feat(linkedin-studio): SB-S3c — cross-silo id-threading + post→analytics assembler [skip-docs]

Hub-side design: the published record now carries the specifics/trends ids
it was built from (additive, omit-empty → byte-backward-compatible), and a
new pure assembler (scripts/brain/src/assemble.ts + `brain assemble`) joins
post↔analytics by normalized title-prefix + date with honest confidence
tiers (high/low/none). Answers the arc's north-star query: which raw
material actually performs? (specific → post → measured analytics).

All four tributaries untouched (analytics READ-only via inlined raw-JSON,
no package import); profile.md grammar untouched (the fact→post link stays
OUT — C-1). The repeatable --specific/--trend ingest flags collect via a
new collectRepeated helper, leaving parseFlags untouched.

TDD: 19 new brain tests (ingest 4 + publish 3 + assemble 8 + cli 4), all
SC1–SC12. brain 113/113, gate 95/0/0, BRAIN_TESTS_FLOOR 94→113,
ASSERT_BASELINE_FLOOR unchanged at 80. Light-Voyage hardened
(brief-review 5 FIX · plan-critic 1 BLOCK+4 MAJOR+4 MINOR · scope-guardian ALIGNED).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RigJBiRFNtFZKCz21qNbQ4
This commit is contained in:
Kjell Tore Guttormsen 2026-06-23 20:47:34 +02:00
commit edd3e15ef7
12 changed files with 515 additions and 14 deletions

View file

@ -25,6 +25,7 @@ import {
type Candidate,
type ProfileDiff,
} from "./consolidate.js";
import { assemblePostGraph, loadAnalyticsRows } from "./assemble.js";
import { dataRoot } from "./dataRoot.js";
import { ingestText, listPublished, parsePublishedRecord, scanInbox } from "./ingest.js";
import { parseProfile, serializeProfile } from "./profile.js";
@ -59,6 +60,25 @@ function parseFlags(args: string[]): Record<string, string> {
return out;
}
/**
* SB-S3c: collect EVERY value of a repeatable `--key <value>` flag into an array
* (the single-value `parseFlags` keeps only the last). Scans the raw args directly,
* leaving `parseFlags` untouched so single-value flag behaviour is unchanged.
*/
function collectRepeated(args: string[], key: string): string[] {
const out: string[] = [];
for (let i = 0; i < args.length; i++) {
if (args[i] === `--${key}`) {
const next = args[i + 1];
if (next !== undefined && !next.startsWith("--")) {
out.push(next);
i++;
}
}
}
return out;
}
function today(): string {
return new Date().toISOString().slice(0, 10);
}
@ -68,9 +88,10 @@ function usage(msg: string): never {
console.error(
"usage:\n" +
" init\n" +
" ingest --file <path> [--source <s>] [--date <YYYY-MM-DD>]\n" +
" ingest --file <path> [--source <s>] [--date <YYYY-MM-DD>] [--specific <id>]… [--trend <id>]…\n" +
" ingest --scan-inbox [--source <s>]\n" +
" published list [--json]",
" published list [--json]\n" +
" assemble",
);
process.exit(2);
}
@ -89,7 +110,7 @@ function runInit(): void {
if (created.length === 0) console.log("Already initialised — nothing to do.");
}
function runIngest(flags: Record<string, string>): void {
function runIngest(rest: string[], flags: Record<string, string>): void {
if (flags["scan-inbox"] === "true") {
const res = scanInbox({ captured_at: today(), source: flags.source });
console.log(
@ -100,11 +121,14 @@ function runIngest(flags: Record<string, string>): void {
const file = flags.file;
if (!file || file === "true") usage("ingest needs --file <path> or --scan-inbox");
const body = readFileSync(file, "utf8");
// SB-S3c: --specific / --trend are repeatable — read ONLY via collectRepeated.
const res = ingestText({
body,
captured_at: today(),
source: flags.source,
published_date: flags.date === "true" ? undefined : flags.date,
specifics: collectRepeated(rest, "specific"),
trends: collectRepeated(rest, "trend"),
});
if (res.written && res.collision) {
console.log(`Collision (different body, same id) → wrote ${res.path}`);
@ -129,6 +153,53 @@ function runPublished(rest: string[], flags: Record<string, string>): void {
}
}
/**
* SB-S3c: read-only cross-silo assembler view post raw-material performance.
* Loads published records + analytics rows (inlined raw-JSON, no analytics import),
* prints the join newest-first. Writes NOTHING.
*/
function runAssemble(_flags: Record<string, string>): void {
const pubDir = dataRoot(join("ingest", "published"));
const records = existsSync(pubDir)
? readdirSync(pubDir)
.filter((f) => f.endsWith(".md") && !f.startsWith("."))
.map((f) => {
try {
return parsePublishedRecord(readFileSync(join(pubDir, f), "utf8"));
} catch {
return null;
}
})
.filter((r): r is NonNullable<typeof r> => r !== null)
: [];
const analytics = loadAnalyticsRows();
const bodyById = new Map(records.map((r) => [r.id, r.body]));
const graph = assemblePostGraph({ records, analytics }).sort((a, b) =>
b.published_date.localeCompare(a.published_date),
);
if (graph.length === 0) {
console.log(
"No published records to assemble. Ingest posts with `brain ingest --file <p> [--specific <id>] [--trend <id>]`.",
);
return;
}
console.log(`Post graph — ${graph.length} record(s); ${analytics.length} analytics row(s):`);
for (const node of graph) {
const firstLine = (bodyById.get(node.contentId) ?? "").split("\n", 1)[0];
console.log(`\${node.contentId} · ${node.published_date} · ${firstLine}`);
console.log(` specifics: ${node.specifics.length ? node.specifics.join(", ") : "—"}`);
console.log(` trends: ${node.trends.length ? node.trends.join(", ") : "—"}`);
if (node.match.confidence === "none") {
console.log(" analytics: none (no title-prefix+date match)");
} else {
const eng = node.match.row?.metrics?.engagementRate;
console.log(
` analytics: ${node.match.confidence}${eng !== undefined ? ` [eng ${eng}%]` : ""}`,
);
}
}
}
function renderDiffMd(diff: ProfileDiff): string {
const lines = ["# Pending profile diff", "", "> Operator-gated. Review, then `brain consolidate --apply --diff brain/pending-diff.json --confirm`.", ""];
const section = (title: string, items: string[]) => {
@ -235,9 +306,10 @@ function main(): void {
const flags = parseFlags(rest);
if (command === "init") return runInit();
if (command === "ingest") return runIngest(flags);
if (command === "ingest") return runIngest(rest, flags);
if (command === "published") return runPublished(rest, flags);
if (command === "consolidate") return runConsolidate(flags);
if (command === "assemble") return runAssemble(flags);
usage(command ? `unknown command: ${command}` : "no command given");
}