mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-17 10:22:34 +00:00
Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
72b9e9333f |
@@ -1551,24 +1551,6 @@ export async function checkRerankerHealth(engine: BrainEngine): Promise<Check> {
|
||||
};
|
||||
}
|
||||
|
||||
// Historical #2059 rows were logged as `unknown` before missing reranker
|
||||
// auth was classified at the gateway. Surface repeated unknowns instead of
|
||||
// reporting "ok" while every rerank fails open.
|
||||
const unknownFails = failures.filter((f) => f.reason === 'unknown');
|
||||
if (unknownFails.length >= 3) {
|
||||
const setupHint = unknownFails.some((f) => {
|
||||
const summary = String(f.error_summary ?? '');
|
||||
return summary.includes('ZEROENTROPY_API_KEY') || summary.toLowerCase().includes('api key');
|
||||
})
|
||||
? ' Fix: verify ZEROENTROPY_API_KEY and run `gbrain models doctor`.'
|
||||
: '';
|
||||
return {
|
||||
name: 'reranker_health',
|
||||
status: 'warn',
|
||||
message: `${unknownFails.length} unknown reranker failure(s) in last 7 days.${setupHint}`,
|
||||
};
|
||||
}
|
||||
|
||||
return {
|
||||
name: 'reranker_health',
|
||||
status: 'ok',
|
||||
|
||||
+15
-5
@@ -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, pruneDir, isSyncable } from '../core/sync.ts';
|
||||
import { pathToSlug, slugifyPath, 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
|
||||
@@ -269,14 +269,24 @@ 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;
|
||||
|
||||
const s1 = join(fileDir, targetNoExt);
|
||||
if (allSlugs.has(s1)) return s1;
|
||||
// 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 parts = fileDir.split('/').filter(Boolean);
|
||||
for (let strip = 1; strip <= parts.length; strip++) {
|
||||
const ancestor = parts.slice(0, parts.length - strip).join('/');
|
||||
const candidate = ancestor ? join(ancestor, targetNoExt) : targetNoExt;
|
||||
if (allSlugs.has(candidate)) return candidate;
|
||||
const candidate = hit(ancestor ? join(ancestor, targetNoExt) : targetNoExt);
|
||||
if (candidate) return candidate;
|
||||
}
|
||||
|
||||
return null;
|
||||
|
||||
@@ -3656,15 +3656,7 @@ export async function rerank(input: RerankInput): Promise<RerankResult[]> {
|
||||
// whose request/response shape differs from ZE/llama.cpp (e.g. Voyage with
|
||||
// `top_k` / `data[]`) needs separate adapter hooks in a follow-up plan.
|
||||
const url = `${compat.baseURL.replace(/\/$/, '')}${tp.path ?? '/models/rerank'}`;
|
||||
let auth: { apiKey?: string; headers?: Record<string, string> };
|
||||
try {
|
||||
auth = applyResolveAuth(recipe, cfg, 'reranker');
|
||||
} catch (err) {
|
||||
if (err instanceof AIConfigError) {
|
||||
throw new RerankError(err.message, 'auth');
|
||||
}
|
||||
throw err;
|
||||
}
|
||||
const auth = applyResolveAuth(recipe, cfg, 'reranker');
|
||||
// applyResolveAuth returns { apiKey } for Bearer-style auth (SDK's native
|
||||
// path) or { headers } for custom-header providers (Azure). v0.37.6.0:
|
||||
// recipes can ALSO declare default_headers (attribution etc.) which flow
|
||||
|
||||
@@ -14,6 +14,7 @@
|
||||
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
|
||||
@@ -482,14 +483,29 @@ export async function extractPageLinks(
|
||||
// pre-v0.40.8.2 behavior of dropping bare wikilinks outside
|
||||
// DIR_PATTERN.
|
||||
if (ref.needsResolution) {
|
||||
if (!opts.globalBasename || typeof resolver.resolveBasenameMatches !== 'function') {
|
||||
continue;
|
||||
}
|
||||
if (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.
|
||||
const matches = await resolver.resolveBasenameMatches(ref.slug);
|
||||
//
|
||||
// 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);
|
||||
}
|
||||
if (matches.length === 0) continue;
|
||||
const idx = content.indexOf(ref.slug);
|
||||
const context = idx >= 0 ? excerpt(content, idx, 240) : ref.name;
|
||||
|
||||
@@ -154,28 +154,6 @@ describe('gateway.rerank() — happy path', () => {
|
||||
describe('gateway.rerank() — error classification', () => {
|
||||
beforeEach(() => configureZE());
|
||||
|
||||
test('missing required reranker API key → RerankError(auth) before HTTP call', async () => {
|
||||
configureGateway({
|
||||
reranker_model: 'zeroentropyai:zerank-2',
|
||||
env: {},
|
||||
});
|
||||
let called = false;
|
||||
__setRerankTransportForTests(async () => {
|
||||
called = true;
|
||||
return mockResp({ results: [{ index: 0, relevance_score: 0.5 }] });
|
||||
});
|
||||
|
||||
try {
|
||||
await rerank({ query: 'q', documents: ['d'] });
|
||||
throw new Error('should have thrown');
|
||||
} catch (err) {
|
||||
expect(err).toBeInstanceOf(RerankError);
|
||||
expect((err as RerankError).reason).toBe('auth');
|
||||
expect((err as Error).message).toContain('ZEROENTROPY_API_KEY');
|
||||
expect(called).toBe(false);
|
||||
}
|
||||
});
|
||||
|
||||
test('401 → auth', async () => {
|
