fix(dream): scope the patterns phase to the cycle's resolved source (#1586) (#4034)

#1586 threaded the cycle's resolved source through the synthesize phase so
subagent-written pages land in that source's (source_id, slug) rows. The
patterns phase was not updated and kept the pre-#1586 shape: it stamped a
literal 'default' on every collected ref and compared the reverse-write path
against a literal 'default'.

On a per-source cycle that files the page against the wrong source. The row is
created under 'default' (the child had no source_id to scope its put_page
calls) while the reverse-write drops the file into the named source's checkout,
because source_id === 'default' selects the brainDir/<slug>.md branch and
brainDir IS that source's checkout. Row and file then disagree about which
source owns the page — what doctor reports as multi_source_drift.

Applies the same threading synthesize.ts already uses: PatternsPhaseOpts gains
sourceId, cycle.ts passes cycleSourceId at the patterns call site the way it
already does for synthesize, the child carries SubagentHandlerData.source_id,
and reverseWriteRefs takes the cycle source as its native source. Unset stays
'default', so unscoped callers are unchanged.
This commit is contained in:
Masa
2026-08-13 05:51:48 -07:00
committed by GitHub
parent 638dd0d247
commit e8785c1ab1
3 changed files with 158 additions and 12 deletions
+7
View File
@@ -2063,6 +2063,13 @@ export async function runCycle(
yieldDuringPhase: opts.yieldDuringPhase,
once: opts.onceForPhase === 'patterns',
deadlineAtMs: opts.deadlineAtMs ?? null,
// #1586: scope pattern writes to the cycle's resolved source, same as
// synthesize above. Without it the child's put_page rows land in
// 'default' while the reverse-write drops the file into the named
// source's checkout — the row and the file disagree about which
// source owns the page, which is what doctor reports as
// multi_source_drift.
sourceId: cycleSourceId,
}));
result.duration_ms = duration_ms;
phaseResults.push(result);
+37 -12
View File
@@ -60,6 +60,13 @@ export interface PatternsPhaseOpts {
* mid-phase and starves every tail phase (#2781).
*/
deadlineAtMs?: number | null;
/**
* #1586: the cycle's resolved source. Stamped onto every subagent child as
* `source_id` so put_page writes land in this source's rows, and passed to
* reverseWriteRefs so getPage/getTags read the correct (source_id, slug)
* row. Unset → legacy 'default'. Mirrors synthesize.ts's `sourceId`.
*/
sourceId?: string;
}
/**
@@ -197,6 +204,9 @@ export async function runPhasePatterns(
model: config.model,
max_turns: 30,
allowed_slug_prefixes: allowedSlugPrefixes,
// #1586: scope every child tool call to the cycle's resolved source so
// put_page writes land there instead of the hardcoded 'default'.
...(opts.sourceId ? { source_id: opts.sourceId } : {}),
};
const submitOpts: Partial<MinionJobInput> = {
max_stalled: 3,
@@ -243,10 +253,14 @@ export async function runPhasePatterns(
// Collect refs the subagent wrote (codex finding #2 — query tool exec rows).
// v0.32.8: refs carry source_id so reverseWriteRefs targets the right
// (source, slug) row instead of the first DB match.
const writtenRefs = await collectChildPutPageSlugs(engine, [job.id]);
// #1586: refs carry the cycle's resolved source (children wrote there via
// SubagentHandlerData.source_id), so getPage/getTags read the same row the
// child wrote, and the reverse-write treats it as the native source.
const cycleSourceId = opts.sourceId ?? 'default';
const writtenRefs = await collectChildPutPageSlugs(engine, [job.id], cycleSourceId);
// Reverse-write to fs.
const reverseWriteCount = await reverseWriteRefs(engine, opts.brainDir, writtenRefs);
const reverseWriteCount = await reverseWriteRefs(engine, opts.brainDir, writtenRefs, cycleSourceId);
const details = {
reflections_considered: reflections.length,
@@ -454,13 +468,14 @@ When done, briefly list the pattern slugs you wrote/updated in your final messag
async function collectChildPutPageSlugs(
engine: BrainEngine,
childIds: number[],
sourceId = 'default',
): Promise<Array<{ slug: string; source_id: string }>> {
if (childIds.length === 0) return [];
// v0.32.8: subagent put_page tool schema doesn't expose source_id (subagents
// are scoped to a single source). Default to 'default' here; multi-source
// dream cycles are a v0.33 follow-up. The point of threading source_id is
// so reverseWriteRefs can pass it through getPage and pick the correct
// (source_id, slug) row instead of whatever the DB happens to return.
