mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-17 10:22:34 +00:00
Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
78cc6d1e84 |
@@ -56,36 +56,6 @@ export const litellmProxy: Recipe = {
|
||||
cost_per_1m_output_usd: undefined,
|
||||
price_last_verified: '2026-06-14',
|
||||
},
|
||||
// LiteLLM normalizes Cohere / Voyage / Jina / etc. rerank backends to the
|
||||
// same wire shape gbrain's gateway.rerank() already speaks (the
|
||||
// ZeroEntropy/llama.cpp contract):
|
||||
// { model, query, documents, top_n } → { results: [{ index, relevance_score }] }
|
||||
// So any rerank model the user registers in their LiteLLM config is
|
||||
// reachable via `gbrain config set search.reranker.model litellm:<model>`
|
||||
// with no request/response adapter — same as embeddings ride the proxy.
|
||||
reranker: {
|
||||
models: [], // user-provided; whatever rerank models the proxy serves
|
||||
// No canonical default — the proxy defines its own model ids. The user
|
||||
// sets search.reranker.model explicitly (mirrors the embedding
|
||||
// touchpoint's user_provided_models contract).
|
||||
default_model: '',
|
||||
// The proxied backend bills (Cohere/Voyage/…); pricing-unknown is the
|
||||
// honest state — same stance as this recipe's embedding/chat
|
||||
// touchpoints and budget-tracker's deliberate litellm exclusion from
|
||||
// the free-provider sets.
|
||||
cost_per_1m_tokens_usd: undefined,
|
||||
price_last_verified: '2026-06-27',
|
||||
max_payload_bytes: 5_000_000,
|
||||
// LEAF path only (matches llama-server-reranker's convention). LiteLLM
|
||||
// serves both `/rerank` and `/v1/rerank`, and LITELLM_BASE_URL may be
|
||||
// set with or without the `/v1` suffix (the setup_hint allows both), so
|
||||
// the leaf form yields a valid route either way:
|
||||
// http://localhost:4000 + /rerank → /rerank ✓
|
||||
// http://localhost:4000/v1 + /rerank → /v1/rerank ✓
|
||||
// Pinning '/v1/rerank' here would double to /v1/v1/rerank → 404 on
|
||||
// /v1-suffixed bases.
|
||||
path: '/rerank',
|
||||
},
|
||||
},
|
||||
setup_hint: 'Run LiteLLM (https://docs.litellm.ai) in front of any provider; set LITELLM_BASE_URL (include the /v1 suffix if your proxy serves the OpenAI route there, e.g. http://localhost:4000/v1) + pass --embedding-model litellm:<model> and --embedding-dimensions <N>. For rerank: register a rerank model in LiteLLM and set search.reranker.model litellm:<model-name>.',
|
||||
setup_hint: 'Run LiteLLM (https://docs.litellm.ai) in front of any provider; set LITELLM_BASE_URL (include the /v1 suffix if your proxy serves the OpenAI route there, e.g. http://localhost:4000/v1) + pass --embedding-model litellm:<model> and --embedding-dimensions <N>.',
|
||||
};
|
||||
|
||||
@@ -20,6 +20,14 @@ export const CJK_SLUG_CHARS = '一-鿿-ゟ゠-ヿ가-';
|
||||
|
||||
export const CJK_RANGES_REGEX = new RegExp(`[${CJK_SLUG_CHARS}]`);
|
||||
|
||||
/**
|
||||
* Page-slug segment grammar (no anchors): alnum-or-CJK lead char, then
|
||||
* alnum/CJK/hyphen continuation. Single source for validatePageSlug
|
||||
* (operations.ts), SlugRegistry's SLUG_RE, and the dream-cycle
|
||||
* SUMMARY_SLUG_RE so every slug validator shares one grammar (#738).
|
||||
*/
|
||||
export const PAGE_SLUG_SEG = `[a-z0-9${CJK_SLUG_CHARS}][a-z0-9${CJK_SLUG_CHARS}\\-]*`;
|
||||
|
||||
export const CJK_SENTENCE_DELIMITERS = ['。', '!', '?']; // 。!?
|
||||
export const CJK_CLAUSE_DELIMITERS = [';', ':', ',', '、']; // ;:,、
|
||||
|
||||
|
||||
@@ -43,10 +43,11 @@ import { serializeMarkdown, serializePageToMarkdown } from '../markdown.ts';
|
||||
import type { Page, PageType } from '../types.ts';
|
||||
import { validateSourceId } from '../utils.ts';
|
||||
import { safeSplitIndex } from '../text-safe.ts';
|
||||
import { PAGE_SLUG_SEG } from '../cjk.ts';
|
||||
|
||||
// Slug regex from validatePageSlug — kept in sync.
