mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-16 18:02:30 +00:00
Compare commits
2
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
303bbfb0b8 | ||
|
|
9efe229eee |
+18
-1
@@ -509,8 +509,12 @@ export function extractTimelineFromContent(content: string, slug: string): Extra
|
||||
// DB-level uniqueness cannot collapse.
|
||||
const citationPattern = /\[Source:\s*([^\]]+?),\s*(\d{4}-\d{2}-\d{2})\s*\]/g;
|
||||
const bulletLinePattern = /^-\s+\*\*\d{4}-\d{2}-\d{2}\*\*\s*\|/;
|
||||
// Lines captured by Format 4 (plain bullet) are skipped for the same
|
||||
// reason: quality.md mandates a trailing [Source: ...] on those bullets,
|
||||
// and re-extracting the citation would double-count the event.
|
||||
const plainBulletLinePattern = /^-\s+\d{4}-\d{2}-\d{2}\s*[—–-]/;
|
||||
for (const line of content.split(/\r?\n/)) {
|
||||
if (bulletLinePattern.test(line)) continue;
|
||||
if (bulletLinePattern.test(line) || plainBulletLinePattern.test(line)) continue;
|
||||
const lineMatches = [...line.matchAll(citationPattern)];
|
||||
if (lineMatches.length === 0) continue;
|
||||
// Strip every citation marker from the line to leave the annotated text.
|
||||
@@ -526,6 +530,19 @@ export function extractTimelineFromContent(content: string, slug: string): Extra
|
||||
}
|
||||
}
|
||||
|
||||
// Format 4: Plain bullet — - YYYY-MM-DD — Summary
|
||||
// This is the format gbrain's own enrich skill writes (no bold, no source
|
||||
// pipe). Without it, every brain-authored timeline entry is invisible to
|
||||
// extraction and timeline_coverage stays at 0%. Anchored at line start so a
|
||||
// date inside a summary/link cannot start a spurious entry; a bold Format-1
|
||||
// line (`- **…**`) cannot match here (a `*` follows the bullet, not a
|
||||
// digit), and the citation loop above skips these lines, so a plain bullet
|
||||
// carrying its own [Source: ...] files exactly one entry.
|
||||
const plainBulletPattern = /^-\s+(\d{4}-\d{2}-\d{2})\s*[—–-]\s*(.+)$/gm;
|
||||
while ((match = plainBulletPattern.exec(content)) !== null) {
|
||||
entries.push({ slug, date: match[1], source: 'markdown', summary: match[2].trim() });
|
||||
}
|
||||
|
||||
return entries;
|
||||
}
|
||||
|
||||
|
||||
@@ -197,7 +197,7 @@ export interface SyncResult {
|
||||
/** Pages re-embedded during this sync's auto-embed step. 0 if --no-embed or skipped. */
|
||||
embedded: number;
|
||||
pagesAffected: string[];
|
||||
failedFiles?: number; // count of per-file import/sync failures (Bug 9)
|
||||
failedFiles?: number; // count of parse failures (Bug 9)
|
||||
/**
|
||||
* v0.41.13.0 partial-sync fields (only set when status === 'partial').
|
||||
*
|
||||
@@ -3183,7 +3183,7 @@ async function performSyncInner(engine: BrainEngine, opts: SyncOpts): Promise<Sy
|
||||
await clearOpCheckpoint(engine, ckpt.target);
|
||||
};
|
||||
|
||||
// issue #1939 adversarial finding #1: a file that failed to import (open ledger
|
||||
// issue #1939 adversarial finding #1: a file that failed to parse (open ledger
|
||||
// row) and is then deleted/renamed-away never re-enters failedFiles and never
|
||||
// imports, so its row would never clear and would age doctor to a permanent
|
||||
// FAIL. Treat removed paths as resolved so the ledger self-heals.
