Compare commits

..
Author SHA1 Message Date
ddb000b0e2 fix(dream): keep dream --dry-run --json stdout clean of embed summaries (#394)
The cycle's embed phase called runEmbedCore with no output suppression, so
the '[dry-run] Would embed ...' / 'Embedded N chunks ...' slog summaries
landed on stdout ahead of the JSON CycleReport, breaking the documented
stdout-clean-for-JSON contract (docs/progress-events.md).

Adds EmbedOpts.quiet gating the human stdout summary slog sites in
embed.ts (embedPage, embedAll, embedAllStale); the cycle's runPhaseEmbed
sets quiet: true since it reports counts via its own PhaseResult. Errors
and warnings still go to stderr regardless.

Takeover of #854 (same approach, reimplemented on current master — the
original patch predates the slog migration and the widened
embedAll/embedAllStale signatures). Regression test ported from #854.

Co-authored-by: Kage18 <Kage18@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:31:13 -07:00
7 changed files with 68 additions and 74 deletions
+33 -15
View File
@@ -107,6 +107,14 @@ export interface EmbedOpts {
* runs lock every source in sorted order. dryRun skips it.
*/
singleFlight?: boolean;
/**
* #394: suppress human stdout summaries (the `[dry-run] Would embed ...` /
* `Embedded N chunks ...` slog lines). Set by structured-output callers —
* the cycle's embed phase (dream --json must keep stdout JSON-clean per
* docs/progress-events.md) reports counts via its own PhaseResult instead.
* Errors/warnings still go to stderr regardless.
*/
quiet?: boolean;
}
/**
@@ -253,7 +261,7 @@ export async function runEmbedCore(engine: BrainEngine, opts: EmbedOpts): Promis
for (const s of opts.slugs) {
if (isAborted(opts.signal)) break; // #1737: stop the per-slug loop on abort
try {
await embedPage(engine, s, !!opts.dryRun, result, opts.sourceId, opts.signal);
await embedPage(engine, s, !!opts.dryRun, result, opts.sourceId, opts.signal, opts.quiet);
} catch (e: unknown) {
serr(` Error embedding ${s}: ${e instanceof Error ? e.message : e}`);
}
@@ -347,6 +355,7 @@ export async function runEmbedCore(engine: BrainEngine, opts: EmbedOpts): Promis
catchUp: opts.catchUp,
pacer,
paceMaxConcurrency,
quiet: opts.quiet,
}, opts.signal);
} finally {
// E1: surface pacing telemetry (human + structured) when pacing was on.
@@ -376,7 +385,7 @@ export async function runEmbedCore(engine: BrainEngine, opts: EmbedOpts): Promis
return result;
}
if (opts.slug) {
await embedPage(engine, opts.slug, !!opts.dryRun, result, opts.sourceId, opts.signal);
await embedPage(engine, opts.slug, !!opts.dryRun, result, opts.sourceId, opts.signal, opts.quiet);
return result;
}
throw new Error('No embed target specified. Pass { slug }, { slugs }, { all }, or { stale }.');
@@ -521,6 +530,7 @@ async function embedPage(
result: EmbedResult,
sourceId?: string,
signal?: AbortSignal,
quiet?: boolean,
) {
const opts = sourceId ? { sourceId } : undefined;
const page = await engine.getPage(slug, opts);
@@ -565,7 +575,7 @@ async function embedPage(
result.skipped += chunks.length - toEmbed.length;
if (toEmbed.length === 0) {
slog(`${slug}: all ${chunks.length} chunks already embedded`);
if (!quiet) slog(`${slug}: all ${chunks.length} chunks already embedded`);
result.pages_processed++;
return;
}
@@ -602,7 +612,7 @@ async function embedPage(
}
result.embedded += toEmbed.length;
result.pages_processed++;
slog(`${slug}: embedded ${toEmbed.length} chunks`);
if (!quiet) slog(`${slug}: embedded ${toEmbed.length} chunks`);
}
async function embedAll(
@@ -620,6 +630,8 @@ async function embedAll(
pacer?: DbPacer;
/** Resolved concurrency cap (E-1: the worker count, no separate permit). */
paceMaxConcurrency?: number;
/** #394: suppress human stdout summaries (structured-output callers). */
quiet?: boolean;
},
signal?: AbortSignal,
) {
@@ -763,10 +775,12 @@ async function embedAll(
});
// Stdout summary preserved for scripts/tests that grep for counts.
