Compare commits

..
Author SHA1 Message Date
Garry TanandClaude Fable 5 bcdb435d73 fix(dream): deterministic last-writer attribution for colliding slugs
collectChildPutPageSlugs paired each slug to a jobId first-seen over an
unordered result set. When two children collide on a final slug, the pages
row holds the LAST put_page write, so the provenance stamp
(transcript_id/transcript_source/date) could attribute an arbitrary other
transcript. ORDER BY id + last-writer-wins aligns the stamp with the
surviving content; pinned by a collision test.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 12:14:19 -07:00
Garry TanandClaude Fable 5 093d693502 test(progress): assert net-zero live-reporter delta, not absolute zero
The 'only one process-level signal handler' test asserted
__liveReporterCountForTest() === 0, which encodes 'no other test file in
this bun process left a live reporter' — a shard-composition property,
not this test's invariant. PR #3096's new test files reshuffled the LPT
shard packing so a shardmate's live reporter now lands before
progress.test.ts in CI shard 5, failing the test deterministically
(both run attempts). Snapshot the count before the 50 lifecycles and
assert the delta is zero, mirroring the installedBefore baseline the
test already uses for the signal handler.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 11:22:03 -07:00
9268552d70 feat(dream): orchestrator-owned transcript metadata + transcriptSource discovery (#2285)
Takeover of #2286, rebased onto master so #1586's cycle-source scoping is
preserved (refs keep the cycleSourceId threading; the original branch's
rewritten collectChildPutPageSlugs hardcoded source_id 'default').

- DiscoveredTranscript carries transcriptSource, derived from the
  <corpus>/<source>/<date>/<id>.md layout; null for ad-hoc inputs.
- Transcript date inference now prefers the '| First message |' row in the
  transcript's '## Metadata' table (stable across mtime-restamping
  re-syncs), with the filename-regex date as fallback — implementing the
  cascade #2286 promised but didn't ship.
- The synthesize orchestrator stamps deterministic frontmatter
  (transcript_id, transcript_hash, transcript_source, chunk, date) through
  the existing #2569 stampDreamProvenance jsonb funnel — no second putPage
  write; reverseWriteRefs re-reads the row so DB and disk stay lockstep.
  Subagents retain authority over type/title/tags/body.

Co-authored-by: brettdavies <brettdavies@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:25:51 -07:00
22 changed files with 434 additions and 1904 deletions
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
+1 -1
View File
@@ -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-BpDk4NI4.js"></script>
<script type="module" crossorigin src="/admin/assets/index-CoGEje3-.js"></script>
<link rel="stylesheet" crossorigin href="/admin/assets/index-GxkWX7v3.css">
</head>
<body>
+2 -6
View File
@@ -5,14 +5,13 @@ import { AgentsPage } from './pages/Agents';
import { RequestLogPage } from './pages/RequestLog';
import { CalibrationPage } from './pages/Calibration';
import { JobsWatchPage } from './pages/JobsWatch';
import { SourcesPage } from './pages/Sources';
import { api } from './api';
type Page = 'login' | 'dashboard' | 'agents' | 'sources' | 'log' | 'calibration' | 'jobs';
type Page = 'login' | 'dashboard' | 'agents' | 'log' | 'calibration' | 'jobs';
function getPage(): Page {
const hash = window.location.hash.replace('#', '') || 'dashboard';
if (['login', 'dashboard', 'agents', 'sources', 'log', 'calibration', 'jobs'].includes(hash)) return hash as Page;
if (['login', 'dashboard', 'agents', 'log', 'calibration', 'jobs'].includes(hash)) return hash as Page;
return 'dashboard';
}
@@ -55,8 +54,6 @@ export function App() {
onClick={() => navigate('dashboard')}>Dashboard</a>
<a className={`nav-item ${page === 'agents' ? 'active' : ''}`}
onClick={() => navigate('agents')}>Agents</a>
<a className={`nav-item ${page === 'sources' ? 'active' : ''}`}
onClick={() => navigate('sources')}>Sources</a>
<a className={`nav-item ${page === 'log' ? 'active' : ''}`}
onClick={() => navigate('log')}>Request Log</a>
<a className={`nav-item ${page === 'calibration' ? 'active' : ''}`}
@@ -86,7 +83,6 @@ export function App() {
<main className="main">
{page === 'dashboard' && <DashboardPage />}
{page === 'agents' && <AgentsPage />}
{page === 'sources' && <SourcesPage />}
{page === 'log' && <RequestLogPage />}
{page === 'calibration' && <CalibrationPage />}
{page === 'jobs' && <JobsWatchPage />}
-18
View File
@@ -52,22 +52,4 @@ export const api = {
apiFetchText(`/admin/api/calibration/charts/${encodeURIComponent(type)}${holder ? `?holder=${encodeURIComponent(holder)}` : ''}`),
// v0.41 D2 — live minion-jobs dashboard snapshot.