|
||||
@@ -3215,9 +3215,9 @@ async function performSyncInner(engine: BrainEngine, opts: SyncOpts): Promise<Sy
|
||||
} else {
|
||||
const fileFailCount = failedFiles.filter(f => isSkippablePath(f.path)).length;
|
||||
serr(
|
||||
`\nSync blocked: ${fileFailCount} file(s) failed to import:\n` +
|
||||
`\nSync blocked: ${fileFailCount} file(s) failed to parse:\n` +
|
||||
`${codeBreakdown}\n\n` +
|
||||
`Fix the listed file errors and re-run, or use 'gbrain sync --skip-failed' to ` +
|
||||
`Fix the frontmatter and re-run, or use 'gbrain sync --skip-failed' to ` +
|
||||
`acknowledge and move on. A file that keeps failing auto-skips after ` +
|
||||
`${resolveAutoSkipThreshold()} consecutive syncs.`,
|
||||
);
|
||||
@@ -5355,7 +5355,7 @@ function printSyncResult(result: SyncResult, sink: NodeJS.WriteStream = process.
|
||||
case 'dry_run':
|
||||
break; // already printed in performSync
|
||||
case 'blocked_by_failures':
|
||||
write(`Sync BLOCKED at ${result.toCommit.slice(0, 8)}: ${result.failedFiles ?? 0} file(s) failed to import.`);
|
||||
write(`Sync BLOCKED at ${result.toCommit.slice(0, 8)}: ${result.failedFiles ?? 0} file(s) failed to parse.`);
|
||||
write(` See ~/.gbrain/sync-failures.jsonl for details, or run 'gbrain doctor'.`);
|
||||
write(` Fix the files then re-run 'gbrain sync', or 'gbrain sync --skip-failed' to move on.`);
|
||||
break;
|
||||
|
||||
@@ -1103,6 +1103,11 @@ export interface TimelineCandidate {
|
||||
// Match: `- **YYYY-MM-DD** | summary` or `- **YYYY-MM-DD** -- summary`
|
||||
// or `- **YYYY-MM-DD** - summary` or just `**YYYY-MM-DD** | summary`.
|
||||
const TIMELINE_LINE_RE = /^\s*-?\s*\*\*(\d{4}-\d{2}-\d{2})\*\*\s*[|\-–—]+\s*(.+?)\s*$/;
|
||||
// Plain bullet: `- YYYY-MM-DD — summary` (no bold, no source pipe). Kept in
|
||||
// sync with extractTimelineFromContent's Format 4 (the fs-source path).
|
||||
// Anchored flush-left so a date inside an indented continuation line cannot
|
||||
// start a spurious entry.
|
||||
const PLAIN_TIMELINE_LINE_RE = /^-\s+(\d{4}-\d{2}-\d{2})\s*[—–-]\s*(.+?)\s*$/;
|
||||
|
||||
/**
|
||||
* Parse timeline entries from content. Looks at:
|
||||
@@ -1119,7 +1124,7 @@ export function parseTimelineEntries(content: string): TimelineCandidate[] {
|
||||
|
||||
let i = 0;
|
||||
while (i < lines.length) {
|
||||
const m = TIMELINE_LINE_RE.exec(lines[i]);
|
||||
const m = TIMELINE_LINE_RE.exec(lines[i]) ?? PLAIN_TIMELINE_LINE_RE.exec(lines[i]);
|
||||
if (!m) {
|
||||
i++;
|
||||
continue;
|
||||
@@ -1136,7 +1141,7 @@ export function parseTimelineEntries(content: string): TimelineCandidate[] {
|
||||
let j = i + 1;
|
||||
while (j < lines.length) {
|
||||
const next = lines[j];
|
||||
if (TIMELINE_LINE_RE.test(next)) break;
|
||||
if (TIMELINE_LINE_RE.test(next) || PLAIN_TIMELINE_LINE_RE.test(next)) break;
|
||||
if (/^#{1,6}\s/.test(next)) break;
|
||||
if (next.trim().length === 0 && detailLines.length === 0) {
|
||||
// skip leading blank line; if we hit a blank after detail content
|
||||
@@ -1166,7 +1171,7 @@ export function parseTimelineEntries(content: string): TimelineCandidate[] {
|
||||
// bullet pass are skipped (a bullet often carries its own citation).
