mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-17 10:22:34 +00:00
Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
1b45023dba |
Vendored
-56
File diff suppressed because one or more lines are too long
Vendored
+57
File diff suppressed because one or more lines are too long
Vendored
+1
-1
@@ -7,7 +7,7 @@
|
||||
<link rel="preconnect" href="https://fonts.googleapis.com" />
|
||||
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
|
||||
<link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600&family=JetBrains+Mono:wght@400;500&display=swap" rel="stylesheet" />
|
||||
<script type="module" crossorigin src="/admin/assets/index-CoGEje3-.js"></script>
|
||||
<script type="module" crossorigin src="/admin/assets/index-CzLjRij_.js"></script>
|
||||
<link rel="stylesheet" crossorigin href="/admin/assets/index-GxkWX7v3.css">
|
||||
</head>
|
||||
<body>
|
||||
|
||||
@@ -39,6 +39,7 @@ export const api = {
|
||||
stats: () => apiFetch('/admin/api/stats'),
|
||||
health: () => apiFetch('/admin/api/health-indicators'),
|
||||
agents: () => apiFetch('/admin/api/agents'),
|
||||
sources: () => apiFetch('/admin/api/sources'),
|
||||
requests: (page = 1, qs = '') => apiFetch(`/admin/api/requests?page=${page}${qs}`),
|
||||
apiKeys: () => apiFetch('/admin/api/api-keys'),
|
||||
createApiKey: (name: string) => apiFetch('/admin/api/api-keys', { method: 'POST', body: JSON.stringify({ name }) }),
|
||||
|
||||
@@ -23,9 +23,16 @@ interface Agent {
|
||||
total_requests: number;
|
||||
requests_today: number;
|
||||
token_ttl: number | null;
|
||||
source_id: string | null;
|
||||
federated_read: string[] | null;
|
||||
status: 'active' | 'revoked';
|
||||
}
|
||||
|
||||
interface SourceOption {
|
||||
id: string;
|
||||
name: string | null;
|
||||
}
|
||||
|
||||
interface ApiKey {
|
||||
id: string;
|
||||
name: string;
|
||||
@@ -88,6 +95,7 @@ export function AgentsPage() {
|
||||
<th>Name</th>
|
||||
<th>Type</th>
|
||||
<th>Scopes</th>
|
||||
<th>Source</th>
|
||||
<th>Status</th>
|
||||
<th>Requests</th>
|
||||
<th>Last Used</th>
|
||||
@@ -108,6 +116,9 @@ export function AgentsPage() {
|
||||
<span key={s} className={`badge badge-${s}`} style={{ marginRight: 4 }}>{s}</span>
|
||||
))}
|
||||
</td>
|
||||
<td className="mono" style={{ fontSize: 12, color: 'var(--text-secondary)' }}>
|
||||
{a.auth_type === 'oauth' ? (a.source_id || 'default') : 'all'}
|
||||
</td>
|
||||
<td>
|
||||
<span className={`badge ${a.status === 'active' ? 'badge-success' : 'badge-danger'}`}>{a.status}</span>
|
||||
</td>
|
||||
@@ -257,9 +268,29 @@ function RegisterModal({ onClose, onRegistered }: {
|
||||
Object.fromEntries(ALLOWED_SCOPES_LIST.map(s => [s, s === 'read'])) as Record<Scope, boolean>,
|
||||
);
|
||||
const [ttl, setTtl] = useState('86400'); // 24h default
|
||||
const [redirectUris, setRedirectUris] = useState('');
|
||||
const [sources, setSources] = useState<SourceOption[]>([{ id: 'default', name: 'default' }]);
|
||||
const [sourceId, setSourceId] = useState('default');
|
||||
const [readSources, setReadSources] = useState<Record<string, boolean>>({ default: true });
|
||||
const [loading, setLoading] = useState(false);
|
||||
const [error, setError] = useState('');
|
||||
|
||||
useEffect(() => {
|
||||
api.sources()
|
||||
.then((rows: SourceOption[]) => {
|
||||
const nextSources = rows.length > 0 ? rows : [{ id: 'default', name: 'default' }];
|
||||
const nextSourceId = nextSources.some(s => s.id === sourceId) ? sourceId : nextSources[0].id;
|
||||
setSources(nextSources);
|
||||
setSourceId(nextSourceId);
|
||||
setReadSources(prev => {
|
||||
const next = Object.fromEntries(nextSources.map(s => [s.id, Boolean(prev[s.id])])) as Record<string, boolean>;
|
||||
next[nextSourceId] = true;
|
||||
return next;
|
||||
});
|
||||
})
|
||||
.catch(() => {});
|
||||
}, []);
|
||||
|
||||
const ttlOptions = [
|
||||
{ label: '1 hour', value: '3600' },
|
||||
{ label: '24 hours', value: '86400' },
|
||||
@@ -277,11 +308,24 @@ function RegisterModal({ onClose, onRegistered }: {
|
||||
try {
|
||||
// Use the CLI registration endpoint (POST to admin API)
|
||||
const selectedScopes = Object.entries(scopes).filter(([, v]) => v).map(([k]) => k).join(' ');
|
||||
const federatedRead = sources.map(s => s.id).filter(id => readSources[id]);
|
||||
if (federatedRead.length === 0) { setError('Select at least one read source'); setLoading(false); return; }
|
||||
// #1036: redirect URIs, one per line. Mirrors the CLI convention
|
||||
// (src/commands/auth.ts): presence of redirect URIs implies
|
||||
// authorization_code + refresh_token grants unless the user had none.