jobsWatch: () => apiFetch('/admin/api/jobs/watch'),
// v0.41.29 Sources tab + federated-read management
sources: () => apiFetch('/admin/api/sources'),
agentsFederatedRead: () => apiFetch('/admin/api/agents/federated-read'),
grantRead: (clientId: string, sourceId: string) =>
apiFetch(`/admin/api/agents/${encodeURIComponent(clientId)}/grant-read`, {
method: 'POST',
body: JSON.stringify({ source_id: sourceId }),
}),
revokeRead: (clientId: string, sourceId: string) =>
apiFetch(`/admin/api/agents/${encodeURIComponent(clientId)}/revoke-read`, {
method: 'POST',
body: JSON.stringify({ source_id: sourceId }),
}),
setFederatedRead: (clientId: string, sourceIds: string[]) =>
apiFetch(`/admin/api/agents/${encodeURIComponent(clientId)}/set-federated-read`, {
method: 'POST',
body: JSON.stringify({ source_ids: sourceIds }),
}),
};
-196
View File
@@ -381,16 +381,8 @@ function CredentialsModal({ credentials, onClose }: {
);
}
interface FederationState {
source_id: string | null;
federated_read: string[];
}
function AgentDrawer({ agent, onClose, onRevoked }: { agent: Agent; onClose: () => void; onRevoked: () => void }) {
const [tab, setTab] = useState<'claude-code' | 'chatgpt' | 'claude-cowork' | 'perplexity' | 'cursor' | 'json'>('claude-code');
const [federation, setFederation] = useState<FederationState | null>(null);
const [allSources, setAllSources] = useState<string[]>([]);
const [showFederation, setShowFederation] = useState(false);
const copy = (text: string) => navigator.clipboard.writeText(text);
const serverUrl = window.location.origin;
@@ -398,30 +390,6 @@ function AgentDrawer({ agent, onClose, onRevoked }: { agent: Agent; onClose: ()
const isOAuth = agent.auth_type === 'oauth';
const agentName = agent.name || agent.client_name || 'unknown';
// Lazy-load federation state when the drawer opens for an OAuth client.
// The /admin/api/agents endpoint doesn't carry source_id / federated_read,
// so we fetch /admin/api/agents/federated-read separately and pair by id.
useEffect(() => {
if (!isOAuth || !cid) return;
let cancelled = false;
Promise.all([
api.agentsFederatedRead().catch(() => ({ clients: [] })),
api.sources().catch(() => ({ sources: [] })),
]).then(([feds, srcs]: any) => {
if (cancelled) return;
const me = (feds.clients || []).find((c: any) => c.client_id === cid);
setFederation(me ? { source_id: me.source_id, federated_read: me.federated_read || [] } : null);
setAllSources((srcs.sources || []).map((s: any) => s.source_id));
});
return () => { cancelled = true; };
}, [cid, isOAuth]);
const reloadFederation = async () => {
const feds: any = await api.agentsFederatedRead().catch(() => ({ clients: [] }));
const me = (feds.clients || []).find((c: any) => c.client_id === cid);
setFederation(me ? { source_id: me.source_id, federated_read: me.federated_read || [] } : null);
};
// For API keys, we can't show the actual token (it was shown once at creation).
// For OAuth, we show the client_id and tell them to use their secret.
@@ -585,34 +553,6 @@ function AgentDrawer({ agent, onClose, onRevoked }: { agent: Agent; onClose: ()
<span>{agent.token_ttl ? (agent.token_ttl >= 31536000 ? 'No expiry' : agent.token_ttl >= 86400 ? `${Math.floor(agent.token_ttl / 86400)}d` : agent.token_ttl >= 3600 ? `${Math.floor(agent.token_ttl / 3600)}h` : `${agent.token_ttl}s`) : '1h (default)'}</span>
</div>
{isOAuth && federation && (
<>
<div className="section-title" style={{ display: 'flex', alignItems: 'center', justifyContent: 'space-between' }}>
<span>Federation</span>
<button
className="btn btn-secondary"
style={{ padding: '4px 10px', fontSize: 12 }}
onClick={() => setShowFederation(true)}
>
Manage reads
</button>
</div>
<div style={{ display: 'grid', gridTemplateColumns: '120px 1fr', gap: '6px 12px', fontSize: 13 }}>
<span style={{ color: 'var(--text-secondary)' }}>Write source</span>
<span className="mono">{federation.source_id || '(none)'}</span>
<span style={{ color: 'var(--text-secondary)' }}>Federated reads</span>
<span style={{ fontSize: 12 }}>
{federation.federated_read.length === 0
? <span style={{ color: 'var(--text-muted)' }}>(empty no federated reads)</span>
: federation.federated_read.map((s) => (
<span key={s} className="badge badge-read" style={{ marginRight: 4, marginBottom: 2 }}>{s}</span>
))
}
</span>
</div>
</>
)}
{/*
Config Export visible for both auth_type=oauth AND auth_type=api_key.
Claude Code + Cursor + JSON tabs render real snippets regardless
@@ -688,142 +628,6 @@ function AgentDrawer({ agent, onClose, onRevoked }: { agent: Agent; onClose: ()
)}
</div>
</div>
{showFederation && federation && (
<FederationModal
clientId={cid}
clientName={agentName}
allSources={allSources}
currentReads={federation.federated_read}
writeSource={federation.source_id}
onClose={() => setShowFederation(false)}
onSaved={async () => {
await reloadFederation();
setShowFederation(false);
}}
/>
)}
</>
);
}
/**
* FederationModal admin counterpart of `gbrain auth set-federated-read`.
* Source checkbox list; "Save" submits the full new list via the
* race-safe atomic SQL path in setFederatedReadCore. Per the CLI's
* documented contract, this is wholesale-replace semantics concurrent
* grant/revoke from a CLI operator would be last-writer-wins against
* a Save here.