|
||||
const citationRe = /\[Source:\s*([^\]]+?),\s*(\d{4}-\d{2}-\d{2})\s*\]/g;
|
||||
for (const line of lines) {
|
||||
if (TIMELINE_LINE_RE.test(line)) continue;
|
||||
if (TIMELINE_LINE_RE.test(line) || PLAIN_TIMELINE_LINE_RE.test(line)) continue;
|
||||
const matches = [...line.matchAll(citationRe)];
|
||||
if (matches.length === 0) continue;
|
||||
const summary = line
|
||||
|
||||
@@ -1058,16 +1058,6 @@ export class PGLiteEngine implements BrainEngine {
|
||||
RETURNING id, source_id, slug, type, title, compiled_truth, timeline, frontmatter, content_hash, created_at, updated_at, effective_date, effective_date_source, import_filename, source_kind, source_uri, ingested_via, ingested_at`,
|
||||
[sourceId, slug, page.type, pageKind, page.title, page.compiled_truth, page.timeline || '', JSON.stringify(frontmatter), hash, effectiveDate, effectiveDateSource, importFilename, chunkerVersion, sourcePath, sourceKind, sourceUri, ingestedVia, ingestedAt]
|
||||
);
|
||||
// #2189: an INSERT … ON CONFLICT DO UPDATE … RETURNING that yields 0 rows
|
||||
// (e.g. a BEFORE trigger suppressing the write) previously crashed in
|
||||
// rowToPage with an opaque "undefined is not an object (row.deleted_at)".
|
||||
// Throw a diagnosable error naming the row instead. Mirrors postgres-engine.ts.
|
||||
if (!rows[0]) {
|
||||
throw new Error(
|
||||
`putPage: INSERT … RETURNING produced no row for slug='${slug}' source_id='${sourceId}'. ` +
|
||||
`A trigger or rule on the pages table may be suppressing the write.`
|
||||
);
|
||||
}
|
||||
return rowToPage(rows[0] as Record<string, unknown>);
|
||||
}
|
||||
|
||||
|
||||
@@ -1119,16 +1119,6 @@ export class PostgresEngine implements BrainEngine {
|
||||
ingested_at = COALESCE(EXCLUDED.ingested_at, pages.ingested_at)
|
||||
RETURNING id, source_id, slug, type, title, compiled_truth, timeline, frontmatter, content_hash, created_at, updated_at, effective_date, effective_date_source, import_filename, source_kind, source_uri, ingested_via, ingested_at
|
||||
`;
|
||||
// #2189: an INSERT … ON CONFLICT DO UPDATE … RETURNING that yields 0 rows
|
||||
// (e.g. a BEFORE trigger suppressing the write) previously crashed in
|
||||
// rowToPage with an opaque "undefined is not an object (row.deleted_at)".
|
||||
// Throw a diagnosable error naming the row instead. Mirrors pglite-engine.ts.
|
||||
if (!rows[0]) {
|
||||
throw new Error(
|
||||
`putPage: INSERT … RETURNING produced no row for slug='${slug}' source_id='${sourceId}'. ` +
|
||||
`A trigger or rule on the pages table may be suppressing the write.`
|
||||
);
|
||||
}
|
||||
return rowToPage(rows[0]);
|
||||
}
|
||||
|
||||
|
||||
@@ -185,6 +185,49 @@ describe('extractTimelineFromContent', () => {
|
||||
expect(entries).toHaveLength(1);
|
||||
expect(entries[0].summary).toBe('Landed the enterprise pilot with acme-example.');
|
||||
});
|
||||
|
||||
// Format 4: the plain bullet `- YYYY-MM-DD — Summary` that gbrain's own
|
||||
// enrich skill writes. Before this was supported, every brain-authored
|
||||
// timeline entry was invisible and timeline_coverage was stuck at 0%.
|
||||
it('extracts plain bullet format (- YYYY-MM-DD — Summary)', () => {
|
||||
const content = `## Timeline\n- 2026-06-01 — Catch-up call with alice-example; intros offered.`;
|
||||
const entries = extractTimelineFromContent(content, 'people/alice-example');
|
||||
expect(entries).toHaveLength(1);
|
||||
expect(entries[0].date).toBe('2026-06-01');
|
||||
expect(entries[0].source).toBe('markdown');
|
||||
expect(entries[0].summary).toBe('Catch-up call with alice-example; intros offered.');
|
||||
});
|
||||
|
||||
it('files exactly one entry for a plain bullet that carries its own citation', () => {
|
||||
// quality.md mandates this shape; it must not double-count via the
|
||||
// citation arm (Format 3) AND the plain-bullet arm (Format 4).