// are scoped to a single source). #1586: stamp the cycle's resolved source
// children write there via SubagentHandlerData.source_id — so reverseWriteRefs
// can pass it through getPage and pick the correct (source_id, slug) row
// instead of whatever the DB happens to return. Unset → legacy 'default'.
const rows = await engine.executeRaw<{ slug: string }>(
`SELECT DISTINCT
COALESCE(input->>'slug', (input #>> '{}')::jsonb->>'slug') AS slug
@@ -474,7 +489,7 @@ async function collectChildPutPageSlugs(
return rows
.map(r => r.slug)
.filter((s): s is string => typeof s === 'string' && s.length > 0)
.map(slug => ({ slug, source_id: 'default' }));
.map(slug => ({ slug, source_id: sourceId }));
}
// ── Reverse-write ────────────────────────────────────────────────────
@@ -485,6 +500,7 @@ async function reverseWriteRefs(
engine: BrainEngine,
brainDir: string,
refs: Array<{ slug: string; source_id: string }>,
nativeSourceId = 'default',
): Promise<number> {
let count = 0;
for (const { slug, source_id } of refs) {
@@ -496,11 +512,12 @@ async function reverseWriteRefs(
const tags = await engine.getTags(slug, { sourceId: source_id });
try {
const md = renderPageToMarkdown(page, tags);
// v0.32.8 F6: non-default sources land under brainDir/.sources/<id>/<slug>.md
// so same-slug-different-source pages don't collide on disk. Default-source
// pages stay at brainDir/<slug>.md so single-source brains see no change.
// `.sources/` is a reserved prefix; walkBrainRepo skips dot-dirs.
const filePath = source_id === 'default'
// v0.32.8 F6: foreign-source pages land under brainDir/.sources/<id>/<slug>.md
// so same-slug-different-source pages don't collide on disk. Pages belonging
// to the cycle's own source (#1586: brainDir IS that source's checkout —
// legacy 'default' when unscoped) stay at brainDir/<slug>.md so single-source
// brains see no change. `.sources/` is a reserved prefix; walkBrainRepo skips dot-dirs.
const filePath = source_id === nativeSourceId
? join(brainDir, `${slug}.md`)
: join(brainDir, '.sources', source_id, `${slug}.md`);
mkdirSync(dirname(filePath), { recursive: true });
@@ -558,3 +575,11 @@ function failed(error: PhaseError): PhaseResult {
function makeError(cls: string, code: string, message: string, hint?: string): PhaseError {
return hint ? { class: cls, code, message, hint } : { class: cls, code, message };
}
// `__testing` re-exports otherwise-private helpers so unit tests can pin the
// source-scoping contract (#1586) without driving a whole dream cycle.
// Mirrors synthesize.ts's `__testing` block.
export const __testing = {
collectChildPutPageSlugs,
reverseWriteRefs,
};
+114
View File
@@ -0,0 +1,114 @@
/**
* Regression for #1586's unfixed half: the patterns phase.
*
* #1586 threaded the cycle's resolved source through `synthesize.ts` so dream
* output lands in the named source's `(source_id, slug)` rows. `patterns.ts`
* was left on the pre-#1586 shape: `collectChildPutPageSlugs` stamped a literal
* `'default'` and `reverseWriteRefs` compared against a literal `'default'`.
*
* The result on a per-source cycle was a page filed against the wrong source:
* the ROW is created under `default` (the child had no `source_id` to scope
* its put_page calls), while the reverse-write drops the FILE into the named
* source's checkout — `source_id === 'default'` selected the
* `brainDir/<slug>.md` branch, and on a per-source cycle `brainDir` IS the
* named source's checkout. Row and file then disagree about which source owns
* the page, which is what `doctor` reports as `multi_source_drift`.
