Compare commits

..
Author SHA1 Message Date
97ddee0548 fix(schema-pack): narrow stats catch-all so masked errors surface, not fake 0 pages (#2466)
fetchCountRows and detectDeadPrefixes in src/core/schema-pack/stats.ts
swallowed EVERY engine error into empty results, so any real failure
printed 'Total pages: 0' + a vacuous 100% coverage on a populated brain.
Both catches now swallow only isUndefinedTableError (pre-init brain,
missing pages table) and rethrow everything else. Four regression tests:
real non-zero count on a populated PGLite brain, rethrow on non-missing-
table errors in both catch sites, and the missing-table degrade path.

Takeover of #2493.

Co-authored-by: javieraldape <javieraldape@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:41:12 -07:00
6 changed files with 109 additions and 110 deletions
+5 -15
View File
@@ -43,7 +43,7 @@ import {
} from '../core/link-extraction.ts';
import { createProgress } from '../core/progress.ts';
import { getCliOptions, cliOptsToProgressOptions } from '../core/cli-options.ts';
import { pathToSlug, slugifyPath, pruneDir, isSyncable } from '../core/sync.ts';
import { pathToSlug, pruneDir, isSyncable } from '../core/sync.ts';
// v0.41.18.0: withRetry + isRetryableConnError + WithRetryOpts moved to
// src/core/retry.ts as the canonical primitive. Engine methods
// (addLinksBatch/addTimelineEntriesBatch/upsertChunks) now self-retry via
@@ -269,24 +269,14 @@ export function extractMarkdownLinks(content: string): { name: string; relTarget
export function resolveSlug(fileDir: string, relTarget: string, allSlugs: Set<string>): string | null {
const targetNoExt = relTarget.endsWith('.md') ? relTarget.slice(0, -3) : relTarget;
// Issue #1964: wikilinks carry raw Obsidian paths (`[[llm-wiki/entities/AI 3.0]]`)
// but allSlugs holds sync-slugified slugs (`llm-wiki/entities/ai-3.0`). Try the
// raw candidate first (back-compat), then the sync-consistent slugified form.
const hit = (candidate: string): string | null => {
if (allSlugs.has(candidate)) return candidate;
const slugified = slugifyPath(candidate);
if (slugified !== candidate && allSlugs.has(slugified)) return slugified;
return null;
};
const s1 = hit(join(fileDir, targetNoExt));
if (s1) return s1;
const s1 = join(fileDir, targetNoExt);
if (allSlugs.has(s1)) return s1;
const parts = fileDir.split('/').filter(Boolean);
for (let strip = 1; strip <= parts.length; strip++) {
const ancestor = parts.slice(0, parts.length - strip).join('/');
const candidate = hit(ancestor ? join(ancestor, targetNoExt) : targetNoExt);
if (candidate) return candidate;
const candidate = ancestor ? join(ancestor, targetNoExt) : targetNoExt;
if (allSlugs.has(candidate)) return candidate;
}
return null;
+4 -20
View File
@@ -14,7 +14,6 @@
import type { BrainEngine } from './engine.ts';
import type { PageType } from './types.ts';
import { ensureWellFormed } from './text-safe.ts';
import { slugifyPath } from './sync.ts';
/**
* v0.42.7 — link-extraction version stamp. Bump this ISO timestamp whenever the
@@ -483,29 +482,14 @@ export async function extractPageLinks(
// pre-v0.40.8.2 behavior of dropping bare wikilinks outside
// DIR_PATTERN.
if (ref.needsResolution) {
if (typeof resolver.resolveBasenameMatches !== 'function') continue;
if (!opts.globalBasename || typeof resolver.resolveBasenameMatches !== 'function') {
continue;
}
// Issue #972 (codex): resolve by the wikilink TARGET (ref.slug — the
// text inside `[[...]]` before any `|`), NOT the display alias
// (ref.name = match[2]). `[[struktura|the project]]` must resolve
// `struktura`, not "the project". The display text is for context only.