*/
function FederationModal({
clientId, clientName, allSources, currentReads, writeSource, onClose, onSaved,
}: {
clientId: string;
clientName: string;
allSources: string[];
currentReads: string[];
writeSource: string | null;
onClose: () => void;
onSaved: () => Promise<void> | void;
}) {
const [selected, setSelected] = useState<Set<string>>(new Set(currentReads));
const [saving, setSaving] = useState(false);
const [error, setError] = useState<string | null>(null);
const toggle = (id: string) => {
const next = new Set(selected);
if (next.has(id)) next.delete(id); else next.add(id);
setSelected(next);
};
const handleSave = async () => {
setSaving(true);
setError(null);
try {
await api.setFederatedRead(clientId, Array.from(selected));
await onSaved();
} catch (e: any) {
setError(e.message || 'save failed');
setSaving(false);
}
};
// Union: all known sources + any current reads not in the source list
// (e.g. orphan entries from before the source was deleted). The latter
// surface as "(missing source)" so operators can revoke them.
const allKnown = new Set([...allSources, ...currentReads]);
const ordered = Array.from(allKnown).sort();
return (
<div className="modal-overlay" onClick={onClose}>
<div className="modal" onClick={(e) => e.stopPropagation()} style={{ maxWidth: 520 }}>
<div className="modal-header">
<div style={{ fontSize: 16, fontWeight: 600 }}>Manage federated reads</div>
<div style={{ fontSize: 13, color: 'var(--text-secondary)', marginTop: 4 }}>
<strong>{clientName}</strong> pick which sources this client can read in addition to its
{writeSource ? <> write source <code className="mono">{writeSource}</code></> : <> write source</>}.
</div>
</div>
<div className="modal-body" style={{ maxHeight: '50vh', overflowY: 'auto' }}>
{ordered.length === 0 && (
<div style={{ color: 'var(--text-muted)', fontSize: 13 }}>
No sources registered. Use <code>gbrain sources add &lt;id&gt; --path &lt;dir&gt;</code> from the CLI first.
</div>
)}
{ordered.map((id) => {
const isOrphan = !allSources.includes(id);
const isWriteSource = id === writeSource;
return (
<label
key={id}
style={{
display: 'flex',
alignItems: 'center',
gap: 10,
padding: '8px 10px',
borderBottom: '1px solid var(--border)',
cursor: 'pointer',
fontSize: 13,
}}
>
<input
type="checkbox"
checked={selected.has(id)}
onChange={() => toggle(id)}
style={{ width: 16, height: 16, margin: 0, flexShrink: 0, cursor: 'pointer' }}
/>
<span className="mono" style={{ flex: 1, minWidth: 0, overflow: 'hidden', textOverflow: 'ellipsis', whiteSpace: 'nowrap' }}>{id}</span>
{isWriteSource && <span className="badge badge-write" style={{ fontSize: 10, flexShrink: 0 }}>write source</span>}
{isOrphan && <span className="badge badge-danger" style={{ fontSize: 10, flexShrink: 0 }}>missing source</span>}
</label>
);
})}
</div>
{error && (
<div style={{
background: 'rgba(239,68,68,0.08)',
border: '1px solid rgba(239,68,68,0.3)',
color: '#ef4444',
padding: '10px 12px',
borderRadius: 6,
margin: '12px 0',
fontSize: 12,
}}>
{error}
</div>
)}
<div className="modal-footer">
<button type="button" className="btn btn-secondary" onClick={onClose} disabled={saving}>Cancel</button>
<button
type="button"
className="btn btn-primary"
onClick={handleSave}
disabled={saving}
>
{saving ? 'Saving…' : `Save (${selected.size} source${selected.size === 1 ? '' : 's'})`}
</button>
</div>
</div>
</div>
);
}
-195
View File
@@ -1,195 +0,0 @@
import React, { useState, useEffect } from 'react';
import { api } from '../api';
interface SourceRow {
source_id: string;
name: string;
local_path: string | null;
sync_enabled: boolean;
last_sync_at: string | null;
staleness_hours: number | null;
staleness_class: 'fresh' | 'stale' | 'severe' | 'unknown';
last_commit: string | null;
pages: number;
chunks_total: number;
chunks_unembedded: number;
embedding_coverage_pct: number;
}
interface FederatedClient {
client_id: string;
client_name: string;
source_id: string | null;
federated_read: string[];
}
function timeAgo(iso: string | null): string {
if (!iso) return 'never';
const s = Math.floor((Date.now() - new Date(iso).getTime()) / 1000);
if (s < 0) return 'in the future?';
if (s < 60) return 'just now';
if (s < 3600) return `${Math.floor(s / 60)}m ago`;
if (s < 86400) return `${Math.floor(s / 3600)}h ago`;
return `${Math.floor(s / 86400)}d ago`;
}
function stalenessColor(cls: string): string {
switch (cls) {
case 'fresh': return '#4ade80';
case 'stale': return '#fbbf24';
case 'severe': return '#ef4444';
default: return 'var(--text-muted)';
}
}
function coverageColor(pct: number): string {
if (pct >= 99) return '#4ade80';
if (pct >= 90) return '#fbbf24';
return '#ef4444';
}
export function SourcesPage() {
const [sources, setSources] = useState<SourceRow[]>([]);
const [clients, setClients] = useState<FederatedClient[]>([]);
const [loading, setLoading] = useState(true);
const [error, setError] = useState<string | null>(null);
const load = async () => {
setLoading(true);
setError(null);
try {
const [srcReport, clientsResp] = await Promise.all([
api.sources(),
api.agentsFederatedRead(),
]);
setSources(srcReport.sources || []);
setClients(clientsResp.clients || []);
} catch (e: any) {
setError(e.message || 'load failed');
} finally {
setLoading(false);
}
};
useEffect(() => { load(); }, []);
// Reverse-lookup: for each source, which clients can read it?