|
||||
const uris = redirectUris.split('\n').map(u => u.trim()).filter(Boolean);
|
||||
const res = await fetch('/admin/api/register-client', {
|
||||
method: 'POST',
|
||||
credentials: 'same-origin',
|
||||
headers: { 'Content-Type': 'application/json' },
|
||||
body: JSON.stringify({ name: name.trim(), scopes: selectedScopes, tokenTtl: ttl === '0' ? 315360000 : Number(ttl) }),
|
||||
body: JSON.stringify({
|
||||
name: name.trim(),
|
||||
scopes: selectedScopes,
|
||||
tokenTtl: ttl === '0' ? 315360000 : Number(ttl),
|
||||
source_id: sourceId,
|
||||
federated_read: federatedRead,
|
||||
...(uris.length > 0 ? { redirectUris: uris, grantTypes: ['authorization_code', 'refresh_token'] } : {}),
|
||||
}),
|
||||
});
|
||||
if (!res.ok) throw new Error('Registration failed');
|
||||
const data = await res.json();
|
||||
@@ -312,6 +356,42 @@ function RegisterModal({ onClose, onRegistered }: {
|
||||
))}
|
||||
</div>
|
||||
</div>
|
||||
<div style={{ marginBottom: 16 }}>
|
||||
<label>Write Source</label>
|
||||
<select value={sourceId} onChange={e => {
|
||||
const id = e.target.value;
|
||||
setSourceId(id);
|
||||
setReadSources(p => ({ ...p, [id]: true }));
|
||||
}}
|
||||
style={{ width: '100%', background: 'var(--bg-secondary)', color: 'var(--text-primary)', border: '1px solid var(--border)', borderRadius: 6, padding: '6px 10px', fontSize: 14 }}>
|
||||
{sources.map(s => <option key={s.id} value={s.id}>{s.name && s.name !== s.id ? `${s.id} (${s.name})` : s.id}</option>)}
|
||||
</select>
|
||||
</div>
|
||||
<div style={{ marginBottom: 16 }}>
|
||||
<label>Read Sources</label>
|
||||
<div className="checkbox-group">
|
||||
{sources.map(s => (
|
||||
<label key={s.id} className="checkbox-label">
|
||||
<input
|
||||
type="checkbox"
|
||||
checked={Boolean(readSources[s.id])}
|
||||
onChange={e => setReadSources(p => ({ ...p, [s.id]: e.target.checked }))}
|
||||
/>
|
||||
{s.name && s.name !== s.id ? `${s.id} (${s.name})` : s.id}
|
||||
</label>
|
||||
))}
|
||||
</div>
|
||||
</div>
|
||||
<div style={{ marginBottom: 16 }}>
|
||||
<label>Redirect URIs <span style={{ color: 'var(--text-secondary)', fontWeight: 400 }}>(optional, one per line — enables authorization_code flow)</span></label>
|
||||
<textarea
|
||||
placeholder={'https://example.com/callback'}
|
||||
value={redirectUris}
|
||||
onChange={e => setRedirectUris(e.target.value)}
|
||||
rows={2}
|
||||
style={{ width: '100%', background: 'var(--bg-secondary)', color: 'var(--text-primary)', border: '1px solid var(--border)', borderRadius: 6, padding: '6px 10px', fontSize: 13, fontFamily: 'inherit', resize: 'vertical' }}
|
||||
/>
|
||||
</div>
|
||||
<div style={{ marginBottom: 20 }}>
|
||||
<label>Token Lifetime</label>
|
||||
<select value={ttl} onChange={e => setTtl(e.target.value)}
|
||||
@@ -528,6 +608,8 @@ function AgentDrawer({ agent, onClose, onRevoked }: { agent: Agent; onClose: ()
|
||||
client_name: agentName,
|
||||
auth_type: agent.auth_type,
|
||||
scope: agent.scope,
|
||||
source_id: agent.source_id,
|
||||
federated_read: agent.federated_read,
|
||||
}, null, 2),
|
||||
};
|
||||
|
||||
@@ -547,6 +629,10 @@ function AgentDrawer({ agent, onClose, onRevoked }: { agent: Agent; onClose: ()
|
||||
<span>{(agent.scope || '').split(' ').filter(Boolean).map(s => (
|
||||
<span key={s} className={`badge badge-${s}`} style={{ marginRight: 4 }}>{s}</span>
|
||||
))}</span>
|
||||
<span style={{ color: 'var(--text-secondary)' }}>Write Source</span>
|
||||
<span className="mono">{agent.source_id || (isOAuth ? 'default' : 'all')}</span>
|
||||
<span style={{ color: 'var(--text-secondary)' }}>Read Sources</span>
|
||||
<span className="mono">{isOAuth ? (agent.federated_read && agent.federated_read.length > 0 ? agent.federated_read.join(', ') : (agent.source_id || 'default')) : 'all'}</span>
|
||||
<span style={{ color: 'var(--text-secondary)' }}>Registered</span>
|
||||
<span>{new Date(agent.created_at).toLocaleDateString()}</span>
|
||||
<span style={{ color: 'var(--text-secondary)' }}>Token TTL</span>
|
||||
|
||||
@@ -1,13 +1,13 @@
|
||||
// AUTO-GENERATED — do not edit by hand.
|
||||
// Run `bun run scripts/build-admin-embedded.ts` to regenerate.
|
||||
// Source: admin/dist/ at 2026-05-27.
|
||||
// Source: admin/dist/ at 2026-07-21.
|
||||
//
|
||||
// Bun resolves the file: imports to a path that works at runtime even
|
||||
// inside a compiled binary (`bun build --compile`). The manifest maps
|
||||
// the request path the express handler sees to (resolved-path, mime).
|
||||
|
||||
// @ts-ignore — type: 'file' is Bun ESM, not in lib.d.ts
|
||||
import A_0_assets_index_CoGEje3__js from '../admin/dist/assets/index-CoGEje3-.js' with { type: 'file' };
|
||||
import A_0_assets_index_CzLjRij__js from '../admin/dist/assets/index-CzLjRij_.js' with { type: 'file' };
|
||||
// @ts-ignore — type: 'file' is Bun ESM, not in lib.d.ts
|
||||
import A_1_assets_index_GxkWX7v3_css from '../admin/dist/assets/index-GxkWX7v3.css' with { type: 'file' };
|
||||
// @ts-ignore — type: 'file' is Bun ESM, not in lib.d.ts
|
||||
@@ -19,7 +19,7 @@ export interface AdminAsset {
|
||||
}
|
||||
|
||||
export const ADMIN_ASSETS: Record<string, AdminAsset> = {
|
||||
"/admin/assets/index-CoGEje3-.js": { path: A_0_assets_index_CoGEje3__js as unknown as string, mime: "application/javascript; charset=utf-8" },
|
||||
"/admin/assets/index-CzLjRij_.js": { path: A_0_assets_index_CzLjRij__js as unknown as string, mime: "application/javascript; charset=utf-8" },
|
||||
"/admin/assets/index-GxkWX7v3.css": { path: A_1_assets_index_GxkWX7v3_css as unknown as string, mime: "text/css; charset=utf-8" },
|
||||
"/admin/index.html": { path: A_2_index_html as unknown as string, mime: "text/html; charset=utf-8" },
|
||||
};
|
||||
|
||||
@@ -39,6 +39,7 @@ import * as db from '../core/db.ts';
|
||||
import { sqlQueryForEngine, executeRawJsonb } from '../core/sql-query.ts';
|
||||
import { MinionQueue } from '../core/minions/queue.ts';
|
||||
import { isRetryableError } from '../core/retry-matcher.ts';
|
||||
import { normalizeAdminClientSourceScope } from '../core/admin-source-scope.ts';
|
||||
import {
|
||||
computeContentHash,
|
||||
validateIngestionEvent,
|
||||
@@ -1086,6 +1087,7 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
|
||||
const oauthClients = await sql`
|
||||
SELECT c.client_id as id, c.client_name as name, 'oauth' as auth_type,
|
||||
c.grant_types, c.scope, c.created_at, c.token_ttl,
|
||||
c.source_id, c.federated_read,
|
||||
CASE WHEN c.deleted_at IS NOT NULL THEN 'revoked' ELSE 'active' END as status,
|
||||
(SELECT max(created_at) FROM mcp_request_log WHERE token_name = c.client_id) as last_used_at,
|
||||
(SELECT count(*)::int FROM mcp_request_log WHERE token_name = c.client_id) as total_requests,
|
||||
@@ -1095,6 +1097,7 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
|
||||
const legacyKeys = await sql`
|
||||
SELECT a.id, a.name, 'api_key' as auth_type,
|
||||
'{"bearer"}' as grant_types, 'read write admin' as scope, a.created_at, null as token_ttl,
|
||||
null as source_id, null as federated_read,
|
||||
CASE WHEN a.revoked_at IS NOT NULL THEN 'revoked' ELSE 'active' END as status,
|
||||
a.last_used_at,
|
||||
(SELECT count(*)::int FROM mcp_request_log WHERE token_name = a.name) as total_requests,
|
||||
@@ -1107,6 +1110,17 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
|
||||
}
|
||||
});
|
||||
|
||||
app.get('/admin/api/sources', requireAdmin, async (_req: Request, res: Response) => {
|
||||
try {
|
||||
const sources = await engine.listAllSources({ includeArchived: false });
|
||||
const options = sources.map(s => ({ id: s.id, name: s.name }));
|
||||
if (!options.some(s => s.id === 'default')) options.unshift({ id: 'default', name: 'default' });
|
||||
res.json(options);
|
||||
} catch (e) {
|
||||
res.status(503).json({ error: 'service_unavailable' });
|
||||
}
|
||||
});
|
||||
|
||||
// v0.38 Slice 4 — per-OAuth-client agent spend viewer. Pre-computes today's
|
||||
// spend (committed + pending reservations) per client so the Agents tab
|
||||
// can render a "$X / $Y today" cell. Read-side endpoint only — no mutation.