//
// Issue #1964: a dir-qualified wikilink (`[[llm-wiki/entities/AI 3.0]]`)
// carries a raw Obsidian path while page slugs are sync-slugified
// (`llm-wiki/entities/ai-3.0`). Slugify the path the same way sync does,
// then match by exact slug or path-suffix (wiki-root-relative authoring).
// This runs regardless of global_basename — it's dir-qualified, so the
// cross-dir false-positive risk the flag guards against doesn't apply.
// Mirrors the FS path's resolveSlug ancestor walk. Bare `[[name]]`
// wikilinks still require the global_basename flag.
let matches: string[] = [];
const slugified = ref.slug.includes('/') ? slugifyPath(ref.slug) : '';
if (slugified.includes('/')) {
const tail = slugified.slice(slugified.lastIndexOf('/') + 1);
matches = (await resolver.resolveBasenameMatches(tail))
.filter(m => m === slugified || m.endsWith(`/${slugified}`));
} else if (opts.globalBasename) {
matches = await resolver.resolveBasenameMatches(ref.slug);
}
const matches = await resolver.resolveBasenameMatches(ref.slug);
if (matches.length === 0) continue;
const idx = content.indexOf(ref.slug);
const context = idx >= 0 ? excerpt(content, idx, 240) : ref.name;
+17 -6
View File
@@ -18,6 +18,7 @@
import type { BrainEngine } from '../engine.ts';
import { loadActivePackBestEffort } from './best-effort.ts';
import type { OperationContext } from '../operations.ts';
import { isUndefinedTableError } from '../utils.ts';
export interface StatsOpts {
/** Single source scope. Omit + omit sourceIds for whole-brain aggregate. */
@@ -164,9 +165,17 @@ async function fetchCountRows(engine: BrainEngine, opts: StatsOpts): Promise<Raw
`;
try {
return await engine.executeRaw<RawCountRow>(sql, params);
} catch {
// Empty / pre-init brain: pages table may not exist yet.
return [];
} catch (err) {
// ONLY swallow the genuine "pages table doesn't exist yet" case
// (empty / pre-init brain). #2466: the old bare `catch {}` masked
// EVERY error — so any engine-level failure (connection, version
// skew, a query incompatibility) was silently converted to 0 rows,
// printing "Total pages: 0" on a populated brain and cascading into
// false "100% coverage" + a starved `schema suggest`. Surface
// everything that is not a missing-table error so the real failure
// is visible instead of hidden behind a fake zero.
if (isUndefinedTableError(err)) return [];
throw err;
}
}
@@ -204,9 +213,11 @@ async function detectDeadPrefixes(
if (cnt === 0) {
hints.push({ type: t.name, prefix });
}
} catch {
// Skip on engine error (no pages table yet, etc.).
continue;
} catch (err) {
// #2466: only skip on the genuine "no pages table yet" case;
// rethrow any other engine error so it isn't silently masked.
if (isUndefinedTableError(err)) continue;
throw err;
}
}
}
-27
View File
@@ -389,33 +389,6 @@ describe('resolveSlugAll', () => {
});
});
// ─── issue #1964: cross-directory wikilinks — slug/path mismatch ──────────
describe('issue #1964: raw Obsidian wikilink paths resolve to sync-slugified slugs', () => {
test('resolveSlug slugifies the candidate (sync-consistent), no flag needed', () => {
const all = new Set(['llm-wiki/entities/ai-3.0']);
// Wikilink literal `[[llm-wiki/entities/AI 3.0]]` — spaces + uppercase.
expect(resolveSlug('llm-wiki/notes', 'llm-wiki/entities/AI 3.0.md', all))
.toBe('llm-wiki/entities/ai-3.0');
});
test('resolveSlug slugifies raw (unslugified) fileDir too', () => {
const all = new Set(['llm-wiki/entities/ai-3.0']);
// fileDir comes from dirname(relPath) — the raw on-disk directory.