if (dryRun) {
slog(`[dry-run] Would embed ${result.would_embed} chunks across ${pages.length} pages`);
} else {
slog(`Embedded ${result.embedded} chunks across ${pages.length} pages`);
if (!staleOpts?.quiet) {
if (dryRun) {
slog(`[dry-run] Would embed ${result.would_embed} chunks across ${pages.length} pages`);
} else {
slog(`Embedded ${result.embedded} chunks across ${pages.length} pages`);
}
}
}
@@ -802,6 +816,8 @@ async function embedAllStale(
pacer?: DbPacer;
/** Resolved concurrency cap (E-1: the worker count, no separate permit). */
paceMaxConcurrency?: number;
/** #394: suppress human stdout summaries (structured-output callers). */
quiet?: boolean;
},
signature?: string,
externalSignal?: AbortSignal,
@@ -819,7 +835,7 @@ async function embedAllStale(
signature,
...(sourceId && { sourceId }),
});
if (invalidated > 0) {
if (invalidated > 0 && !staleOpts?.quiet) {
slog(`[embed] invalidated ${invalidated} chunk(s) embedded under a prior model signature`);
}
}
@@ -830,10 +846,12 @@ async function embedAllStale(
dryRun && signature ? { ...sourceOpt, signature } : sourceOpt,
);
if (staleCount === 0) {
if (dryRun) {
slog('[dry-run] Would embed 0 chunks (0 stale found)');
} else {
slog('Embedded 0 chunks (0 stale found)');
if (!staleOpts?.quiet) {
if (dryRun) {
slog('[dry-run] Would embed 0 chunks (0 stale found)');
} else {
slog('Embedded 0 chunks (0 stale found)');
}
}
return;
}
@@ -842,7 +860,7 @@ async function embedAllStale(
result.would_embed += staleCount;
result.total_chunks += staleCount;
if (onProgress) onProgress(1, 1, 0);
slog(`[dry-run] Would embed ${staleCount} stale chunks`);
if (!staleOpts?.quiet) slog(`[dry-run] Would embed ${staleCount} stale chunks`);
return;
}
@@ -1082,7 +1100,7 @@ async function embedAllStale(
if (budgetTimer) clearTimeout(budgetTimer);
}
slog(`Embedded ${result.embedded} chunks across ${totalProcessedPages} pages`);
if (!staleOpts?.quiet) slog(`Embedded ${result.embedded} chunks across ${totalProcessedPages} pages`);
// #1946 (OV2a): a catch-up pass that completed without being aborted but left
// chunks unembedded means those chunks are stuck (a non-transient embed
+1 -9
View File
@@ -1743,15 +1743,7 @@ async function extractStaleFromDB(
// `page.updated_at.toISOString()` — the JS Date is ms-truncated, so the
// µs-precision DB updated_at stayed strictly greater and the page never
// cleared on Postgres. Stamping the exact value makes them equal.
//
// Version-arm floor: a page last edited BEFORE LINK_EXTRACTOR_VERSION_TS
// would otherwise be stamped below the version watermark and stay
// permanently stale (`links_extracted_at < versionTs` re-fires every run).
// Stamp max(updated_at, versionTs) — versionTs is always a past release
// date, so a concurrent edit's now() still exceeds the stamp and D4 holds.