|
||||
@@ -1440,6 +1454,8 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
|
||||
// missing, empty) and rejects the rest with a structured 400.
|
||||
const { name, tokenTtl, grantTypes, redirectUris, tokenEndpointAuthMethod } = req.body;
|
||||
const rawScopes = (req.body as Record<string, unknown>).scopes ?? (req.body as Record<string, unknown>).scope;
|
||||
const rawSourceId = (req.body as Record<string, unknown>).source_id ?? (req.body as Record<string, unknown>).sourceId;
|
||||
const rawFederatedRead = (req.body as Record<string, unknown>).federated_read ?? (req.body as Record<string, unknown>).federatedRead;
|
||||
if (!name) { res.status(400).json({ error: 'Name required' }); return; }
|
||||
let scopeString: string;
|
||||
try {
|
||||
@@ -1470,8 +1486,23 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
|
||||
});
|
||||
return;
|
||||
}
|
||||
let sourceScope: ReturnType<typeof normalizeAdminClientSourceScope>;
|
||||
try {
|
||||
const sources = await engine.listAllSources({ includeArchived: false });
|
||||
sourceScope = normalizeAdminClientSourceScope(
|
||||
rawSourceId,
|
||||
rawFederatedRead,
|
||||
sources.map(s => s.id),
|
||||
);
|
||||
} catch (e) {
|
||||
res.status(400).json({
|
||||
error: 'invalid_source_scope',
|
||||
message: e instanceof Error ? e.message : String(e),
|
||||
});
|
||||
return;
|
||||
}
|
||||
const result = await oauthProvider.registerClientManual(
|
||||
name, grants, scopeString, uris, 'default', undefined, validatedAuthMethod,
|
||||
name, grants, scopeString, uris, sourceScope.sourceId, sourceScope.federatedRead, validatedAuthMethod,
|
||||
);
|
||||
// Set per-client TTL if specified
|
||||
if (tokenTtl && Number(tokenTtl) > 0) {
|
||||
|
||||
@@ -0,0 +1,51 @@
|
||||
import { isValidSourceId } from './source-id.ts';
|
||||
|
||||
export interface AdminClientSourceScope {
|
||||
sourceId: string;
|
||||
federatedRead: string[];
|
||||
}
|
||||
|
||||
function parseFederatedReadInput(raw: unknown, sourceId: string): string[] {
|
||||
if (raw === undefined || raw === null) return [sourceId];
|
||||
if (typeof raw === 'string') {
|
||||
const values = raw.split(',').map(s => s.trim()).filter(Boolean);
|
||||
return values.length > 0 ? values : [sourceId];
|
||||
}
|
||||
if (Array.isArray(raw)) {
|
||||
if (!raw.every(v => typeof v === 'string')) {
|
||||
throw new Error('federated_read must be an array of source ids');
|
||||
}
|
||||
const values = raw.map(v => v.trim()).filter(Boolean);
|
||||
return values.length > 0 ? values : [sourceId];
|
||||
}
|
||||
throw new Error('federated_read must be a string or array');
|
||||
}
|
||||
|
||||
export function normalizeAdminClientSourceScope(
|
||||
rawSourceId: unknown,
|
||||
rawFederatedRead: unknown,
|
||||
availableSourceIds: string[],
|
||||
): AdminClientSourceScope {
|
||||
const knownSources = new Set(availableSourceIds);
|
||||
const fallbackSourceId = knownSources.has('default') ? 'default' : (availableSourceIds[0] ?? 'default');
|
||||
const sourceId = rawSourceId === undefined || rawSourceId === null || rawSourceId === ''
|
||||
? fallbackSourceId
|
||||
: rawSourceId;
|
||||
if (!isValidSourceId(sourceId)) {
|
||||
throw new Error(`Invalid source_id: ${JSON.stringify(sourceId)}`);
|
||||
}
|
||||
if (knownSources.size > 0 && !knownSources.has(sourceId)) {
|
||||
throw new Error(`Unknown source_id: ${sourceId}`);
|
||||
}
|
||||
|
||||
const federatedRead = Array.from(new Set(parseFederatedReadInput(rawFederatedRead, sourceId)));
|
||||
for (const id of federatedRead) {
|
||||
if (!isValidSourceId(id)) {
|
||||
throw new Error(`Invalid federated_read source_id: ${JSON.stringify(id)}`);
|
||||
}
|
||||
if (knownSources.size > 0 && !knownSources.has(id)) {
|
||||
throw new Error(`Unknown federated_read source_id: ${id}`);
|
||||
}
|
||||
}
|
||||
return { sourceId, federatedRead };
|
||||
}
|
||||
@@ -18,9 +18,8 @@
|
||||
* at runtime.
|
||||
*/
|
||||
|
||||
import { chunkText as recursiveChunk, capByEstimatedTokens, DEFAULT_MAX_EST_TOKENS } from './recursive.ts';
|
||||
import { chunkText as recursiveChunk } from './recursive.ts';
|
||||
import { buildQualifiedName } from './qualified-names.ts';
|
||||
import { estimateEmbeddingTokens } from '../cjk.ts';
|
||||
|
||||
// Embed the tree-sitter runtime + per-language grammars as files.
|
||||
// `with { type: 'file' }` returns a path (string) at runtime. Bun bundles
|
||||
@@ -112,15 +111,7 @@ import G_ZIG from '../../assets/wasm/grammars/tree-sitter-zig.wasm' with { type:
|
||||
// chunks get the new columns populated. Without this, the v28 backfill
|
||||
// gives every existing chunk a search_vector but subsequent Layer 5 AST
|
||||
// work would silently no-op.
|
||||
//
|
||||
// v5: estimated-token hard cap on AST-path chunks (capCodeChunks). A node
|
||||
// splitLargeNode can't subdivide (giant single-statement function, huge
|
||||
// literal) previously shipped WHOLE regardless of size and could overflow
|
||||
// strict per-request embedding-token limits (local llama-server crashes
|
||||
// past ~2,050 tokens, measured). Mirrors the markdown
|
||||
// chunker's v4 cap; fallback-path chunks are already capped inside
|
||||
// recursiveChunk.
|
||||
export const CHUNKER_VERSION = 5;
|
||||
export const CHUNKER_VERSION = 4;
|
||||
|
||||
// Lazy-loaded tree-sitter module (v0.22.x API: Parser is default export)
|
||||
let Parser: typeof import('web-tree-sitter') | null = null;
|
||||
@@ -717,7 +708,7 @@ export async function chunkCodeTextFull(
|
||||
if (chunks.length === 0) {
|
||||
return { chunks: fallbackChunks(source, filePath, language, opts), edges: rawEdges };
|
||||
}
|
||||
return { chunks: capCodeChunks(mergeSmallSiblings(chunks, chunkTarget)), edges: rawEdges };
|
||||
return { chunks: mergeSmallSiblings(chunks, chunkTarget), edges: rawEdges };
|
||||
} catch {
|
||||
return { chunks: fallbackChunks(source, filePath, language, opts), edges: [] };
|
||||
} finally {
|
||||
@@ -800,33 +791,6 @@ function mergeSmallSiblings(chunks: CodeChunk[], chunkTarget: number): CodeChunk
|
||||
return merged;
|
||||
}
|
||||
|
||||
/**
|
||||
* v5 final safety pass for AST-path chunks: split any chunk whose
|
||||
* ESTIMATED embedding tokens (conservative per-char-class heuristic,
|
||||
* cjk.ts) exceed DEFAULT_MAX_EST_TOKENS. Reaches chunks the AST logic
|
||||
* can't subdivide — splitLargeNode returns [] for nodes with < 2 body
|
||||
* children (giant single-statement functions, huge literals), which
|
||||
* previously shipped whole at any size.
