: birthSessionOf is provenance-only — the legacy
  mapping-line fallback for provenance-empty notes nodes dies
- deletion: no mapping rows to strip; stats lose mappingsRemoved
- replay-layout batches nodes by first provenance point
- graph.test pins the new independence semantics (re-merge re-creates;
  duplicate ids within one submit resolve once); extraction tests pin
  per-chunk merges + the fingerprint guard
This commit is contained in:
amosblomqvist
2026-09-29 02:25:32 +03:00
parent 92146248d2
commit 8355fbabdb
17 changed files with 182 additions and 304 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/core/graph-deletion.ts
+5 -30
View File
@@ -13,7 +13,7 @@
*
* preserve-graph the chat's extraction bookkeeping dies — its coverage
* rows and its legacy checkpoint lines — and NOTHING else:
* nodes, edges, mappings stay byte-identical.
* nodes and edges stay byte-identical.
* The graph keeps the session's contributions; the
* snapshot simply no longer resolves the dead chatId to
* a title (nodeSessions filters unknown ids at read
@@ -22,8 +22,8 @@
* delete-nodes "this session never happened": every trace of the
* chat leaves the ledgers — its provenance points on
* every node and edge line, its link lines (their
* phrasings die with them), its mapping lines (the audit trail), its
* coverage/checkpoint rows — and orphans die: a node
* phrasings die with them), its coverage/checkpoint
* rows — and orphans die: a node
* whose references all came from this chat disappears
* entirely, pruned from the positions and embedding
* ledgers too (dead members would break cluster hulls).
@@ -57,7 +57,6 @@ import type {
CoverageEntry,
GraphEdge,
GraphNode,
NodeMapping,
SessionCheckpoint,
} from "./contracts.ts";
import type { GraphStore } from "./ports.ts";
@@ -74,8 +73,6 @@ export interface ChatDeletionStats {
nodesRemoved: number;
/** Edge assertion LINES removed (empty-provenance or dead endpoint). */
edgesRemoved: number;
/** Mapping lines removed (the chat's audit trail). */
mappingsRemoved: number;
/** Coverage rows removed. */
coverageRemoved: number;
/** Checkpoint lines removed. */
@@ -85,7 +82,6 @@ export interface ChatDeletionStats {
const EMPTY_STATS: ChatDeletionStats = {
nodesRemoved: 0,
edgesRemoved: 0,
mappingsRemoved: 0,
coverageRemoved: 0,
checkpointsRemoved: 0,
};
@@ -121,7 +117,6 @@ export function deleteChatTraces(graphStore: GraphStore, chatId: string, mode: C
// ── delete-nodes: the full purge ──────────────────────────────────────
const nodeLines = graphStore.readNodes();
const edgeLines = graphStore.readEdges();
const mappings = graphStore.readMappings();
// Does the chat touch the graph at all? (A never-extracted chat still
// needs its coverage rows dropped above, but no ledger rewrite — keeps
@@ -129,8 +124,7 @@ export function deleteChatTraces(graphStore: GraphStore, chatId: string, mode: C
// changed.)
const touched =
nodeLines.some((line) => line.provenance.some((pt) => pt.chatId === chatId)) ||
edgeLines.some((line) => line.provenance.some((pt) => pt.chatId === chatId)) ||
mappings.some((m) => m.chatId === chatId);
edgeLines.some((line) => line.provenance.some((pt) => pt.chatId === chatId));
if (!touched) {
if (stats.coverageRemoved > 0 || stats.checkpointsRemoved > 0) {
graphStore.rewriteLedgers({ coverage, checkpoints });
@@ -153,9 +147,6 @@ export function deleteChatTraces(graphStore: GraphStore, chatId: string, mode: C
for (const line of nodeLines) {
if (survives(line.provenance)) live.add(line.id);
}
for (const mapping of mappings) {
if (mapping.chatId !== chatId) live.add(mapping.graphNodeId);
}
// 2. Node lines. Per-line (each line is ONE extraction run's append, so
// per-session alias provenance exists at line granularity):
@@ -209,17 +200,12 @@ export function deleteChatTraces(graphStore: GraphStore, chatId: string, mode: C
outEdges.push(points.length === line.provenance.length ? line : { ...line, provenance: points });
}
// 4. Mappings: the chat's rows die outright.
const outMappings = mappings.filter((m) => m.chatId !== chatId);
stats.nodesRemoved = [...new Set(nodeLines.map((line) => line.id))].filter((id) => !live.has(id)).length;
stats.edgesRemoved = edgeLines.length - outEdges.length;
stats.mappingsRemoved = mappings.length - outMappings.length;
graphStore.rewriteLedgers({
nodes: outNodes,
edges: outEdges,
mappings: outMappings,
coverage,
checkpoints,
});
@@ -272,14 +258,11 @@ export function deleteChatTraces(graphStore: GraphStore, chatId: string, mode: C
export interface NodeDeletionStats {
/** Edge assertion LINES removed (every edge touching the node). */
edgesRemoved: number;
/** Mapping lines removed (the node's audit trail). */
mappingsRemoved: number;
}
/** The confirm dialog's pre-flight facts (the GET on the same node id):
* what full death would take with it. sessions is the deduped set of
* chats/notes sources that reference the node — provenance points and
* mapping lines count. */
* chats/notes sources that reference the node — provenance points count. */
export interface NodeDeletionImpact {
edges: number;
sessions: string[];
@@ -298,9 +281,6 @@ export function nodeDeletionImpact(graphStore: GraphStore, nodeId: string): Node
for (const line of nodeLinesOf(graphStore, nodeId)) {
for (const pt of line.provenance) sessions.add(pt.chatId);
}
for (const mapping of graphStore.readMappings()) {
if (mapping.graphNodeId === nodeId) sessions.add(mapping.chatId);
}
return {
edges: edges.length,
sessions: [...sessions].sort(),
@@ -318,10 +298,7 @@ export function deleteNodeTraces(graphStore: GraphStore, nodeId: string): NodeDe
if (nodeLines.length === 0) return null;
const edgeLines = graphStore.readEdges();
const mappings = graphStore.readMappings();
const outEdges = edgeLines.filter((line) => line.from !== nodeId && line.to !== nodeId);
const outMappings = mappings.filter((m) => m.graphNodeId !== nodeId);
// Only the touched ledgers: the node's own lines always die (its file
// must move), everything else rewrites only when rows actually drop.
@@ -329,7 +306,6 @@ export function deleteNodeTraces(graphStore: GraphStore, nodeId: string): NodeDe
graphStore.rewriteLedgers({
nodes: outNodes,
...(outEdges.length !== edgeLines.length ? { edges: outEdges } : {}),
...(outMappings.length !== mappings.length ? { mappings: outMappings } : {}),
});
// The resting position dies with the node.
@@ -341,6 +317,5 @@ export function deleteNodeTraces(graphStore: GraphStore, nodeId: string): NodeDe
return {
edgesRemoved: edgeLines.length - outEdges.length,
mappingsRemoved: mappings.length - outMappings.length,
};
}