||||
__setRerankTransportForTests(async () => new Response('Unauthorized', { status: 401 }));
|
||||
try {
|
||||
|
||||
@@ -2,11 +2,6 @@ import { describe, test, expect, beforeAll, afterAll, beforeEach } from 'bun:tes
|
||||
import { mkdirSync, rmSync, writeFileSync } from 'fs';
|
||||
import { join } from 'path';
|
||||
import { tmpdir } from 'os';
|
||||
import * as fs from 'node:fs';
|
||||
import * as os from 'node:os';
|
||||
import * as path from 'node:path';
|
||||
import { withEnv } from './helpers/with-env.ts';
|
||||
import { logRerankFailure } from '../src/core/rerank-audit.ts';
|
||||
|
||||
describe('doctor command', () => {
|
||||
test('doctor module exports runDoctor', async () => {
|
||||
@@ -52,34 +47,6 @@ describe('doctor command', () => {
|
||||
expect(check.issues![0].action).toContain('trigger');
|
||||
});
|
||||
|
||||
test('reranker_health warns on repeated unknown rerank failures', async () => {
|
||||
const { checkRerankerHealth } = await import('../src/commands/doctor.ts');
|
||||
const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gbrain-rerank-doctor-'));
|
||||
try {
|
||||
await withEnv({ GBRAIN_AUDIT_DIR: tmpDir }, async () => {
|
||||
for (let i = 0; i < 3; i++) {
|
||||
logRerankFailure({
|
||||
model: 'zeroentropyai:zerank-2',
|
||||
reason: 'unknown',
|
||||
query_hash: `unknown${i}`,
|
||||
doc_count: 30,
|
||||
error_summary: 'ZeroEntropy reranker requires ZEROENTROPY_API_KEY.',
|
||||
});
|
||||
}
|
||||
const check = await checkRerankerHealth({
|
||||
async getConfig(key: string): Promise<string | null> {
|
||||
return key === 'search.reranker.enabled' ? 'true' : null;
|
||||
},
|
||||
} as any);
|
||||
expect(check.status).toBe('warn');
|
||||
expect(check.message).toContain('unknown');
|
||||
expect(check.message).toContain('ZEROENTROPY_API_KEY');
|
||||
});
|
||||
} finally {
|
||||
fs.rmSync(tmpDir, { recursive: true, force: true });
|
||||
}
|
||||
});
|
||||
|
||||
test('runDoctor accepts null engine for filesystem-only mode', async () => {
|
||||
const { runDoctor } = await import('../src/commands/doctor.ts');
|
||||
// runDoctor should accept null engine — it runs filesystem checks only.
|
||||
|
||||
@@ -389,6 +389,33 @@ 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.
|
||||
|
||||
@@ -9,6 +9,8 @@ import {
|
||||
parseTimelineEntries,
|
||||
isAutoLinkEnabled,
|
||||
FRONTMATTER_LINK_MAP,
|
||||
buildBasenameIndex,
|
||||
queryBasenameIndex,
|
||||
type SlugResolver,
|
||||
} from '../src/core/link-extraction.ts';
|
||||
import type { BrainEngine } from '../src/core/engine.ts';
|
||||
@@ -424,6 +426,46 @@ 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.
|
||||
|
||||
@@ -12,14 +12,9 @@
|
||||
*/
|
||||
|
||||
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
|
||||
import * as fs from 'node:fs';
|
||||
import * as os from 'node:os';
|
||||
import * as path from 'node:path';
|
||||
import { applyReranker, type RerankerOpts } from '../../src/core/search/rerank.ts';
|
||||
import { RerankError, type RerankResult } from '../../src/core/ai/gateway.ts';
|
||||
import { readRecentRerankFailures } from '../../src/core/rerank-audit.ts';
|
||||
import type { SearchResult } from '../../src/core/types.ts';
|
||||
import { withEnv } from '../helpers/with-env.ts';
|
||||
|
||||
function makeResult(slug: string, score: number, chunk: string): SearchResult {
|
||||
return {
|
||||
@@ -165,36 +160,6 @@ describe('applyReranker — fail-open on every RerankError reason', () => {
|
||||
expect(out).toEqual(results);
|
||||
});
|
||||
|
||||
test('missing gateway reranker API key fail-opens and audits auth', async () => {
|
||||
const { configureGateway } = await import('../../src/core/ai/gateway.ts');
|
||||
const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gbrain-rerank-search-'));
|
||||
try {
|
||||
await withEnv({ GBRAIN_AUDIT_DIR: tmpDir }, async () => {
|
||||
configureGateway({
|
||||
reranker_model: 'zeroentropyai:zerank-2',
|
||||
env: {},
|
||||
});
|
||||
|
||||
const results = [makeResult('a', 1.0, 'doc a')];
|
||||
const out = await applyReranker('q', results, {
|
||||
enabled: true,
|
||||
topNIn: 1,
|
||||
topNOut: null,
|
||||
model: 'zeroentropyai:zerank-2',
|
||||
});
|
||||
|
||||
expect(out).toEqual(results);
|
||||
const failures = readRecentRerankFailures(1);
|
||||
expect(failures).toHaveLength(1);
|
||||
expect(failures[0]!.reason).toBe('auth');
|
||||
expect(failures[0]!.error_summary).toContain('ZEROENTROPY_API_KEY');
|
||||
});
|
||||
} finally {
|
||||
fs.rmSync(tmpDir, { recursive: true, force: true });
|
||||
configureGateway({ env: { ZEROENTROPY_API_KEY: 'test-key' } });
|
||||
}
|
||||
});
|
||||
|
||||
test('fail-open on non-RerankError throw too', async () => {
|
||||
const results = [makeResult('a', 1.0, 'a')];
|
||||
const opts: RerankerOpts = {
|
||||
|
||||
Reference in New Issue
Block a user