|
||||
*
|
||||
* Split pieces inherit the source chunk's metadata verbatim; start/end
|
||||
* lines become approximate for pieces after the first. Acceptable —
|
||||
* these chunks exist for embedding + retrieval, and the alternative was
|
||||
* an embedding request the server rejects (or worse, crashes on).
|
||||
*/
|
||||
function capCodeChunks(chunks: CodeChunk[]): CodeChunk[] {
|
||||
if (chunks.every((c) => estimateEmbeddingTokens(c.text) <= DEFAULT_MAX_EST_TOKENS)) {
|
||||
return chunks;
|
||||
}
|
||||
const out: CodeChunk[] = [];
|
||||
for (const c of chunks) {
|
||||
const pieces = capByEstimatedTokens(c.text, DEFAULT_MAX_EST_TOKENS);
|
||||
for (const piece of pieces) {
|
||||
out.push({ ...c, text: piece, index: out.length, metadata: { ...c.metadata } });
|
||||
}
|
||||
}
|
||||
return out;
|
||||
}
|
||||
|
||||
function buildMergedChunk(group: CodeChunk[], index: number): CodeChunk {
|
||||
const first = group[0]!;
|
||||
const last = group[group.length - 1]!;
|
||||
|
||||
@@ -17,13 +17,7 @@
|
||||
* Lossless invariant: non-overlapping portions reassemble to original.
|
||||
*/
|
||||
|
||||
import {
|
||||
countCJKAwareWords,
|
||||
CJK_SENTENCE_DELIMITERS,
|
||||
CJK_CLAUSE_DELIMITERS,
|
||||
charEmbedTokenWeight,
|
||||
estimateEmbeddingTokens,
|
||||
} from '../cjk.ts';
|
||||
import { countCJKAwareWords, CJK_SENTENCE_DELIMITERS, CJK_CLAUSE_DELIMITERS } from '../cjk.ts';
|
||||
|
||||
/**
|
||||
* Markdown chunker version. Folded into the per-page chunker_version column
|
||||
@@ -39,20 +33,8 @@ import {
|
||||
* re-embed (not re-chunk) so existing pages pick up the wrapper on the
|
||||
* post-upgrade reembed sweep. See
|
||||
* `src/core/contextual-retrieval-service.ts`.
|
||||
*
|
||||
* v4: estimated-token hard cap + whitespace-word undercount fix. The word
|
||||
* pipeline counted a 150-char URL as ONE whitespace word, so URL/phone/
|
||||
* email-dense docs (CJK density < 0.30 → whitespace fallback) produced
|
||||
* 3-4K-char chunks that overflow strict per-request embedding-token
|
||||
* limits (measured: local llama-server crashes past ~2,050 tokens; URL
|
||||
* soup tokenizes at ~1.6 chars/token). Two changes:
|
||||
* 1. countWords() floors the count at ceil(nonWhitespaceChars/6) so a
|
||||
* URL counts roughly per-character, not as one word.
|
||||
* 2. capByEstimatedTokens() final pass guarantees every chunk fits
|
||||
* `maxTokens` (default 1500) under a conservative per-char-class
|
||||
* token estimate, regardless of how word counting misjudged it.
|
||||
*/
|
||||
export const MARKDOWN_CHUNKER_VERSION = 4;
|
||||
export const MARKDOWN_CHUNKER_VERSION = 3;
|
||||
|
||||
const DELIMITERS: string[][] = [
|
||||
['\n\n'], // L0: paragraphs
|
||||
@@ -66,20 +48,8 @@ export interface ChunkOptions {
|
||||
chunkSize?: number; // target words per chunk (default 300)
|
||||
chunkOverlap?: number; // overlap words (default 50)
|
||||
maxChars?: number; // hard cap on any chunk's char length (default 6000)
|
||||
/**
|
||||
* v4: hard cap on any chunk's ESTIMATED embedding tokens (default 1500).
|
||||
* Estimate = conservative per-char-class weights (see cjk.ts
|
||||
* estimateEmbeddingTokens) — deliberately high, so the real tokenizer
|
||||
* count stays below this value. Default leaves headroom for the
|
||||
* contextual-retrieval wrapper (≤ ~630 chars) under a ~2,050-token
|
||||
* per-request embedding server limit.
|
||||
*/
|
||||
maxTokens?: number;
|
||||
}
|
||||
|
||||
/** v4 default for ChunkOptions.maxTokens — see the field doc above. */
|
||||
export const DEFAULT_MAX_EST_TOKENS = 1500;
|
||||
|
||||
export interface TextChunk {
|
||||
text: string;
|
||||
index: number;
|
||||
@@ -103,7 +73,6 @@ export function chunkText(text: string, opts?: ChunkOptions): TextChunk[] {
|
||||
const chunkSize = opts?.chunkSize || 300;
|
||||
const chunkOverlap = opts?.chunkOverlap || 50;
|
||||
const maxChars = opts?.maxChars || 6000;
|
||||
const maxTokens = opts?.maxTokens || DEFAULT_MAX_EST_TOKENS;
|
||||
|
||||
if (!text || text.trim().length === 0) return [];
|
||||
|
||||
@@ -120,9 +89,8 @@ export function chunkText(text: string, opts?: ChunkOptions): TextChunk[] {
|
||||
|
||||
const wordCount = countWords(stripped);
|
||||
if (wordCount <= chunkSize) {
|
||||
// Single-chunk path: still apply the maxChars + maxTokens caps.
|
||||
const capped = capByChars(stripped.trim(), maxChars)
|
||||
.flatMap((t) => capByEstimatedTokens(t, maxTokens));
|
||||
// Single-chunk path: still apply the maxChars cap.
|
||||
const capped = capByChars(stripped.trim(), maxChars);
|
||||
return capped.map((t, i) => ({ text: t, index: i }));
|
||||
}
|
||||
|
||||
@@ -133,14 +101,9 @@ export function chunkText(text: string, opts?: ChunkOptions): TextChunk[] {
|
||||
// v0.32.7: hard char cap. Catches pathological CJK + whitespace-less text
|
||||
// that the word-level pipeline can't bound (a single Chinese paragraph can
|
||||
// exceed 8192 OpenAI embedding tokens at any word count).
|
||||
// v4: estimated-token cap on top — the char cap alone passes token-dense
|
||||
// content (URL soup at ~1.6 chars/token) that overflows strict embedding
|
||||
// server limits.
