amosblomqvist
4985b6f9fa
Owner rulings 2026-09-30: reasoning chains are the stored truth; the graph canvas renders a lossy derived image. No migration, no backcompat — old graph data was wiped. - contracts: GraphChain (arg_-minted id, premises, conclusion) replaces typed edges; GraphEdge survives only as the untyped derived arrow; GraphSnapshot carries stored chains; supports edges retired entirely - store: chains.jsonl ledger (edges.jsonl purged at load alongside legacy events.jsonl); readChains/appendChain seam; merge dedupes by (sorted premises, conclusion), re-assertions append under the same arg_ id - core: deriveView mints implication nodes (name ⟹, statement via formatChainLine) plus premise→imp→conclusion arrows; clusters stay proposition-only (birthSessionPartition); chainsForSelection now groups STORED chains (chain rides iff every member selected) — independent arguments for one conclusion never union; chainsToGraph/chainsToEdges die - extraction: extractor submits chains natively (expandFindings deleted); auditor receives propositions only; supports fan-out gone - deletion: full death of a proposition kills every referencing chain; arg_-prefixed node deletes kill that chain; chainsRemoved stats - UI: every arrow renders the ⟹ double shaft; supports toggle + thickness slider and detail-card edge sections deleted (card keeps name + proposition); chain table + practice pipeline read stored chains - tests: 1188 green across the new seams
65 lines
2.5 KiB
TypeScript
65 lines
2.5 KiB
TypeScript
/**
|
|
* Import raw notes files through the format-agnostic front door (vision §1,
|
|
* 2026-09-13) — every *.md / *.txt file in a directory becomes one
|
|
* extraction run (extractor → auditor → merger) over its raw text. Run
|
|
* from this worktree only — data never crosses trees:
|
|
*
|
|
* npx tsx --env-file=.env.local scripts/import-notes.ts <dir> [concurrency]
|
|
*
|
|
* Default dir: real-data-extraction/learn-sessions (the prototype
|
|
* learning-session exports — deliberately NOT imported as chats: they run
|
|
* through the notes path, raw). Runs in this process: the dev server's
|
|
* status chips do NOT see them (registry is per-process) — the dev server
|
|
* sees runs triggered through /api/graph/import.
|
|
*/
|
|
import * as fs from "node:fs";
|
|
import * as path from "node:path";
|
|
import { createExtractionPipeline } from "../src/agent/subagents/extraction.ts";
|
|
import { getGraph } from "../src/core/graph.ts";
|
|
import { effectiveSettings, stores } from "../src/server/stores.ts";
|
|
|
|
async function main() {
|
|
const dir = process.argv[2] ?? "real-data-extraction/learn-sessions";
|
|
const limit = Number(process.argv[3] ?? 4);
|
|
const files = fs
|
|
.readdirSync(dir)
|
|
.filter((f) => f.endsWith(".md") || f.endsWith(".markdown") || f.endsWith(".txt"))
|
|
.sort();
|
|
console.log(`[import-notes] ${files.length} note files from ${dir} (concurrency ${limit})`);
|
|
|
|
const pipeline = createExtractionPipeline({
|
|
...stores,
|
|
// Live budget: the graph section's setting, same as the app's trigger
|
|
getChunkTokens: () => effectiveSettings().graph.extractionChunkTokens,
|
|
});
|
|
const queue = [...files];
|
|
const totals = { nodes: 0, chains: 0, failed: 0 };
|
|
const workers = Array.from({ length: Math.min(limit, files.length) }, async () => {
|
|
for (;;) {
|
|
const file = queue.shift();
|
|
if (!file) return;
|
|
const filePath = path.join(dir, file);
|
|
const t0 = Date.now();
|
|
try {
|
|
const stats = await pipeline.importNotes({ filePath, text: fs.readFileSync(filePath, "utf-8") });
|
|
totals.nodes += stats.nodes;
|
|
totals.chains += stats.chains ?? 0;
|
|
console.log(
|
|
`[import-notes] ${file}: ${stats.nodes} nodes, ${stats.chains ?? 0} chains in ${((Date.now() - t0) / 1000).toFixed(1)}s`,
|
|
);
|
|
} catch (err) {
|
|
totals.failed++;
|
|
console.error(`[import-notes] ${file} FAILED:`, err);
|
|
}
|
|
}
|
|
});
|
|
await Promise.all(workers);
|
|
|
|
const graph = getGraph(stores.graphStore);
|
|
console.log(
|
|
`[import-notes] done: +${totals.nodes} nodes, +${totals.chains} chains, ${totals.failed} failed — ` +
|
|
`graph now ${graph.nodes.length} nodes, ${graph.chains.length} chains`,
|
|
);
|
|
}
|
|
|
|
main(); |