const readersBySource = (sourceId: string): string[] =>
clients.filter((c) => c.federated_read.includes(sourceId)).map((c) => c.client_name);
// Reverse-lookup: which clients WRITE to this source (source_id == sourceId)?
const writersBySource = (sourceId: string): string[] =>
clients.filter((c) => c.source_id === sourceId).map((c) => c.client_name);
return (
<div style={{ padding: 24, maxWidth: 1200 }}>
<div style={{ display: 'flex', alignItems: 'center', justifyContent: 'space-between', marginBottom: 24 }}>
<h1 style={{ fontSize: 24, margin: 0 }}>Sources</h1>
<button
onClick={load}
style={{
background: 'transparent',
border: '1px solid var(--border)',
color: 'var(--text-secondary)',
padding: '6px 12px',
borderRadius: 6,
fontSize: 12,
cursor: 'pointer',
}}
>
Refresh
</button>
</div>
{loading && <div style={{ color: 'var(--text-muted)' }}>Loading</div>}
{error && (
<div style={{
background: 'rgba(239,68,68,0.08)',
border: '1px solid rgba(239,68,68,0.3)',
color: '#ef4444',
padding: 12,
borderRadius: 6,
marginBottom: 16,
fontSize: 13,
}}>
Failed to load sources: {error}
</div>
)}
{!loading && !error && sources.length === 0 && (
<div style={{ color: 'var(--text-muted)', padding: 16 }}>
No active sources with a local_path. Use{' '}
<code style={{ background: 'var(--bg-elevated)', padding: '2px 6px', borderRadius: 4 }}>
gbrain sources add &lt;id&gt; --path &lt;dir&gt;
</code>{' '}
to register one.
</div>
)}
{!loading && !error && sources.length > 0 && (
<div style={{ overflowX: 'auto' }}>
<table style={{ width: '100%', borderCollapse: 'collapse', fontSize: 13 }}>
<thead>
<tr style={{ borderBottom: '1px solid var(--border)', textAlign: 'left', color: 'var(--text-muted)' }}>
<th style={{ padding: '10px 12px' }}>ID</th>
<th style={{ padding: '10px 12px', textAlign: 'right' }}>Pages</th>
<th style={{ padding: '10px 12px', textAlign: 'right' }}>Chunks</th>
<th style={{ padding: '10px 12px', textAlign: 'right' }}>Embed%</th>
<th style={{ padding: '10px 12px' }}>Last Sync</th>
<th style={{ padding: '10px 12px' }}>Writers</th>
<th style={{ padding: '10px 12px' }}>Readers (federated)</th>
</tr>
</thead>
<tbody>
{sources.map((s) => {
const readers = readersBySource(s.source_id);
const writers = writersBySource(s.source_id);
return (
<tr key={s.source_id} style={{ borderBottom: '1px solid var(--border)' }}>
<td style={{ padding: '10px 12px', fontFamily: 'JetBrains Mono, monospace' }}>
<div>{s.source_id}</div>
{s.name !== s.source_id && (
<div style={{ fontSize: 11, color: 'var(--text-muted)', fontFamily: 'inherit' }}>{s.name}</div>
)}
</td>
<td style={{ padding: '10px 12px', textAlign: 'right', fontFamily: 'JetBrains Mono, monospace' }}>{s.pages.toLocaleString()}</td>
<td style={{ padding: '10px 12px', textAlign: 'right', fontFamily: 'JetBrains Mono, monospace' }}>{s.chunks_total.toLocaleString()}</td>
<td style={{ padding: '10px 12px', textAlign: 'right', color: coverageColor(s.embedding_coverage_pct), fontFamily: 'JetBrains Mono, monospace' }}>
{s.embedding_coverage_pct.toFixed(0)}%
</td>
<td style={{ padding: '10px 12px', color: s.local_path == null ? 'var(--text-muted)' : stalenessColor(s.staleness_class) }}>
{s.local_path == null ? 'push-only' : timeAgo(s.last_sync_at)}
</td>
<td style={{ padding: '10px 12px', fontSize: 12, color: 'var(--text-secondary)' }}>
{writers.length === 0 ? <span style={{ color: 'var(--text-muted)' }}>none</span> : writers.join(', ')}
</td>
<td style={{ padding: '10px 12px', fontSize: 12, color: 'var(--text-secondary)' }}>
{readers.length === 0 ? <span style={{ color: 'var(--text-muted)' }}>none</span> : readers.join(', ')}
</td>
</tr>
);
})}
</tbody>
</table>
</div>
)}
<div style={{
marginTop: 24,
padding: 12,
background: 'var(--bg-elevated)',
border: '1px solid var(--border)',
borderRadius: 6,
fontSize: 12,
color: 'var(--text-muted)',
lineHeight: 1.6,
}}>
<strong style={{ color: 'var(--text-secondary)' }}>Two scopes per OAuth client:</strong>{' '}
<em>Writers</em> = clients with this source as their <code>source_id</code> (write authority).{' '}
<em>Readers</em> = clients with this source in their <code>federated_read</code> list (read access via federation).