|
||||
const capped: string[] = [];
|
||||
for (const chunk of withOverlap) {
|
||||
for (const piece of capByChars(chunk.trim(), maxChars)) {
|
||||
capped.push(...capByEstimatedTokens(piece, maxTokens));
|
||||
}
|
||||
capped.push(...capByChars(chunk.trim(), maxChars));
|
||||
}
|
||||
return capped.map((t, i) => ({ text: t, index: i }));
|
||||
}
|
||||
@@ -169,68 +132,6 @@ function capByChars(text: string, maxChars: number): string[] {
|
||||
return out;
|
||||
}
|
||||
|
||||
/**
|
||||
* How far back (in chars) the token cap looks for a friendly cut point
|
||||
* before falling back to a hard cut. 300 covers typical rollup/list line
|
||||
* lengths so forced splits land at line starts, not mid-URL.
|
||||
*/
|
||||
const TOKEN_CAP_CUT_LOOKBACK = 300;
|
||||
|
||||
/**
|
||||
* v4: hard-cap a chunk's ESTIMATED embedding tokens. Final safety pass —
|
||||
* runs after capByChars on every chunk, so no upstream miscounting
|
||||
* (whitespace-word fallback, overlap inflation, char-cap survivors) can
|
||||
* emit a chunk past `maxTokens`.
|
||||
*
|
||||
* Cut placement prefers, within the last TOKEN_CAP_CUT_LOOKBACK chars of
|
||||
* the window: a newline, then any whitespace, then a hard cut. This keeps
|
||||
* forced splits off mid-line/mid-URL positions for list-shaped content
|
||||
* and inside code fences. No overlap is added (pieces stay lossless
|
||||
* modulo the trims the char cap already applies).
|
||||
*
|
||||
* @internal exported for the code chunker (code.ts) and tests.
|
||||
*/
|
||||
export function capByEstimatedTokens(text: string, maxTokens: number): string[] {
|
||||
if (text.length === 0) return [];
|
||||
if (estimateEmbeddingTokens(text) <= maxTokens) return [text];
|
||||
|
||||
const out: string[] = [];
|
||||
let start = 0;
|
||||
while (start < text.length) {
|
||||
// Greedily extend the window until the next char would break the cap.
|
||||
// Always take at least one char so the loop makes forward progress.
|
||||
let est = 0;
|
||||
let end = start;
|
||||
while (end < text.length) {
|
||||
const w = charEmbedTokenWeight(text.charCodeAt(end));
|
||||
if (est + w > maxTokens && end > start) break;
|
||||
est += w;
|
||||
end++;
|
||||
}
|
||||
|
||||
if (end < text.length) {
|
||||
const windowStart = Math.max(start + 1, end - TOKEN_CAP_CUT_LOOKBACK);
|
||||
let cut = text.lastIndexOf('\n', end - 1);
|
||||
if (cut < windowStart) {
|
||||
cut = -1;
|
||||
for (let i = end - 1; i >= windowStart; i--) {
|
||||
const code = text.charCodeAt(i);
|
||||
if (code === 0x20 || (code >= 0x09 && code <= 0x0d)) {
|
||||
cut = i;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
if (cut >= windowStart) end = cut + 1;
|
||||
}
|
||||
|
||||
const slice = text.slice(start, end).trim();
|
||||
if (slice.length > 0) out.push(slice);
|
||||
start = end;
|
||||
}
|
||||
return out;
|
||||
}
|
||||
|
||||
function recursiveSplit(text: string, level: number, target: number): string[] {
|
||||
if (level >= DELIMITERS.length) {
|
||||
// Level 4: split on whitespace
|
||||
@@ -416,19 +317,7 @@ function extractTrailingContext(text: string, targetWords: number): string {
|
||||
* Delegated to src/core/cjk.ts so the slugify whitelist, expansion
|
||||
* detection, and PGLite keyword fallback all agree on what "CJK enough"
|
||||
* means.
|
||||
*
|
||||
* v4: floored at ceil(nonWhitespaceChars/6). The whitespace fallback
|
||||
* counts a 150-char URL as ONE word, so URL/phone/email-dense docs
|
||||
* (whose ASCII mass pushes CJK density below the 0.30 threshold) were
|
||||
* sized at a fraction of their real bulk and merged into 3-4K-char
|
||||
* chunks. The floor makes long whitespace-less runs count roughly
|
||||
* per-character while leaving normal Latin prose untouched (average
|
||||
* English word ≈ 5 chars < 6, so the whitespace count still wins).
|
||||
* Kept local to the chunker — search/expansion.ts keeps the original
|
||||
* countCJKAwareWords semantics for its query-length check.
|
||||
*/
|
||||
function countWords(text: string): number {
|
||||
const cjkAware = countCJKAwareWords(text);
|
||||
const nonWhitespace = text.replace(/\s/g, '').length;
|
||||
return Math.max(cjkAware, Math.ceil(nonWhitespace / 6));
|
||||
return countCJKAwareWords(text);
|
||||
}
|
||||
|
||||
@@ -65,64 +65,3 @@ export function countCJKAwareWords(s: string): number {
|
||||
export function escapeLikePattern(s: string): string {
|
||||
return s.replace(/\\/g, '\\\\').replace(/%/g, '\\%').replace(/_/g, '\\_');
|
||||
}
|
||||
|
||||
/**
|
||||
* Conservative per-char-class embedding-token weights (markdown chunker v4).
|
||||
*
|
||||
* Why this exists: the chunker's "word" counting drastically UNDER-counts
|
||||
* whitespace-less ASCII runs (a 150-char URL = 1 whitespace word), so
|
||||
* word-based size targets can emit chunks that overflow an embedding
|
||||
* server's per-request token limit. Measured on a local Qwen3-embedding
|
||||
* llama-server stack:
|
||||
* - URL/phone/email-dense text tokenizes at ~1.6 chars/token
|
||||
* - base64-ish / minified blobs approach ~1.3 chars/token (worst case)
|
||||
* - Korean prose tokenizes NO WORSE than 1 char/token in practice
|
||||
*
|
||||
* Weights are deliberately HIGH (tokens are overestimated) so any cap
|
||||
* based on this estimate is safe against real tokenizers:
|
||||
* - CJK char → 1.0 token (real CJK prose is cheaper)
|
||||
* - other non-space → 0.75 token (≈1.33 chars/token, covers base64)
|
||||
* - whitespace → 0.1 token (mostly folds into neighbor tokens)
|
||||
*/
|
||||
export const EMBED_TOKEN_WEIGHT_CJK = 1.0;
|
||||
export const EMBED_TOKEN_WEIGHT_OTHER = 0.75;
|
||||
export const EMBED_TOKEN_WEIGHT_WS = 0.1;
|
||||
|
||||
/** BMP CJK check by UTF-16 code unit — same ranges as CJK_SLUG_CHARS. */
|
||||
export function isCJKCodeUnit(code: number): boolean {
|
||||
return (
|
||||
(code >= 0x4e00 && code <= 0x9fff) || // Han
|
||||
(code >= 0x3040 && code <= 0x309f) || // Hiragana
|
||||
(code >= 0x30a0 && code <= 0x30ff) || // Katakana
|
||||
(code >= 0xac00 && code <= 0xd7af) // Hangul Syllables
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* Per-code-unit token weight. Unrecognized whitespace (exotic Unicode
|
||||
* spaces) intentionally falls into OTHER — that only overestimates.
|
||||
*/
|
||||
export function charEmbedTokenWeight(code: number): number {
|
||||
if (isCJKCodeUnit(code)) return EMBED_TOKEN_WEIGHT_CJK;
|
||||
if (
|
||||
code === 0x20 || (code >= 0x09 && code <= 0x0d) ||
|
||||
code === 0xa0 || code === 0x3000
|
||||
) {
|
||||
return EMBED_TOKEN_WEIGHT_WS;
|
||||
}
|
||||
return EMBED_TOKEN_WEIGHT_OTHER;
|
||||
}
|
||||
|
||||
/**
|
||||
* Tokenizer-free embedding-token estimate (conservative overestimate).