|
||||
const content = `- 2026-05-31 — Confirmed full name. [Source: User, 2026-05-31]`;
|
||||
const entries = extractTimelineFromContent(content, 'people/charlie-example');
|
||||
expect(entries).toHaveLength(1);
|
||||
expect(entries[0].date).toBe('2026-05-31');
|
||||
expect(entries[0].source).toBe('markdown');
|
||||
expect(entries[0].summary).toContain('Confirmed full name.');
|
||||
});
|
||||
|
||||
it('does not double-count bold (Format 1) lines as plain bullets', () => {
|
||||
const content = `- **2025-03-18** | Meeting — Discussed partnership`;
|
||||
const entries = extractTimelineFromContent(content, 'test');
|
||||
expect(entries).toHaveLength(1);
|
||||
expect(entries[0].source).toBe('Meeting');
|
||||
});
|
||||
|
||||
it('does not start a spurious entry from a date inside a summary', () => {
|
||||
const content = `- 2026-06-01 — See [meeting](meetings/2026-06-01).`;
|
||||
const entries = extractTimelineFromContent(content, 'people/alice-example');
|
||||
expect(entries).toHaveLength(1);
|
||||
expect(entries[0].date).toBe('2026-06-01');
|
||||
});
|
||||
|
||||
it('handles en dash and hyphen separators in plain bullets', () => {
|
||||
const content = `- 2026-06-01 – First\n- 2026-06-02 - Second`;
|
||||
const entries = extractTimelineFromContent(content, 'test');
|
||||
expect(entries).toHaveLength(2);
|
||||
});
|
||||
});
|
||||
|
||||
describe('walkMarkdownFiles', () => {
|
||||
|
||||
@@ -720,6 +720,30 @@ More prose here.
|
||||
const entries = parseTimelineEntries(content);
|
||||
expect(entries.length).toBe(2);
|
||||
});
|
||||
|
||||
// Plain bullet (extract.ts Format 4 parity — the db-source path must see
|
||||
// the same entries as the fs-source path).
|
||||
test('parses plain bullet: - YYYY-MM-DD — summary', () => {
|
||||
const entries = parseTimelineEntries('## Timeline\n- 2026-06-01 — Catch-up call with alice-example');
|
||||
expect(entries.length).toBe(1);
|
||||
expect(entries[0].date).toBe('2026-06-01');
|
||||
expect(entries[0].summary).toBe('Catch-up call with alice-example');
|
||||
});
|
||||
|
||||
test('files exactly one entry for a plain bullet carrying its own citation', () => {
|
||||
const entries = parseTimelineEntries('- 2026-05-31 — Confirmed full name. [Source: User, 2026-05-31]');
|
||||
expect(entries.length).toBe(1);
|
||||
expect(entries[0].date).toBe('2026-05-31');
|
||||
});
|
||||
|
||||
test('skips invalid dates in plain bullets', () => {
|
||||
expect(parseTimelineEntries('- 2026-13-45 — Bad date').length).toBe(0);
|
||||
});
|
||||
|
||||
test('does not double-count a bold bullet as a plain bullet', () => {
|
||||
const entries = parseTimelineEntries('- **2026-01-15** | Met with Alice');
|
||||
expect(entries.length).toBe(1);
|
||||
});
|
||||
});
|
||||
|
||||
// ─── isAutoLinkEnabled ─────────────────────────────────────────
|
||||
|
||||
@@ -1,74 +0,0 @@
|
||||
// #2189 regression guard: putPage's INSERT … ON CONFLICT DO UPDATE … RETURNING
|
||||
// can yield 0 rows when brain-local DB state (e.g. a BEFORE INSERT trigger)
|
||||
// suppresses the write. Pre-fix, rowToPage(rows[0]) crashed with the opaque
|
||||
// "undefined is not an object (evaluating 'row.deleted_at')" that failed
|
||||
// ~all files of a code sync. Post-fix, putPage throws a descriptive error
|
||||
// naming the slug + source_id so the failure is diagnosable per-file.
|
||||
//
|
||||
// Same guard lands in postgres-engine.ts (engine-parity invariant); this test
|
||||
// exercises the PGLite side, where the issue was reported.
|
||||
|
||||
import { describe, expect, test, beforeAll, afterAll } from 'bun:test';
|
||||
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
|
||||
|
||||
let engine: PGLiteEngine;
|
||||
|
||||
beforeAll(async () => {
|
||||
engine = new PGLiteEngine();
|
||||
await engine.connect({});
|
||||
await engine.initSchema();
|
||||
// Simulate the reporter's state-dependent failure: a trigger that
|
||||
// suppresses inserts for one slug, making RETURNING produce no row.