Manage federation per-client from the <a href="#agents" style={{ color: '#60a5fa' }}>Agents</a> tab using the
"Manage reads" action.
</div>
</div>
);
}
+3 -3
View File
@@ -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 2026-07-22.
// Source: admin/dist/ at 2026-05-27.
//
// 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_BpDk4NI4_js from '../admin/dist/assets/index-BpDk4NI4.js' with { type: 'file' };
import A_0_assets_index_CoGEje3__js from '../admin/dist/assets/index-CoGEje3-.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-BpDk4NI4.js": { path: A_0_assets_index_BpDk4NI4_js as unknown as string, mime: "application/javascript; charset=utf-8" },
"/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-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" },
};
+1 -586
View File
@@ -24,8 +24,6 @@ import { loadConfig, toEngineConfig } from '../core/config.ts';
import { createEngine } from '../core/engine-factory.ts';
import type { BrainEngine } from '../core/engine.ts';
import { sqlQueryForEngine, executeRawJsonb, type SqlQuery } from '../core/sql-query.ts';
import { pgArray } from '../core/oauth-provider.ts';
import { assertValidSourceId } from '../core/source-id.ts';
function hashToken(token: string): string {
return createHash('sha256').update(token).digest('hex');
@@ -167,100 +165,6 @@ async function list() {
});
}
/**
* `gbrain auth list-clients [--json]` read surface for OAuth 2.1 clients.
*
* The existing `gbrain auth list` shows LEGACY bearer tokens from
* `access_tokens`; this is the parallel for v0.26+ OAuth clients. Separate
* commands rather than merged output because the two models have different
* field sets (legacy: lifecycle dates; OAuth: scopes + source_id +
* federated_read).
*
* Human output is card-style (multi-line per client) instead of a fixed-
* width table federated_read can hold many ids per client and a wide
* single-line layout truncates / wraps badly on terminals < 200 cols.
* JSON output uses a `schema_version: 1` envelope; additive only.
*/
async function listClients(args: string[]) {
const json = args.includes('--json');
const includeDeleted = args.includes('--include-deleted');
await withConfiguredSql(async (sql) => {
// Codex finding #2 (medium): default-hide soft-deleted clients so admin
// soft-deletes are honored by the CLI surface. Opt-in via flag.
const rows = includeDeleted
? await sql`
SELECT client_id, client_name, scope, source_id, federated_read,
grant_types, created_at, deleted_at
FROM oauth_clients
ORDER BY client_name
`
: await sql`
SELECT client_id, client_name, scope, source_id, federated_read,
grant_types, created_at, deleted_at
FROM oauth_clients
WHERE deleted_at IS NULL
ORDER BY client_name
`;
if (json) {
const clients = rows.map((r) => ({
client_id: String(r.client_id),
client_name: String(r.client_name),
scope: r.scope == null ? null : String(r.scope),
source_id: r.source_id == null ? null : String(r.source_id),
federated_read: Array.isArray(r.federated_read)
? (r.federated_read as string[]).map(String)
: [],
grant_types: Array.isArray(r.grant_types)
? (r.grant_types as string[]).map(String)
: [],
created_at:
r.created_at instanceof Date
? r.created_at.toISOString()
: r.created_at == null
? null
: String(r.created_at),
deleted_at:
r.deleted_at instanceof Date
? r.deleted_at.toISOString()
: r.deleted_at == null
? null
: String(r.deleted_at),
}));
process.stdout.write(JSON.stringify({ schema_version: 1, clients }, null, 2) + '\n');
return;
}
if (rows.length === 0) {
console.log(
includeDeleted
? 'No OAuth clients found (including deleted). Register one: gbrain auth register-client <name>'
: 'No active OAuth clients found. Register one: gbrain auth register-client <name>'
+ '\n(Use --include-deleted to also show soft-deleted clients.)',
);
return;
}
for (let i = 0; i < rows.length; i++) {
const r = rows[i];
const fed = Array.isArray(r.federated_read)
? (r.federated_read as string[]).map(String)
: [];
const grants = Array.isArray(r.grant_types)
? (r.grant_types as string[]).map(String)
: [];
const deletedAt = r.deleted_at;
const status = deletedAt == null
? ''
: ` [SOFT-DELETED ${deletedAt instanceof Date ? deletedAt.toISOString() : String(deletedAt)}]`;
console.log(`${sanitizeForTerminal(String(r.client_name))}${status}`);
console.log(` client_id: ${sanitizeForTerminal(String(r.client_id))}`);
console.log(` scope: ${r.scope == null ? '(none)' : sanitizeForTerminal(String(r.scope))}`);
console.log(` grant types: ${grants.length ? sanitizeForTerminal(grants.join(', ')) : '(none)'}`);
console.log(` write source: ${r.source_id == null ? '(none)' : sanitizeForTerminal(String(r.source_id))}`);
console.log(` federated: ${fed.length ? sanitizeForTerminal(fed.join(', ')) : '(empty)'}`);
if (i < rows.length - 1) console.log('');
}
});
}
async function revoke(name: string) {
if (!name) { console.error('Usage: auth revoke <name>'); process.exit(1); }
await withConfiguredSql(async (sql) => {
@@ -397,475 +301,6 @@ async function test(url: string, token: string) {
console.log(`\n🧠 Your brain is live! (${elapsed}s)`);
}
/**
* Strip ANSI escapes + C0/C1 control characters from a string before
* printing it to the operator's terminal. Defense for the
* codex-flagged terminal-control-injection class: a client_name or
* source_id registered via DCR with `\x1b[2J` (clear-screen) or
* `\x1b]0;TITLE\x07` (OSC title-change) would poison
* `gbrain auth list-clients` output otherwise.