|
||||
* See weight docs above. Astral chars count as 2 OTHER code units —
|
||||
* another overestimate, which is the safe direction.
|
||||
*/
|
||||
export function estimateEmbeddingTokens(s: string): number {
|
||||
if (s.length === 0) return 0;
|
||||
let est = 0;
|
||||
for (let i = 0; i < s.length; i++) {
|
||||
est += charEmbedTokenWeight(s.charCodeAt(i));
|
||||
}
|
||||
return Math.ceil(est);
|
||||
}
|
||||
|
||||
@@ -0,0 +1,44 @@
|
||||
import { describe, expect, test } from 'bun:test';
|
||||
import { normalizeAdminClientSourceScope } from '../src/core/admin-source-scope.ts';
|
||||
|
||||
describe('admin register-client source scope normalization', () => {
|
||||
const sources = ['default', 'team-a', 'team-b'];
|
||||
|
||||
test('defaults write and read scope to default source', () => {
|
||||
expect(normalizeAdminClientSourceScope(undefined, undefined, sources)).toEqual({
|
||||
sourceId: 'default',
|
||||
federatedRead: ['default'],
|
||||
});
|
||||
});
|
||||
|
||||
test('accepts snake-case body fields with multiple read sources', () => {
|
||||
expect(normalizeAdminClientSourceScope('team-a', ['team-a', 'team-b'], sources)).toEqual({
|
||||
sourceId: 'team-a',
|
||||
federatedRead: ['team-a', 'team-b'],
|
||||
});
|
||||
});
|
||||
|
||||
test('accepts comma-separated federated_read for API callers', () => {
|
||||
expect(normalizeAdminClientSourceScope('team-a', 'team-b, default,team-b', sources)).toEqual({
|
||||
sourceId: 'team-a',
|
||||
federatedRead: ['team-b', 'default'],
|
||||
});
|
||||
});
|
||||
|
||||
test('falls back to selected write source when federated_read is empty', () => {
|
||||
expect(normalizeAdminClientSourceScope('team-b', [], sources)).toEqual({
|
||||
sourceId: 'team-b',
|
||||
federatedRead: ['team-b'],
|
||||
});
|
||||
});
|
||||
|
||||
test('rejects malformed source ids before registration', () => {
|
||||
expect(() => normalizeAdminClientSourceScope('../secret', undefined, sources)).toThrow(/Invalid source_id/);
|
||||
expect(() => normalizeAdminClientSourceScope('team-a', ['snake_case'], sources)).toThrow(/Invalid federated_read/);
|
||||
});
|
||||
|
||||
test('rejects valid-looking but unregistered source ids', () => {
|
||||
expect(() => normalizeAdminClientSourceScope('ghost', undefined, sources)).toThrow(/Unknown source_id/);
|
||||
expect(() => normalizeAdminClientSourceScope('team-a', ['ghost'], sources)).toThrow(/Unknown federated_read/);
|
||||
});
|
||||
});
|
||||
@@ -15,22 +15,19 @@ import { describe, test, expect } from 'bun:test';
|
||||
import { CHUNKER_VERSION } from '../src/core/chunkers/code.ts';
|
||||
|
||||
describe('Layer 12 — CHUNKER_VERSION constant', () => {
|
||||
test('bumped to 5 for the estimated-token hard cap', () => {
|
||||
test('bumped to 4 for Cathedral II', () => {
|
||||
// v3: v0.19.0 Chonkie parity (tokenizer + small-sibling merge).
|
||||
// v4: v0.20.0 Cathedral II (qualified names + parent scope + doc_comment
|
||||
// + fence extraction + chunk-grain FTS). Folded into content_hash
|
||||
// so any bump forces clean re-chunks on next sync.
|
||||
// v5: estimated-token hard cap on AST-path chunks (capCodeChunks) so
|
||||
// un-subdividable giant nodes can't overflow strict embedding
|
||||
// server token limits.
|
||||
expect(CHUNKER_VERSION).toBe(5);
|
||||
expect(CHUNKER_VERSION).toBe(4);
|
||||
});
|
||||
|
||||
test('is stable across imports (not recomputed at call time)', async () => {
|
||||
const a = (await import('../src/core/chunkers/code.ts')).CHUNKER_VERSION;
|
||||
const b = (await import('../src/core/chunkers/code.ts')).CHUNKER_VERSION;
|
||||
expect(a).toBe(b);
|
||||
expect(a).toBe(5);
|
||||
expect(a).toBe(4);
|
||||
});
|
||||
});
|
||||
|
||||
|
||||
@@ -10,8 +10,8 @@ import { describe, test, expect } from 'bun:test';
|
||||
import { chunkCodeText, detectCodeLanguage, CHUNKER_VERSION } from '../../src/core/chunkers/code.ts';
|
||||
|
||||
describe('CHUNKER_VERSION', () => {
|
||||
test('v5: estimated-token hard cap on AST-path chunks', () => {
|
||||
expect(CHUNKER_VERSION).toBe(5);
|
||||
test('v0.20.0 Cathedral II Layer 12 bumped to 4', () => {
|
||||
expect(CHUNKER_VERSION).toBe(4);
|
||||
});
|
||||
});
|
||||
|
||||
|
||||
@@ -135,14 +135,13 @@ describe('Recursive Text Chunker', () => {
|
||||
});
|
||||
|
||||
describe('CJK chunking (v0.32.7)', () => {
|
||||
test('MARKDOWN_CHUNKER_VERSION is 4', async () => {
|
||||
test('MARKDOWN_CHUNKER_VERSION is 3', async () => {
|
||||
// v0.40.3.0: bumped 2→3 to signal the post-upgrade reembed sweep that
|
||||
// contextual retrieval wrapping is now applied at embed time.
|
||||
// v4: estimated-token hard cap + whitespace-word undercount floor
|
||||
// (URL-dense docs produced chunks past strict embedding server token
|
||||
// limits). Boundary change → forces re-chunk for chunker_version < 4.
|
||||
// contextual retrieval wrapping is now applied at embed time. Chunk
|
||||
// boundaries themselves are unchanged; the bump forces re-embed for
|
||||
// pages where chunker_version < 3.
|
||||
const mod = await import('../../src/core/chunkers/recursive.ts');
|
||||
expect(mod.MARKDOWN_CHUNKER_VERSION).toBe(4);
|
||||
expect(mod.MARKDOWN_CHUNKER_VERSION).toBe(3);
|
||||
});
|
||||
|
||||
test('long pure-Chinese paragraph splits into multiple chunks', () => {
|
||||
|
||||
@@ -1,195 +0,0 @@
|
||||
/**
|
||||
* Markdown chunker v4 / code chunker v5 — estimated-token hard cap
|
||||
* regression tests.
|
||||
*
|
||||
* Reproduces a field failure: a local llama-server embedding backend
|
||||
* (`-ub 2048`) crashes deterministically (trace/BPT trap → EOF at the
|
||||
* client) when a single chunk exceeds ~2,050 real tokens. Two content
|
||||
* shapes triggered it:
|
||||
*
|
||||
* 1. Korean docs carrying one long source URL per line.
|
||||
* The URLs' ASCII mass pushes CJK density below 0.30, flipping
|
||||
* countCJKAwareWords to whitespace counting, where a 150-char URL
|
||||
* counts as ONE word → chunks ballooned to 3-4K chars ≈ 2,000+
|
||||
* real tokens (URL soup tokenizes at ~1.6 chars/token).