|
||||
await engine.executeRaw(`
|
||||
CREATE OR REPLACE FUNCTION suppress_pages_insert() RETURNS trigger AS $$
|
||||
BEGIN
|
||||
IF NEW.slug = 'suppressed-page' THEN RETURN NULL; END IF;
|
||||
RETURN NEW;
|
||||
END;
|
||||
$$ LANGUAGE plpgsql;
|
||||
`);
|
||||
await engine.executeRaw(`
|
||||
CREATE TRIGGER suppress_pages_insert_trg
|
||||
BEFORE INSERT ON pages
|
||||
FOR EACH ROW EXECUTE FUNCTION suppress_pages_insert();
|
||||
`);
|
||||
});
|
||||
|
||||
afterAll(async () => {
|
||||
await engine.executeRaw('DROP TRIGGER IF EXISTS suppress_pages_insert_trg ON pages');
|
||||
await engine.executeRaw('DROP FUNCTION IF EXISTS suppress_pages_insert');
|
||||
await engine.disconnect();
|
||||
});
|
||||
|
||||
describe('putPage RETURNING guard (#2189)', () => {
|
||||
test('0-row RETURNING throws a descriptive error, not row.deleted_at TypeError', async () => {
|
||||
let err: Error | undefined;
|
||||
try {
|
||||
await engine.putPage('suppressed-page', {
|
||||
type: 'code',
|
||||
title: 'Suppressed',
|
||||
compiled_truth: 'x',
|
||||
timeline: '',
|
||||
});
|
||||
} catch (e) {
|
||||
err = e as Error;
|
||||
}
|
||||
expect(err).toBeDefined();
|
||||
expect(err!.message).toContain('putPage');
|
||||
expect(err!.message).toContain("slug='suppressed-page'");
|
||||
expect(err!.message).toContain("source_id='default'");
|
||||
// The pre-fix crash signature must be gone.
|
||||
expect(err!.message).not.toContain('deleted_at');
|
||||
});
|
||||
|
||||
test('unsuppressed slugs still upsert normally with the trigger installed', async () => {
|
||||
const page = await engine.putPage('normal-page', {
|
||||
type: 'concept',
|
||||
title: 'Normal',
|
||||
compiled_truth: 'y',
|
||||
timeline: '',
|
||||
});
|
||||
expect(page.slug).toBe('normal-page');
|
||||
expect(page.source_id).toBe('default');
|
||||
});
|
||||
});
|
||||
@@ -375,31 +375,6 @@ describe('performSync dry-run never writes', () => {
|
||||
expect(messages.some(m => m.includes('git pull failed'))).toBe(false);
|
||||
});
|
||||
|
||||
test('first PGLite code sync imports code files without runtime failures', async () => {
|
||||
const { performSync } = await import('../src/commands/sync.ts');
|
||||
mkdirSync(join(repoPath, 'src'), { recursive: true });
|
||||
writeFileSync(
|
||||
join(repoPath, 'src/example.ts'),
|
||||
'export function add(left: number, right: number) { return left + right; }\n',
|
||||
);
|
||||
execSync('git add -A && git commit -m "add code file"', { cwd: repoPath, stdio: 'pipe' });
|
||||
|
||||
const result = await performSync(engine, {
|
||||
repoPath,
|
||||
noPull: true,
|
||||
noEmbed: true,
|
||||
noExtract: true,
|
||||
strategy: 'code',
|
||||
});
|
||||
|
||||
expect(result.status).toBe('first_sync');
|
||||
expect(result.added).toBe(1);
|
||||
expect(result.failedFiles ?? 0).toBe(0);
|
||||
const page = await engine.getPage('src-example-ts');
|
||||
expect(page?.type).toBe('code');
|
||||
expect(page?.frontmatter).toMatchObject({ file: 'src/example.ts', language: 'typescript' });
|
||||
});
|
||||
|
||||
test('incremental dry-run does NOT write to DB or advance the bookmark', async () => {
|
||||
const { performSync } = await import('../src/commands/sync.ts');
|
||||
// First do a real sync to seed the bookmark.
|
||||
|
||||
Reference in New Issue
Block a user