*
* Replaces unsafe bytes with their `\xNN` hex escape so the operator
* sees that something weird is in the field, instead of silent
* mutilation. Tab and newline are preserved as-is so legitimate
* multi-line values render.
*/
export function sanitizeForTerminal(s: string): string {
// ALL C0/C1 controls + DEL get escaped. Codex re-review caught that
// preserving `\n` lets a DCR-registered client_name spoof additional
// human-output lines in list-clients (a real attack — newline in the
// name visually adds a fake row to the operator's terminal). Tab is
// also escaped for the same reason — field-separator spoofing.
// C0: 0x00-0x1F. DEL: 0x7F. C1: 0x80-0x9F.
return s.replace(/[\x00-\x1f\x7f-\x9f]/g, (ch) =>
`\\x${ch.charCodeAt(0).toString(16).padStart(2, '0')}`,
);
}
export interface ResolvedClient {
client_id: string;
client_name: string;
source_id: string | null;
federated_read: string[];
deleted_at: Date | string | null;
}
export type FederatedReadOutcome =
| { kind: 'noop'; reason: 'already-granted' | 'not-present' | 'same-list'; client: ResolvedClient; current: string[] }
| { kind: 'updated'; client: ResolvedClient; before: string[]; after: string[] };
/**
* Resolve an OAuth client by client_id (exact) or client_name (unique).
* Errors on no-match and on ambiguous client_name (>1 row). client_id
* takes precedence if a long hash is passed and matches, returns
* immediately without ever querying by name.
*
* Legacy bearer tokens in `access_tokens` are NOT searched. Federated read
* scope is an OAuth-client concept (oauth_clients.federated_read column);
* legacy bearers have no source scope.
*/
/**
* Resolve an OAuth client. Codex finding #2 (medium): default-hide
* soft-deleted clients so admin-soft-deleted rows aren't mutated by the
* CLI. The `includeDeleted` opt is reserved for future read-side surfaces;
* grant/revoke/set ALWAYS filter active rows only.
*/
export async function resolveClient(
sql: SqlQuery,
nameOrId: string,
opts: { includeDeleted?: boolean } = {},
): Promise<ResolvedClient> {
const allowDeleted = opts.includeDeleted === true;
const byId = allowDeleted
? await sql`
SELECT client_id, client_name, source_id, federated_read, deleted_at
FROM oauth_clients WHERE client_id = ${nameOrId} LIMIT 1
`
: await sql`
SELECT client_id, client_name, source_id, federated_read, deleted_at
FROM oauth_clients WHERE client_id = ${nameOrId} AND deleted_at IS NULL LIMIT 1
`;
if (byId.length === 1) return normalizeClientRow(byId[0]);
const byName = allowDeleted
? await sql`
SELECT client_id, client_name, source_id, federated_read, deleted_at
FROM oauth_clients WHERE client_name = ${nameOrId}
`
: await sql`
SELECT client_id, client_name, source_id, federated_read, deleted_at
FROM oauth_clients WHERE client_name = ${nameOrId} AND deleted_at IS NULL
`;
if (byName.length === 0) {
throw new Error(
`No active OAuth client found with name or id "${nameOrId}". ` +
`Run \`gbrain auth register-client <name>\` to create one, ` +
`or \`gbrain auth list-clients\` to see what exists. ` +
`(Soft-deleted clients are hidden by default.)`,
);
}
if (byName.length > 1) {
const ids = byName.map((r) => ` ${String(r.client_id)}`).join('\n');
throw new Error(
`Multiple active OAuth clients named "${nameOrId}". Pass the full client_id instead:\n${ids}`,
);
}
return normalizeClientRow(byName[0]);
}
function normalizeClientRow(row: Record<string, unknown>): ResolvedClient {
const fed = row.federated_read;
return {
client_id: String(row.client_id),
client_name: String(row.client_name),
source_id: row.source_id == null ? null : String(row.source_id),
federated_read: Array.isArray(fed) ? (fed as string[]).map(String) : [],
deleted_at: row.deleted_at == null
? null
: (row.deleted_at as Date | string),
};
}
/**
* Validate the source_id shape AND DB existence. Codex finding #3 (medium):
* a manually-INSERTed source row with weird chars (e.g. comma, quote)
* would otherwise land in oauth_clients.federated_read as a never-deletable
* malformed entry. Fail at the boundary before the existence query so
* malformed input gets the validator's hint, not a "does not exist" hint
* pointing at a non-creatable id.
*/
export async function assertSourceExists(sql: SqlQuery, sourceId: string): Promise<void> {
assertValidSourceId(sourceId);
const rows = await sql`SELECT id FROM sources WHERE id = ${sourceId} LIMIT 1`;
if (rows.length === 0) {
throw new Error(
`Source "${sourceId}" does not exist. Run \`gbrain sources list\` to see registered sources, ` +
`or \`gbrain sources add ${sourceId}\` to create it.`,
);
}
}
/**
* Atomic append: array_append + NOT-ANY guard so the row-lock fully
* serializes concurrent grant/revoke against the same client. Codex
* finding #1 (HIGH): the previous read-modify-write shape allowed a
* concurrent revoke to be silently UNDONE by a racing grant.