// Tie at ms precision picks updated_at_iso (its µs ≥ versionTs's .000000).
const stampTs = new Date(page.updated_at_iso) >= new Date(versionTs) ? page.updated_at_iso : versionTs;
processedRefs.push({ slug: page.slug, source_id: page.source_id, extractedAt: stampTs });
processedRefs.push({ slug: page.slug, source_id: page.source_id, extractedAt: page.updated_at_iso });
}
// Flush NON-swallowing (CDX-4): a throw here propagates out of the sweep so
+3 -1
View File
@@ -1214,7 +1214,9 @@ async function runPhaseEmbed(engine: BrainEngine, dryRun: boolean, signal?: Abor
// 10-15 min one) bails within a batch instead of running to completion
// after the job was killed — which left gbrain_cycle_locks held and
// wedged every subsequent autopilot cycle.
const result = await runEmbedCore(engine, { stale: true, dryRun, signal });
// #394: quiet — the cycle reports embed counts via its own PhaseResult;
// raw `[dry-run] Would embed ...` stdout lines would corrupt `dream --json`.
const result = await runEmbedCore(engine, { stale: true, dryRun, signal, quiet: true });
const embeddedCount = dryRun ? result.would_embed : result.embedded;
return {
phase: 'embed',
+4 -13
View File
@@ -28,7 +28,7 @@ import { ensureWellFormed } from './text-safe.ts';
* OR updated_at > links_extracted_at`. It is an ISO-8601 string (NOT a number) —
* the column is TIMESTAMPTZ and the predicate binds it as `::timestamptz`.
*/
export const LINK_EXTRACTOR_VERSION_TS = '2026-07-21T00:00:00Z';
export const LINK_EXTRACTOR_VERSION_TS = '2026-05-31T00:00:00Z';
// ─── Entity references ──────────────────────────────────────────
@@ -80,10 +80,10 @@ export type LinkResolutionType = 'qualified' | 'unqualified';
* Directory prefix whitelist. These are the top-level slug dirs the extractor
* recognizes as entity references. Upstream canonical + our extensions:
* - Gbrain canonical: people, companies, meetings, concepts, deal, civic, project, source, media, yc, projects
* - Our domain extensions: tech, finance, personal, openclaw, ops (domain-organized wikis)
* - Our domain extensions: tech, finance, personal, openclaw (domain-organized wikis)
* - Our entity prefix: entities (we kept some legacy entities/projects/ pages)
*/
const DIR_PATTERN = '(?:people|companies|meetings|concepts|deal|civic|project|projects|source|media|yc|tech|finance|personal|openclaw|entities|ops)';
const DIR_PATTERN = '(?:people|companies|meetings|concepts|deal|civic|project|projects|source|media|yc|tech|finance|personal|openclaw|entities)';
/**
* Match `[Name](path)` markdown links pointing to entity directories.
@@ -865,16 +865,7 @@ export function queryBasenameIndex(idx: Map<string, string[]>, name: string): st
if (!name || typeof name !== 'string') return [];
const trimmed = name.trim();
if (!trimmed) return [];
let hit = idx.get(trimmed) ?? idx.get(trimmed.toLowerCase()) ?? idx.get(normalizeBasename(trimmed));
// Issue #2576 bug 2: path-style refs (`runbooks/2026-05-01-x`) from dirs
// outside DIR_PATTERN reach here, but normalizeBasename strips slashes
// into a garbage key (`runbooks2026-05-01-x`) that can never hit the
// tail-keyed index. Fall back to the path tail so qualified refs resolve
// by basename like everything else.
if (!hit && trimmed.includes('/')) {
const tail = trimmed.slice(trimmed.lastIndexOf('/') + 1).trim();
if (tail) hit = idx.get(tail) ?? idx.get(tail.toLowerCase()) ?? idx.get(normalizeBasename(tail));
}
const hit = idx.get(trimmed) ?? idx.get(trimmed.toLowerCase()) ?? idx.get(normalizeBasename(trimmed));
return hit ? [...hit].sort(basenameSort) : [];
}
+27
View File
@@ -292,6 +292,33 @@ describe('runDream — output format', () => {
expect(parsed).toHaveProperty('totals');
});
// #394 / takeover of #854: the embed phase's `[dry-run] Would embed ...`
// summary must not leak onto stdout ahead of the JSON CycleReport.