|
||||
// Slug grammar from validatePageSlug — shared via PAGE_SLUG_SEG (#738).
|
||||
// Used for the orchestrator-written summary index slug.
|
||||
const SUMMARY_SLUG_RE = /^[a-z0-9][a-z0-9\-]*(\/[a-z0-9][a-z0-9\-]*)*$/;
|
||||
const SUMMARY_SLUG_RE = new RegExp(`^${PAGE_SLUG_SEG}(\\/${PAGE_SLUG_SEG})*$`);
|
||||
|
||||
// ── Model context budget (D1, D5, D7, D9) ─────────────────────────────
|
||||
|
||||
|
||||
@@ -25,7 +25,7 @@ import { bumpLastRetrievedAt } from './last-retrieved.ts';
|
||||
import { isSearchMode } from './search/mode.ts';
|
||||
import { stampEvidence } from './search/evidence.ts';
|
||||
import type { SearchResult } from './types.ts';
|
||||
import { CJK_SLUG_CHARS } from './cjk.ts';
|
||||
import { CJK_SLUG_CHARS, PAGE_SLUG_SEG } from './cjk.ts';
|
||||
import * as db from './db.ts';
|
||||
import { VERSION } from '../version.ts';
|
||||
import {
|
||||
@@ -162,7 +162,6 @@ export function validatePageSlug(slug: string): void {
|
||||
}
|
||||
// v0.32.7: CJK ranges (Han / Hiragana / Katakana / Hangul Syllables) allowed
|
||||
// in segments. ASCII shape rules (lead char, hyphen continuation) preserved.
|
||||
const PAGE_SLUG_SEG = `[a-z0-9${CJK_SLUG_CHARS}][a-z0-9${CJK_SLUG_CHARS}\\-]*`;
|
||||
if (!new RegExp(`^${PAGE_SLUG_SEG}(\\/${PAGE_SLUG_SEG})*$`, 'i').test(slug)) {
|
||||
throw new OperationError('invalid_params', `Invalid page_slug: ${slug} (allowed: alphanumeric, CJK, hyphens, forward-slash separated segments)`);
|
||||
}
|
||||
|
||||
@@ -17,6 +17,7 @@
|
||||
|
||||
import type { BrainEngine } from '../engine.ts';
|
||||
import type { PageType } from '../types.ts';
|
||||
import { PAGE_SLUG_SEG } from '../cjk.ts';
|
||||
|
||||
export interface CreateSlugInput {
|
||||
/**
|
||||
@@ -71,7 +72,9 @@ export class SlugRegistryError extends Error {
|
||||
// SlugRegistry
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
const SLUG_RE = /^[a-z0-9][a-z0-9\-]*(\/[a-z0-9][a-z0-9\-]*)+$/;
|
||||
// Shares the page-slug segment grammar (incl. CJK ranges, #738) with
|
||||
// validatePageSlug; keeps this site's dir/name shape (>= 2 segments).
|
||||
const SLUG_RE = new RegExp(`^${PAGE_SLUG_SEG}(\\/${PAGE_SLUG_SEG})+$`);
|
||||
|
||||
export class SlugRegistry {
|
||||
constructor(private engine: BrainEngine) {}
|
||||
|
||||
@@ -1,88 +0,0 @@
|
||||
/**
|
||||
* litellm-proxy reranker touchpoint smoke.
|
||||
*
|
||||
* Sibling of recipe-llama-server-reranker.test.ts. Pins the reranker
|
||||
* touchpoint on the LiteLLM proxy recipe so:
|
||||
* - the touchpoint exists with the LEAF '/rerank' path (LiteLLM serves both
|
||||
* /rerank and /v1/rerank, so the leaf form is valid whether or not the
|
||||
* user's LITELLM_BASE_URL carries the /v1 suffix the setup_hint allows)
|
||||
* - a /v1-suffixed base URL does NOT produce /v1/v1/rerank (the original
|
||||
* community PR pinned '/v1/rerank' which 404s on /v1-suffixed bases)
|
||||
* - models: [] (user-provided; proxy defines the model ids)
|
||||
* - pricing stays undefined (proxy can front a paid provider — same honest
|
||||
* pricing-unknown stance as the embedding/chat touchpoints)
|
||||
*
|
||||
* The gateway.rerank() URL tests drive the real URL builder via the stubbed
|
||||
* transport (same seam as test/ai/rerank.test.ts).