expect(resolveSlug('LLM Wiki/Notes', 'entities/AI 3.0.md', all))
.toBe('llm-wiki/entities/ai-3.0');
});
test('extractLinksFromFile resolves cross-directory wikilink with flag OFF as a typed edge', async () => {
const allSlugs = new Set(['llm-wiki/entities/ai-3.0', 'llm-wiki/notes/roadmap']);
const content = '---\ntitle: Roadmap\ntype: concept\n---\n\nSee [[llm-wiki/entities/AI 3.0]].\n';
const links = await extractLinksFromFile(content, 'llm-wiki/notes/roadmap.md', allSlugs);
expect(links.map(l => l.to_slug)).toEqual(['llm-wiki/entities/ai-3.0']);
// Dir-qualified path resolution is exact, NOT the basename fallback.
expect(links[0].link_type).not.toBe('wikilink_basename');
});
});
describe('issue #972 repro: bare wikilinks resolve when flag is on', () => {
// End-to-end: reproduces the issue's exact repro inside a tempdir +
// PGLite, then asserts edge count under both flag states.
-42
View File
@@ -9,8 +9,6 @@ import {
parseTimelineEntries,
isAutoLinkEnabled,
FRONTMATTER_LINK_MAP,
buildBasenameIndex,
queryBasenameIndex,
type SlugResolver,
} from '../src/core/link-extraction.ts';
import type { BrainEngine } from '../src/core/engine.ts';
@@ -426,46 +424,6 @@ describe('extractPageLinks', () => {
expect(strk!.linkType).toBe('wikilink_basename');
});
// ─── issue #1964: dir-qualified wikilinks with raw Obsidian paths ────────
test('#1964: dir-qualified wikilink resolves via sync-consistent slugification (flag OFF)', async () => {
// `[[llm-wiki/entities/AI 3.0]]` is a raw Obsidian path; the page slug
// is the sync-slugified `llm-wiki/entities/ai-3.0`. Must resolve WITHOUT
// global_basename (it's dir-qualified) and must NOT leak to a same-tail
// page in a different directory.
const resolver: SlugResolver = {
resolve: async () => null,
resolveBasenameMatches: async (name) =>
name === 'ai-3.0' ? ['other/ai-3.0', 'llm-wiki/entities/ai-3.0'] : [],
};
const { candidates } = await extractPageLinks(
'llm-wiki/notes/roadmap',
'See [[llm-wiki/entities/AI 3.0]] for the model.',
{}, 'concept', resolver,
// opts.globalBasename omitted (= false) — path is dir-qualified
);
expect(candidates.map(c => c.targetSlug)).toEqual(['llm-wiki/entities/ai-3.0']);
expect(candidates[0].linkType).toBe('wikilink_basename');
expect(candidates[0].linkSource).toBe('wikilink-resolved');
});
test('#1964: path-suffix match resolves wiki-root-relative paths against a real index', async () => {
// Author writes `[[llm-wiki/entities/AI 3.0]]` but the brain nests the
// wiki under a vault dir. Suffix match rescues it; queried through the
// REAL basename index so the tail-key lookup is exercised end to end.
const idx = buildBasenameIndex(['vault/llm-wiki/entities/ai-3.0', 'people/ai-3.0']);
const resolver: SlugResolver = {
resolve: async () => null,
resolveBasenameMatches: async (name) => queryBasenameIndex(idx, name),
};
const { candidates } = await extractPageLinks(
'vault/llm-wiki/notes/roadmap',
'See [[llm-wiki/entities/AI 3.0]].',
{}, 'concept', resolver,
);
expect(candidates.map(c => c.targetSlug)).toEqual(['vault/llm-wiki/entities/ai-3.0']);
});
test('opts.skipFrontmatter suppresses the frontmatter pass', async () => {
// Real resolver shape that WOULD resolve frontmatter source: too,
// but skipFrontmatter blocks the path entirely.