test('--dry-run --json emits only JSON even when embed has stale chunks', async () => {
await engine.putPage('concepts/testing', {
type: 'concept',
title: 'Testing',
compiled_truth: 'Testing keeps JSON contracts honest.',
timeline: '',
});
await engine.upsertChunks('concepts/testing', [
{ chunk_index: 0, chunk_text: 'Testing keeps JSON contracts honest.', chunk_source: 'compiled_truth' },
]);
const lines: string[] = [];
const logSpy = spyOn(console, 'log').mockImplementation((msg: string) => { lines.push(String(msg)); });
await runDream(engine, ['--dir', repo, '--phase', 'embed', '--dry-run', '--json']);
logSpy.mockRestore();
const output = lines.join('\n');
expect(output.trimStart().startsWith('{')).toBe(true);
const parsed = JSON.parse(output);
expect(parsed.schema_version).toBe('1');
expect(parsed.phases[0].phase).toBe('embed');
// The stale chunk was still counted in the structured report.
expect(parsed.phases[0].details.would_embed).toBe(1);
});
test('human output for clean status mentions "Brain is healthy"', async () => {
const lines: string[] = [];
const logSpy = spyOn(console, 'log').mockImplementation((msg: string) => { lines.push(String(msg)); });
-18
View File
@@ -209,24 +209,6 @@ describe('gbrain extract --stale', () => {
expect(usRows[0]?.eq).toBe(true);
});
test('version-arm floor: page edited BEFORE LINK_EXTRACTOR_VERSION_TS clears after --stale (issue #2576 bug 3)', async () => {
// A page whose updated_at predates the version watermark used to be
// stamped at its updated_at (< versionTs), so the version arm re-fired
// every run — permanently stale. The sweep now floors the stamp at
// versionTs. (The #1768 test above also covers this since the v0.42.x
// VERSION_TS bump moved its date below the watermark, but this pins the
// behavior explicitly so a date "repair" there can't drop coverage.)
await engine.putPage('people/alice', personPage('Alice'));
await engine.executeRaw(`UPDATE pages SET updated_at = '2000-01-01T00:00:00Z' WHERE slug = 'people/alice'`);
expect(await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS })).toBe(1);
await runExtract(engine, ['--stale']);
// Pre-floor this stayed 1 forever (stamp < versionTs → version arm re-fires).
expect(await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS })).toBe(0);
await runExtract(engine, ['--stale']);
expect(await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS })).toBe(0);
});
test('CDX-4 (D2): a link-flush throw aborts the sweep and leaves pages UNSTAMPED', async () => {
await engine.putPage('people/alice', personPage('Alice'));
await engine.putPage('companies/acme', companyPage('Acme', '[Alice](people/alice) founded [Acme](companies/acme).'));
-18
View File
@@ -140,15 +140,6 @@ describe('extractEntityRefs', () => {
expect(wikiRefs[0].needsResolution).toBe(true);
});
test('recognizes ops/ qualified wikilinks (issue #2576 bug 2)', () => {
// `ops` was missing from DIR_PATTERN, so [[ops/...]] fell through to
// the generic 2c pass (needsResolution) instead of being a real ref.
const refs = extractEntityRefs('Deployed via [[ops/services/pointer-agent]].');
expect(refs.length).toBe(1);
expect(refs[0].slug).toBe('ops/services/pointer-agent');
expect(refs[0].needsResolution).toBeUndefined();
});
test('skips qualified-syntax tokens (those belong to 2a)', () => {
// [[wiki:topics/ai]] looks like 2a's qualified shape — even though
// it wouldn't satisfy DIR_PATTERN, 2c must not claim it either
@@ -1078,15 +1069,6 @@ describe('makeResolver — fallback chain', () => {
]);
});
test('resolveBasenameMatches: path-style ref falls back to the tail (issue #2576 bug 2)', async () => {
// normalizeBasename strips slashes, so `runbooks/2026-05-01-pointer-agent`
// used to normalize to a garbage key that never hit the tail-keyed index.
const engine = makeFakeEngineWithSlugs(['ops/changes/2026-05-01-pointer-agent']);
const r = makeResolver(engine);
expect(await r.resolveBasenameMatches!('runbooks/2026-05-01-pointer-agent'))
.toEqual(['ops/changes/2026-05-01-pointer-agent']);
});
test('resolveBasenameMatches: case-insensitive fallback', async () => {
const engine = makeFakeEngineWithSlugs(['companies/fast-weigh']);
const r = makeResolver(engine);