Files
learnharness/scripts/replay-layout.ts
T
amosblomqvist 8355fbabdb delete the mappings ledger — per-job in-memory resolution + notes fingerprint guard
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
2026-09-29 02:25:32 +03:00

122 lines
4.9 KiB
TypeScript

/**
* Option A simulation: replay the CURRENT graph through the incremental
* layout as if it had arrived one imported-notes file at a time — the
* organic growth path the user described (one dependency structure /
* cluster at a time, orphans collecting on the rim).
*
* Reads ONLY the ledgers (nodes / edges / mappings / sources); writes ONLY
* data/graph/positions.json — no LLM calls, no extraction, no chat records.
*
* npx tsx scripts/replay-layout.ts [--depth=vertical|radial]
*
* --depth regenerates the ledger WITH inference-depth anchoring (the
* playground mode baked into the rest state); omit it for the free layout.
*/
import { graphStore } from "../src/store/graph.ts";
// --depth=vertical|radial: bake the playground depth mode into the ledger.
const depthArg = process.argv.find((a) => a.startsWith("--depth="));
const depthMode: "off" | "vertical" | "radial" =
depthArg === "--depth=vertical" ? "vertical" : depthArg === "--depth=radial" ? "radial" : "off";
import { incrementalLayout } from "../src/core/layout.ts";
import { birthSessionPartition } from "../src/core/session-clusters.ts";
import type { GraphNode, Position } from "../src/core/contracts.ts";
function main() {
const t0 = Date.now();
// Unique nodes (lines may repeat an id — first defines).
const seen = new Set<string>();
const nodes: GraphNode[] = [];
for (const line of graphStore.readNodes()) {
if (seen.has(line.id)) continue;
seen.add(line.id);
nodes.push(line);
}
const edges = graphStore.readEdges();
// The cluster source (wave 7): the birth-session partition, derived on
// read — same as the real settle (core/layout-settle.ts).
const birthClusters = birthSessionPartition(nodes);
// Batches: each imported file, in real import order (sources.json
// importedAt). A node belongs to the session of its FIRST provenance
// point (line order = arrival); nodes with no provenance (legacy) ride
// the final batch.
const sources = [...graphStore.readSources()].sort((a, b) => a.importedAt.localeCompare(b.importedAt));
const batchOf = new Map<string, string>(); // nodeId → srcId
for (const node of nodes) {
const birth = node.provenance[0]?.chatId;
if (birth !== undefined && !batchOf.has(node.id)) batchOf.set(node.id, birth);
}
const delivered = new Set<string>();
let positions = new Map<string, Position>(Object.entries(graphStore.readPositions()));
if (positions.size > 0) {
console.log("[replay] discarding existing positions ledger — full replay from empty");
positions = new Map();
}
const byId = new Map(nodes.map((n) => [n.id, n]));
const unmappedFallback = sources[sources.length - 1]?.id ?? "";
console.log(`[replay] ${nodes.length} unique nodes, ${edges.length} edge lines, ${sources.length} sources`);
let maxOldShift = 0;
let shiftReport = "";
for (const source of sources) {
const batch = nodes.filter((n) => batchOf.get(n.id) === source.id);
const isLast = source.id === sources[sources.length - 1]!.id;
if (isLast) {
// Sweep in any never-mapped nodes with the last batch.
for (const n of nodes) {
if (!batchOf.has(n.id) && !delivered.has(n.id)) {
batch.push(n);
batchOf.set(n.id, unmappedFallback);
}
}
}
for (const n of batch) delivered.add(n.id);
// Edges activate once BOTH endpoints exist (a later file can claim
// one endpoint — the edge lights up then).
const activeEdges = edges.filter((e) => delivered.has(e.from) && delivered.has(e.to));
const before = new Map(positions);
const batchNodes = nodes.filter((n) => delivered.has(n.id));
positions = incrementalLayout(batchNodes, activeEdges, positions, {
// The same partition the real settle would see for this batch:
// the birth-session clusters, filtered to delivered nodes.
clusters: birthClusters
.map((c) => ({ members: c.members.filter((id) => delivered.has(id)) }))
.filter((c) => c.members.length > 0),
...(depthMode === "off"
? {}
: {
depthAnchor: {
mode: depthMode,
strength: 0.8,
spacing: 60,
...(depthMode === "radial" ? { baseRadius: 220 } : {}),
},
}),
});
for (const [id, prev] of before) {
const now = positions.get(id)!;
const shift = Math.hypot(prev.x - now.x, prev.y - now.y);
if (shift > maxOldShift) {
maxOldShift = shift;
shiftReport = `${id} ${prev.x.toFixed(0)},${prev.y.toFixed(0)} -> ${now.x.toFixed(0)},${now.y.toFixed(0)} (batch ${batch.length} new, ${activeEdges.length} edges)`;
}
}
const label = source.filePath.split("/").pop() ?? source.id;
console.log(
`[replay] +${String(batch.length).padStart(3)} nodes ${String(activeEdges.length).padStart(4)} edges active (${label})`,
);
}
graphStore.writePositions(Object.fromEntries(positions));
console.log(
`[replay] done: ${positions.size} positions written in ${((Date.now() - t0) / 1000).toFixed(1)}s` +
` (max old-node shift within a batch: ${maxOldShift.toFixed(1)}: ${shiftReport})`,
);
}
main();