|
||||
*
|
||||
* 2. Large JSON code blocks (~7K chars) that the word pipeline
|
||||
* undercounts the same way (few whitespace tokens).
|
||||
*
|
||||
* The fix: every emitted chunk must satisfy
|
||||
* estimateEmbeddingTokens(chunk) <= maxTokens (default 1500)
|
||||
* where the estimate deliberately OVERSTATES real tokenizer counts.
|
||||
*/
|
||||
|
||||
import { describe, test, expect } from 'bun:test';
|
||||
import { chunkText, capByEstimatedTokens, DEFAULT_MAX_EST_TOKENS } from '../../src/core/chunkers/recursive.ts';
|
||||
import { chunkCodeText } from '../../src/core/chunkers/code.ts';
|
||||
import { estimateEmbeddingTokens } from '../../src/core/cjk.ts';
|
||||
|
||||
/** Synthesize the failing shape: Korean rollup lines each ending in a long Notion URL. */
|
||||
function urlDenseKoreanRollup(lines: number): string {
|
||||
const out: string[] = ['# 링크가 줄마다 붙는 한국어 예시 문서', ''];
|
||||
for (let i = 0; i < lines; i++) {
|
||||
const hex32 = (i * 2654435761 >>> 0).toString(16).padStart(8, '0').repeat(4);
|
||||
out.push(
|
||||
`- **항목 ${i}**: 이 줄은 청커 동작 검증을 위한 의미 없는 한국어 예시 문장입니다 · 전화 000-0000-${String(1000 + i)} · ` +
|
||||
`이메일 user${i}@example.com · 링크: https://docs.example.com/pages/${hex32}?v=abcdef0123456789&ref=sample`,
|
||||
);
|
||||
}
|
||||
return out.join('\n');
|
||||
}
|
||||
|
||||
/** Synthesize a large pretty-printed JSON block with CJK values. */
|
||||
function bigJsonBlock(targetChars: number): string {
|
||||
const entries: string[] = [];
|
||||
let i = 0;
|
||||
let len = 0;
|
||||
while (len < targetChars) {
|
||||
const row =
|
||||
` "item_${i}": { "name": "예시-${i}", "url": "https://example.com/api/v2/items/${i}?token=abc${i}def", "qty": ${i % 100}, "memo": "한국어 값이 섞인 예시 데이터" }`;
|
||||
entries.push(row);
|
||||
len += row.length;
|
||||
i++;
|
||||
}
|
||||
return `{\n${entries.join(',\n')}\n}`;
|
||||
}
|
||||
|
||||
describe('v4 estimated-token cap — URL-dense Korean doc (field-failure shape)', () => {
|
||||
test('every chunk stays under the estimated-token cap', () => {
|
||||
const md = urlDenseKoreanRollup(60);
|
||||
const chunks = chunkText(md);
|
||||
expect(chunks.length).toBeGreaterThan(0);
|
||||
for (const c of chunks) {
|
||||
expect(estimateEmbeddingTokens(c.text)).toBeLessThanOrEqual(DEFAULT_MAX_EST_TOKENS);
|
||||
}
|
||||
});
|
||||
|
||||
test('no chunk reaches the measured 3K-char danger zone for URL soup', () => {
|
||||
const md = urlDenseKoreanRollup(60);
|
||||
const chunks = chunkText(md);
|
||||
// 1500 est tokens at the OTHER weight (0.75/char) bounds chunks to
|
||||
// ~2,000 chars for pure ASCII — well under the ~3,300 chars where
|
||||
// URL-dense content crosses ~2,050 real tokens (1.6 chars/token).
|
||||
for (const c of chunks) {
|
||||
expect(c.text.length).toBeLessThanOrEqual(2600);
|
||||
}
|
||||
});
|
||||
|
||||
test('content is preserved (no lines dropped by the cap)', () => {
|
||||
const md = urlDenseKoreanRollup(60);
|
||||
const chunks = chunkText(md);
|
||||
const joined = chunks.map((c) => c.text).join('\n');
|
||||
// Spot-check first / middle / last rollup lines survive chunking.
|
||||
for (const marker of ['항목 0', '항목 30', '항목 59']) {
|
||||
expect(joined).toContain(marker);
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
describe('v4 estimated-token cap — large JSON blocks', () => {
|
||||
test('7K-char pretty JSON through the prose path stays under the cap', () => {
|
||||
const md = `설정 파일 원문 보존:\n\n\`\`\`\n${bigJsonBlock(7000)}\n\`\`\`\n`;
|
||||
const chunks = chunkText(md);
|
||||
expect(chunks.length).toBeGreaterThan(1);
|
||||
for (const c of chunks) {
|
||||
expect(estimateEmbeddingTokens(c.text)).toBeLessThanOrEqual(DEFAULT_MAX_EST_TOKENS);
|
||||
}
|
||||
});
|
||||
|
||||
test('7K-char minified JSON (single whitespace-less token) stays under the cap', () => {
|
||||
const minified = bigJsonBlock(7000).replace(/\n\s*/g, '');
|
||||
const chunks = chunkText(minified);
|
||||
expect(chunks.length).toBeGreaterThan(1);
|
||||
for (const c of chunks) {
|
||||
expect(estimateEmbeddingTokens(c.text)).toBeLessThanOrEqual(DEFAULT_MAX_EST_TOKENS);
|
||||
}
|
||||
});
|
||||
|
||||
test('json fence via the code chunker stays under the cap (+header slack)', async () => {
|
||||
const chunks = await chunkCodeText(bigJsonBlock(7000), 'fence.json');
|
||||
expect(chunks.length).toBeGreaterThan(0);
|
||||
for (const c of chunks) {
|
||||
// buildChunk prepends a short "[JSON] fence.json:…" header AFTER the
|
||||
// body-level cap; allow ~60 est tokens of header slack. Real-token
|
||||
// safety margin (2,050 − overestimated 1,500) absorbs this easily.
|
||||
expect(estimateEmbeddingTokens(c.text)).toBeLessThanOrEqual(DEFAULT_MAX_EST_TOKENS + 60);
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
describe('v4 word-count floor — behavior preserved for normal content', () => {
|
||||
test('Latin prose chunking is unchanged by the floor (avg word < 6 chars)', () => {
|
||||
const prose = Array.from({ length: 120 }, (_, i) =>
|
||||
`This is sentence number ${i} and it talks about ordinary things in plain words.`,
|
||||
).join(' ');
|
||||
const chunks = chunkText(prose);
|
||||
// Historical behavior: ~1,560 whitespace words → multiple ~300-word chunks.
|
||||
expect(chunks.length).toBeGreaterThan(3);
|
||||
for (const c of chunks) {
|
||||
const words = c.text.split(/\s+/).length;
|
||||
expect(words).toBeLessThanOrEqual(300 * 1.5 + 50); // merge cap + overlap
|
||||
}
|
||||
});
|
||||
|
||||
test('Korean prose (CJK-dense, no URLs) never triggers the token cap', () => {
|
||||
const prose = Array.from({ length: 80 }, (_, i) =>
|
||||
`이 문장은 순수 한국어 산문의 청킹 동작을 확인하기 위한 ${i}번째 예시 문장입니다.`,
|
||||
).join(' ');
|
||||
const chunks = chunkText(prose);
|
||||
expect(chunks.length).toBeGreaterThan(1);
|
||||
for (const c of chunks) {
|
||||
// CJK-dense chunks are char-counted (≈450 max) — nowhere near 1500.