|
||||
*/
|
||||
|
||||
import { describe, expect, test, afterEach } from 'bun:test';
|
||||
import { getRecipe } from '../../src/core/ai/recipes/index.ts';
|
||||
import {
|
||||
configureGateway,
|
||||
resetGateway,
|
||||
rerank,
|
||||
__setRerankTransportForTests,
|
||||
} from '../../src/core/ai/gateway.ts';
|
||||
|
||||
afterEach(() => {
|
||||
__setRerankTransportForTests(null);
|
||||
resetGateway();
|
||||
});
|
||||
|
||||
describe('recipe: litellm reranker touchpoint', () => {
|
||||
test('declares reranker touchpoint with leaf /rerank path', () => {
|
||||
const r = getRecipe('litellm')!;
|
||||
const tp = r.touchpoints.reranker;
|
||||
expect(tp).toBeDefined();
|
||||
expect(tp!.path).toBe('/rerank');
|
||||
expect(tp!.max_payload_bytes).toBe(5_000_000);
|
||||
});
|
||||
|
||||
test('reranker touchpoint uses empty models[] for user-provided model ids', () => {
|
||||
const r = getRecipe('litellm')!;
|
||||
expect(r.touchpoints.reranker!.models).toEqual([]);
|
||||
});
|
||||
|
||||
test('pricing stays undefined — proxy can front a paid provider', () => {
|
||||
const r = getRecipe('litellm')!;
|
||||
expect(r.touchpoints.reranker!.cost_per_1m_tokens_usd).toBeUndefined();
|
||||
});
|
||||
|
||||
test('setup_hint keeps the /v1-suffix guidance AND mentions rerank', () => {
|
||||
const r = getRecipe('litellm')!;
|
||||
expect(r.setup_hint).toMatch(/\/v1 suffix/);
|
||||
expect(r.setup_hint).toMatch(/search\.reranker\.model litellm:/);
|
||||
});
|
||||
});
|
||||
|
||||
describe('gateway.rerank() URL via litellm recipe', () => {
|
||||
async function capturedRerankUrl(baseUrl?: string): Promise<string> {
|
||||
configureGateway({
|
||||
reranker_model: 'litellm:my-reranker',
|
||||
env: {},
|
||||
...(baseUrl ? { base_urls: { litellm: baseUrl } } : {}),
|
||||
});
|
||||
let capturedUrl = '';
|
||||
__setRerankTransportForTests(async (url) => {
|
||||
capturedUrl = url;
|
||||
return new Response(
|
||||
JSON.stringify({ results: [{ index: 0, relevance_score: 0.9 }] }),
|
||||
{ status: 200, headers: { 'content-type': 'application/json' } },
|
||||
);
|
||||
});
|
||||
await rerank({ query: 'q', documents: ['d'] });
|
||||
return capturedUrl;
|
||||
}
|
||||
|
||||
test('default base (no /v1 suffix) → /rerank', async () => {
|
||||
const url = await capturedRerankUrl();
|
||||
expect(url).toBe('http://localhost:4000/rerank');
|
||||
});
|
||||
|
||||
test('/v1-suffixed base → /v1/rerank, NOT /v1/v1/rerank', async () => {
|
||||
const url = await capturedRerankUrl('http://localhost:4000/v1');
|
||||
expect(url).toBe('http://localhost:4000/v1/rerank');
|
||||
expect(url).not.toContain('/v1/v1/');
|
||||
});
|
||||
});
|
||||
@@ -86,6 +86,12 @@ describe('#2415: loadOutputRoot validation + patterns gather scope', () => {
|
||||
expect(await loadOutputRoot(engine)).toBe('wiki');
|
||||
});
|
||||
|
||||
test('CJK root passes the slug grammar (#738)', async () => {
|
||||
await engine.setConfig('dream.synthesize.output_root', '知识/笔记');
|
||||
expect(await loadOutputRoot(engine)).toBe('知识/笔记');
|
||||
await engine.setConfig('dream.synthesize.output_root', '');
|
||||
});
|
||||
|
||||
test('patterns phase gathers reflections under the configured root', async () => {
|
||||
await engine.setConfig('dream.synthesize.output_root', 'notes');
|
||||
for (let i = 0; i < 3; i++) {
|
||||
|
||||
@@ -203,6 +203,17 @@ describe('SlugRegistry', () => {
|
||||
})).rejects.toThrow(SlugRegistryError);
|
||||
});
|
||||
|
||||
test('create accepts CJK slugs (#738)', async () => {
|
||||
const reg = new SlugRegistry(engine);
|
||||
const r = await reg.create({
|
||||
desiredSlug: '知识/品牌圣经',
|
||||
displayName: '品牌圣经',
|
||||
type: 'note',
|
||||
});
|
||||
expect(r.slug).toBe('知识/品牌圣经');
|
||||
expect(r.exact).toBe(true);
|
||||
});
|
||||
|
||||
test('create throws on invalid slug', async () => {
|
||||
const reg = new SlugRegistry(engine);
|
||||
await expect(reg.create({
|
||||
|
||||
Reference in New Issue
Block a user