*
* Returns the post-write federated_read array, or null when no rows
* matched (already-granted, soft-deleted, or missing client). Callers
* disambiguate via prior resolveClient + includes() check.
*
* `WHERE deleted_at IS NULL` is part of the atomic guard so a client
* soft-deleted between resolveClient and the UPDATE can't be mutated.
*/
async function appendFederatedReadAtomic(
sql: SqlQuery,
clientId: string,
sourceId: string,
): Promise<string[] | null> {
const rows = await sql`
UPDATE oauth_clients
SET federated_read = array_append(federated_read, ${sourceId})
WHERE client_id = ${clientId}
AND deleted_at IS NULL
AND NOT (${sourceId} = ANY(federated_read))
RETURNING federated_read
`;
if (rows.length === 0) return null;
const fed = rows[0].federated_read;
return Array.isArray(fed) ? (fed as string[]).map(String) : [];
}
/**
* Atomic remove: array_remove + ANY guard. Same race-correctness story
* as appendFederatedReadAtomic. Returns post-write array or null.
*/
async function removeFederatedReadAtomic(
sql: SqlQuery,
clientId: string,
sourceId: string,
): Promise<string[] | null> {
const rows = await sql`
UPDATE oauth_clients
SET federated_read = array_remove(federated_read, ${sourceId})
WHERE client_id = ${clientId}
AND deleted_at IS NULL
AND ${sourceId} = ANY(federated_read)
RETURNING federated_read
`;
if (rows.length === 0) return null;
const fed = rows[0].federated_read;
return Array.isArray(fed) ? (fed as string[]).map(String) : [];
}
/**
* Wholesale array overwrite for `set-federated-read`. Honors the
* deleted_at filter. Last-writer-wins semantics under concurrent
* `set` calls is acceptable the user is asserting "this exact list"
* intent; concurrent set+set just means whichever ran second wins.
* Concurrent set+grant or set+revoke is also last-writer-wins, which
* is the documented contract for `set`.
*/
async function replaceFederatedReadAtomic(
sql: SqlQuery,
clientId: string,
next: string[],
): Promise<string[] | null> {
// TEXT[] binding via pgArray() string-literal escaping (see helper
// for the security note). Our narrow SqlQuery surface
// (src/core/sql-query.ts) doesn't bind JS arrays directly.
const literal = pgArray(next);
const rows = await sql`
UPDATE oauth_clients
SET federated_read = ${literal}
WHERE client_id = ${clientId}
AND deleted_at IS NULL
RETURNING federated_read
`;
if (rows.length === 0) return null;
const fed = rows[0].federated_read;
return Array.isArray(fed) ? (fed as string[]).map(String) : [];
}
/**
* Pure helper: dedupe a comma-separated source-id list while preserving
* insertion order. Empty input empty array. Exported so the CLI parser
* and tests share one normalizer.
*/
export function parseSourceCsv(csv: string): string[] {
const requested = csv.split(',').map((s) => s.trim()).filter(Boolean);
const seen = new Set<string>();
const out: string[] = [];
for (const s of requested) {
if (!seen.has(s)) {
seen.add(s);
out.push(s);
}
}
return out;
}
export interface FederatedReadOpts {
/** When true, compute the outcome but skip the persisting UPDATE. */
dryRun?: boolean;
}
/**
* Core: append a source to the client's federated_read.
*
* Atomicity contract (Codex finding #1, HIGH):
* The actual write goes through `appendFederatedReadAtomic` which
* serializes at the row-lock so concurrent grant/revoke against the
* same client cannot lose updates. The race vector that previously
* silently restored revoked access is closed: under two operators
* racing `revoke-read sensitive` + `grant-read harmless`, postgres
* serializes the two UPDATEs and BOTH ops apply (sensitive removed,
* harmless added), instead of one clobbering the other.
*
* The reported `before` is the snapshot at resolveClient time, which
* may be stale relative to a concurrent racer. The `after` reflects
* the post-UPDATE state from RETURNING (always fresh).
*/
export async function grantReadCore(
sql: SqlQuery,
nameOrId: string,
sourceId: string,
opts: FederatedReadOpts = {},
): Promise<FederatedReadOutcome> {
const client = await resolveClient(sql, nameOrId);
await assertSourceExists(sql, sourceId);
if (client.federated_read.includes(sourceId)) {
return { kind: 'noop', reason: 'already-granted', client, current: client.federated_read };
}
if (opts.dryRun) {
// Compute the would-be result without touching the row. Last-known
// snapshot is best-effort under concurrent writes.
const projected = [...client.federated_read, sourceId];
return { kind: 'updated', client, before: client.federated_read, after: projected };
}
const after = await appendFederatedReadAtomic(sql, client.client_id, sourceId);
if (after === null) {
// Two equivalent failure modes: (a) racing grant-read already added
// the source and the NOT-ANY guard suppressed our UPDATE, or
// (b) the client was soft-deleted between resolveClient and UPDATE.
// (a) is the more common path. Re-resolve to confirm + report.
const reresolved = await resolveClient(sql, client.client_id, { includeDeleted: true });
if (reresolved.deleted_at != null) {
throw new Error(`Client "${client.client_name}" was soft-deleted before write could land.`);
}
return { kind: 'noop', reason: 'already-granted', client: reresolved, current: reresolved.federated_read };
}
return { kind: 'updated', client, before: client.federated_read, after };
}
/**
* Core: remove a source from the client's federated_read. Atomic via
* array_remove + ANY-guard. Same race-correctness rationale as
* grantReadCore concurrent ops serialize at the row lock.