|
||||
expect(estimateEmbeddingTokens(c.text)).toBeLessThanOrEqual(700);
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
describe('capByEstimatedTokens unit behavior', () => {
|
||||
test('returns input unchanged when under the cap', () => {
|
||||
expect(capByEstimatedTokens('short text', 1500)).toEqual(['short text']);
|
||||
expect(capByEstimatedTokens('', 1500)).toEqual([]);
|
||||
});
|
||||
|
||||
test('prefers newline cut points within the lookback window', () => {
|
||||
const line = 'x'.repeat(100);
|
||||
const text = Array.from({ length: 40 }, () => line).join('\n');
|
||||
const pieces = capByEstimatedTokens(text, 1000);
|
||||
expect(pieces.length).toBeGreaterThan(1);
|
||||
for (const p of pieces) {
|
||||
// Every piece should be whole lines (multiples of the 100-char line).
|
||||
for (const l of p.split('\n')) {
|
||||
expect(l).toBe(line);
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
test('makes forward progress on whitespace-less input (hard cut)', () => {
|
||||
const blob = 'a'.repeat(10_000);
|
||||
const pieces = capByEstimatedTokens(blob, 1000);
|
||||
expect(pieces.length).toBeGreaterThan(1);
|
||||
expect(pieces.join('')).toBe(blob);
|
||||
for (const p of pieces) {
|
||||
expect(estimateEmbeddingTokens(p)).toBeLessThanOrEqual(1000);
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
describe('estimateEmbeddingTokens — weight sanity', () => {
|
||||
test('overestimates URL-dense ASCII (0.75/char ≥ measured ~0.63/char)', () => {
|
||||
const url = 'https://docs.example.com/pages/a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4?v=abc&ref=sample';
|
||||
const est = estimateEmbeddingTokens(url);
|
||||
expect(est).toBeGreaterThanOrEqual(Math.floor(url.length * 0.7));
|
||||
});
|
||||
|
||||
test('counts CJK at 1 token/char', () => {
|
||||
expect(estimateEmbeddingTokens('가나다라마')).toBe(5);
|
||||
});
|
||||
|
||||
test('whitespace is nearly free', () => {
|
||||
expect(estimateEmbeddingTokens(' \n\t ')).toBeLessThanOrEqual(1);
|
||||
});
|
||||
|
||||
test('empty string is 0', () => {
|
||||
expect(estimateEmbeddingTokens('')).toBe(0);
|
||||
});
|
||||
});
|
||||
@@ -78,6 +78,8 @@ describe('v0.36.1.x #1077 — admin register-client supports PKCE public clients
|
||||
// (under either name) from req.body. Pin the fallback pattern so the
|
||||
// PKCE-fix regression contract stays load-bearing.
|
||||
expect(src).toMatch(/req\.body[^;]*scopes\s*\?\?\s*[^;]*scope\b/);
|
||||
expect(src).toMatch(/req\.body[^;]*source_id\s*\?\?\s*[^;]*sourceId\b/);
|
||||
expect(src).toMatch(/req\.body[^;]*federated_read\s*\?\?\s*[^;]*federatedRead\b/);
|
||||
// v0.41.3 (T4 atomicity fix, codex F4): admin endpoint now validates
|
||||
// tokenEndpointAuthMethod via the shared validator and passes it to
|
||||
// registerClientManual as a positional arg. Pre-v0.41.3 the route did
|
||||
@@ -87,6 +89,7 @@ describe('v0.36.1.x #1077 — admin register-client supports PKCE public clients
|
||||
// UPDATE block (the regex deliberately asserts the post-insert UPDATE
|
||||
// is GONE).
|
||||
expect(src).toMatch(/validateTokenEndpointAuthMethod\(tokenEndpointAuthMethod\)/);
|
||||
expect(src).toMatch(/normalizeAdminClientSourceScope\(/);
|
||||
expect(src).toMatch(/registerClientManual\([^)]*validatedAuthMethod[^)]*\)/);
|
||||
// Regression guard: post-insert UPDATE flipping client_secret_hash to
|
||||
// NULL based on a runtime check is exactly the non-atomic pattern T4
|
||||
@@ -267,3 +270,26 @@ describe('v0.42.43.0 #2095 — volunteer-events sink + cycle purge wiring (struc
|
||||
expect(src).toMatch(/purged_volunteer_events_count/);
|
||||
});
|
||||
});
|
||||
|
||||
describe('#1490 + #1036 — admin Register Agent form exposes source scope + redirect URIs', () => {
|
||||
test('Agents.tsx RegisterModal sends source_id + federated_read in the POST body (#1490)', () => {
|
||||
const src = readFileSync('admin/src/pages/Agents.tsx', 'utf8');
|
||||
expect(src).toMatch(/source_id:\s*sourceId/);
|
||||
expect(src).toMatch(/federated_read:\s*federatedRead/);
|
||||
// The source list comes from the requireAdmin-gated endpoint, not a hardcoded 'default'.
|
||||
expect(src).toMatch(/api\.sources\(\)/);
|
||||
});
|
||||
|
||||
test('serve-http.ts serves /admin/api/sources behind requireAdmin (#1490)', () => {
|
||||
const src = readFileSync('src/commands/serve-http.ts', 'utf8');
|
||||
expect(src).toMatch(/app\.get\('\/admin\/api\/sources',\s*requireAdmin/);
|
||||
});
|
||||
|
||||
test('Agents.tsx RegisterModal sends redirectUris + authorization_code grants when URIs are entered (#1036)', () => {
|
||||
const src = readFileSync('admin/src/pages/Agents.tsx', 'utf8');
|
||||
// One-per-line textarea split into an array...
|
||||
expect(src).toMatch(/redirectUris\.split\('\\n'\)/);
|
||||
// ...included in the body with the CLI's grant-type inference convention.
|
||||
expect(src).toMatch(/redirectUris:\s*uris,\s*grantTypes:\s*\['authorization_code',\s*'refresh_token'\]/);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -125,6 +125,30 @@ describe('client registration', () => {
|
||||
expect(client!.client_name).toBe('test-agent');
|
||||
});
|
||||
|
||||
test('registerClientManual persists source_id and federated_read into AuthInfo', async () => {
|
||||
await sql`
|
||||
INSERT INTO sources (id, name) VALUES (${'team-a'}, ${'Team A'}), (${'team-b'}, ${'Team B'})
|
||||
ON CONFLICT DO NOTHING
|
||||
`;
|
||||
const { clientId, clientSecret } = await provider.registerClientManual(
|
||||
'source-scoped-test',
|
||||
['client_credentials'],
|
||||
'read write',
|
||||
[],
|
||||
'team-a',
|
||||
['team-a', 'team-b'],
|
||||
);
|
||||
|
||||
const tokens = await provider.exchangeClientCredentials(clientId, clientSecret!, 'read');
|
||||
const authInfo = await provider.verifyAccessToken(tokens.access_token) as {
|
||||
sourceId?: string;
|
||||
allowedSources?: string[];
|
||||
};
|
||||
|
||||
expect(authInfo.sourceId).toBe('team-a');
|
||||
expect(authInfo.allowedSources).toEqual(['team-a', 'team-b']);
|
||||
});
|
||||
|
||||
test('getClient returns undefined for unknown client', async () => {
|
||||
const client = await provider.clientsStore.getClient('nonexistent');
|
||||
expect(client).toBeUndefined();
|
||||
|
||||
Reference in New Issue
Block a user