*
* These tests pin both halves of the fix, plus the unscoped legacy behavior.
*/
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
import { mkdtempSync, rmSync, existsSync } from 'node:fs';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
import { __testing } from '../src/core/cycle/patterns.ts';
const { collectChildPutPageSlugs, reverseWriteRefs } = __testing;
const SOURCE_ID = 'coast';
const SLUG = 'wiki/personal/patterns/a-pattern';
let engine: PGLiteEngine;
let brainDir: string;
beforeAll(async () => {
engine = new PGLiteEngine();
await engine.connect({});
await engine.initSchema();
brainDir = mkdtempSync(join(tmpdir(), 'gbrain-patterns-scope-'));
const db = (engine as any).db;
await db.exec(`
INSERT INTO sources (id, name, local_path)
VALUES ('${SOURCE_ID}', 'coast', '/tmp/coast-brain')
ON CONFLICT (id) DO NOTHING;
`);
await db.exec(`
INSERT INTO minion_jobs (id, queue, name, data, status)
VALUES (2001, 'default', 'subagent', '{}'::jsonb, 'completed')
ON CONFLICT (id) DO NOTHING;
`);
await db.query(
`INSERT INTO subagent_tool_executions (job_id, message_idx, tool_use_id, tool_name, status, input)
VALUES (2001, 0, 'tool_p1', 'brain_put_page', 'complete', $1::jsonb)`,
[JSON.stringify({ slug: SLUG, body: 'a pattern' })],
);
// The page the child wrote lives in the cycle's source, not in 'default'.
await engine.putPage(SLUG, {
type: 'note',
title: 'A pattern',
compiled_truth: 'a pattern',
} as any, { sourceId: SOURCE_ID });
});
afterAll(async () => {
await engine.disconnect();
rmSync(brainDir, { recursive: true, force: true });
});
describe('#1586: the patterns phase scopes its writes to the cycle source', () => {
test('collected refs carry the cycle source, not a hardcoded default', async () => {
const refs = await collectChildPutPageSlugs(engine as any, [2001], SOURCE_ID);
expect(refs).toHaveLength(1);
expect(refs[0]!.slug).toBe(SLUG);
// Pre-fix this was the literal 'default' no matter which source the cycle
// resolved, which is what filed the page against the wrong source.
expect(refs[0]!.source_id).toBe(SOURCE_ID);
});
test('unscoped callers keep the legacy default source', async () => {
const refs = await collectChildPutPageSlugs(engine as any, [2001]);
expect(refs[0]!.source_id).toBe('default');
});
test('reverse-write resolves the row the child actually wrote', async () => {
const refs = await collectChildPutPageSlugs(engine as any, [2001], SOURCE_ID);
const count = await reverseWriteRefs(engine as any, brainDir, refs, SOURCE_ID);
// The lookup is keyed on the ref's source_id, so a ref carrying the cycle
// source resolves the row the child wrote there.
expect(count).toBe(1);
});
test('the cycle source is native — its pages stay at brainDir/<slug>.md', async () => {
const refs = await collectChildPutPageSlugs(engine as any, [2001], SOURCE_ID);
await reverseWriteRefs(engine as any, brainDir, refs, SOURCE_ID);
expect(existsSync(join(brainDir, `${SLUG}.md`))).toBe(true);
expect(existsSync(join(brainDir, '.sources', SOURCE_ID, `${SLUG}.md`))).toBe(false);
});
test('a foreign source still lands under .sources/<id>/', async () => {
const foreignDir = mkdtempSync(join(tmpdir(), 'gbrain-patterns-foreign-'));
try {
const refs = await collectChildPutPageSlugs(engine as any, [2001], SOURCE_ID);
// brainDir belongs to 'default' here, so 'coast' is foreign to it.
await reverseWriteRefs(engine as any, foreignDir, refs, 'default');
expect(existsSync(join(foreignDir, '.sources', SOURCE_ID, `${SLUG}.md`))).toBe(true);
expect(existsSync(join(foreignDir, `${SLUG}.md`))).toBe(false);
} finally {
rmSync(foreignDir, { recursive: true, force: true });
}
});
});