+83
View File
@@ -222,6 +222,89 @@ describe('runStatsCore — JSON envelope shape', () => {
});
});
describe('runStatsCore — #2466 catch-narrowing (real count + error surfacing)', () => {
// #2466: `gbrain schema stats` reported "Total pages: 0" on a populated
// PGLite brain. The bug was a bare `catch {}` in fetchCountRows (and a
// sibling in detectDeadPrefixes) that converted ANY engine error into 0
// rows. The COUNT query itself is valid on PGLite (proven below), so the
// regression pins two things: (a) a populated brain reports the real,
// non-zero count through the full runStatsCore path; (b) a non-missing-
// table engine error is rethrown, not masked into a fake zero.
it('reports the real non-zero count on a populated PGLite brain (no false 0)', async () => {
await withEnv({ GBRAIN_SCHEMA_PACK: undefined }, async () => {
// Seed a realistic mix: typed, untyped, multiple types — like the
// 169-page brain in the bug report (scaled down).
for (let i = 0; i < 12; i++) {
const type = i % 3 === 0 ? '' : (i % 3 === 1 ? 'person' : 'company');
await seedPage(`notes/p${i}`, { type, sourcePath: `notes/p${i}.md` });
}
const result = await runStatsCore(ctxOf());
// The core regression: NOT zero.
expect(result.aggregate.total_pages).toBe(12);
expect(result.aggregate.typed_pages).toBe(8);
expect(result.aggregate.untyped_pages).toBe(4);
// And coverage is the honest ratio, not the vacuous 1.0 a 0/0 prints.
expect(result.aggregate.coverage).not.toBe(1.0);
});
});
it('fetchCountRows rethrows a non-missing-table engine error instead of masking it as 0 pages', async () => {
await withEnv({ GBRAIN_SCHEMA_PACK: undefined }, async () => {
// No pack → detectDeadPrefixes is skipped, isolating the throw to the
// fetchCountRows catch we narrowed. The count query (the GROUP BY one)
// throws a column-level error (SQLSTATE 42703) — the exact class the
// old bare `catch {}` swallowed into 0 rows; everything else succeeds.
__setPackLocatorForTests(() => null);
const boom = Object.assign(new Error('column "type" does not exist'), { code: '42703' });
const stubEngine = {
executeRaw: async (sql: string) => {
if (/GROUP BY source_id/.test(sql)) throw boom; // the fetchCountRows query
return [];
},
} as unknown as PGLiteEngine;
const ctx = { ...ctxOf(), engine: stubEngine } as unknown as OperationContext;
await expect(runStatsCore(ctx)).rejects.toThrow('column "type" does not exist');
});
});
it('fetchCountRows still degrades to empty (no throw) on a genuine missing pages table', async () => {
await withEnv({ GBRAIN_SCHEMA_PACK: undefined }, async () => {
// Pre-init brain shape: the count query hits a missing pages table
// (SQLSTATE 42P01). This is the ONLY case the narrowed catch swallows.
__setPackLocatorForTests(() => null);
const missing = Object.assign(new Error('relation "pages" does not exist'), { code: '42P01' });
const stubEngine = {
executeRaw: async (sql: string) => {
if (/GROUP BY source_id/.test(sql)) throw missing;
return [];
},
} as unknown as PGLiteEngine;
const ctx = { ...ctxOf(), engine: stubEngine } as unknown as OperationContext;
const result = await runStatsCore(ctx);
expect(result.aggregate.total_pages).toBe(0);
expect(result.per_source).toEqual([]);
});
});
it('detectDeadPrefixes rethrows a non-missing-table error (sibling catch)', async () => {
await withEnv({ GBRAIN_HOME: tmpDir, GBRAIN_SCHEMA_PACK: 'tiny' }, async () => {
seedTinyPack('tiny', [{ name: 'person', prefix: 'people/' }]);
// fetchCountRows (the GROUP BY query) succeeds → []; the per-prefix
// dead-prefix LIKE query then throws a non-missing-table error, which
// must surface through the narrowed sibling catch.
const stubEngine = {
executeRaw: async (sql: string) => {
if (/GROUP BY source_id/.test(sql)) return []; // count query: empty brain, fine
throw Object.assign(new Error('division by zero'), { code: '22012' }); // the LIKE query
},
} as unknown as PGLiteEngine;
const ctx = { ...ctxOf(), engine: stubEngine } as unknown as OperationContext;
await expect(runStatsCore(ctx)).rejects.toThrow('division by zero');
});
});
});
describe('runStatsCore — type/untyped split', () => {
it('treats empty-string type as untyped (not its own bucket)', async () => {
await withEnv({ GBRAIN_SCHEMA_PACK: undefined }, async () => {