*/
export async function revokeReadCore(
sql: SqlQuery,
nameOrId: string,
sourceId: string,
opts: FederatedReadOpts = {},
): Promise<FederatedReadOutcome> {
const client = await resolveClient(sql, nameOrId);
if (!client.federated_read.includes(sourceId)) {
return { kind: 'noop', reason: 'not-present', client, current: client.federated_read };
}
if (opts.dryRun) {
const projected = client.federated_read.filter((s) => s !== sourceId);
return { kind: 'updated', client, before: client.federated_read, after: projected };
}
const after = await removeFederatedReadAtomic(sql, client.client_id, sourceId);
if (after === null) {
// Same disambiguation as grant: either a concurrent revoke already
// removed the source (most common) or the client was soft-deleted.
const reresolved = await resolveClient(sql, client.client_id, { includeDeleted: true });
if (reresolved.deleted_at != null) {
throw new Error(`Client "${client.client_name}" was soft-deleted before write could land.`);
}
return { kind: 'noop', reason: 'not-present', client: reresolved, current: reresolved.federated_read };
}
return { kind: 'updated', client, before: client.federated_read, after };
}
/**
* Core: replace the whole federated_read list. Idempotent on same list.
*
* Race semantics: wholesale-overwrite + deleted_at guard. Concurrent
* set+set is last-writer-wins (documented contract for `set` the
* operator is asserting the exact list). Concurrent set+grant or
* set+revoke is also last-writer-wins. If a strict-merge semantics is
* needed, use grant-read / revoke-read individually.
*/
export async function setFederatedReadCore(
sql: SqlQuery,
nameOrId: string,
sourceCsv: string,
opts: FederatedReadOpts = {},
): Promise<FederatedReadOutcome> {
const next = parseSourceCsv(sourceCsv);
const client = await resolveClient(sql, nameOrId);
for (const s of next) {
await assertSourceExists(sql, s);
}
const prev = client.federated_read;
const same = prev.length === next.length && prev.every((v, i) => v === next[i]);
if (same) {
return { kind: 'noop', reason: 'same-list', client, current: prev };
}
if (opts.dryRun) {
return { kind: 'updated', client, before: prev, after: next };
}
const after = await replaceFederatedReadAtomic(sql, client.client_id, next);
if (after === null) {
throw new Error(`Client "${client.client_name}" was soft-deleted before write could land.`);
}
return { kind: 'updated', client, before: prev, after };
}
function printOutcome(
verb: 'grant' | 'revoke' | 'set',
sourceArg: string,
outcome: FederatedReadOutcome,
dryRun: boolean,
): void {
// Terminal-injection defense (Codex finding #5, low): a client_name
// registered via DCR with ANSI escapes or control chars would
// otherwise poison this output. Sanitize ALL strings that round-trip
// from the DB before printing.
const s = sanitizeForTerminal;
const prefix = dryRun ? '[dry-run] ' : '';
if (outcome.kind === 'noop') {
const name = s(outcome.client.client_name);
if (outcome.reason === 'already-granted') {
console.log(`${prefix}No change: "${name}" already reads "${s(sourceArg)}".`);
} else if (outcome.reason === 'not-present') {
console.log(`${prefix}No change: "${name}" did not read "${s(sourceArg)}".`);
} else {
console.log(`${prefix}No change: "${name}" federated_read already matches.`);
}
console.log(` federated_read: ${outcome.current.map(s).join(', ') || '(empty)'}`);
return;
}
const { client, before, after } = outcome;
const name = s(client.client_name);
const wouldOrDid = dryRun ? 'Would' : 'Did';
if (verb === 'grant') {
console.log(`${prefix}${wouldOrDid} grant: "${name}" can now read "${s(sourceArg)}".`);
console.log(` federated_read: ${after.map(s).join(', ')}`);
} else if (verb === 'revoke') {
console.log(`${prefix}${wouldOrDid} revoke: "${name}" no longer reads "${s(sourceArg)}".`);
console.log(` federated_read: ${after.map(s).join(', ') || '(empty — client has no federated reads)'}`);
} else {
console.log(`${prefix}${wouldOrDid} update "${name}" federated_read:`);
console.log(` before: ${before.map(s).join(', ') || '(empty)'}`);
console.log(` after: ${after.map(s).join(', ') || '(empty)'}`);
}
if (after.length === 0) {
console.log(
'Warning: client now reads no sources via federation. Queries through this ' +
'client will only see content scoped explicitly via its write source.',
);
}
}
/**
* Strip `--dry-run` from a positional-arg list. Returns the filtered list
* plus the flag value. Kept positional-tolerant the existing
* `auth grant-read alice source` shape MUST keep working, AND
* `auth grant-read alice source --dry-run` AND `auth grant-read --dry-run alice source`.
*/
export function extractDryRun(args: string[]): { dryRun: boolean; rest: string[] } {
let dryRun = false;
const rest: string[] = [];
for (const a of args) {
if (a === '--dry-run') {
dryRun = true;
continue;
}
rest.push(a);
}
return { dryRun, rest };
}
async function grantRead(args: string[]): Promise<void> {
const { dryRun, rest } = extractDryRun(args);
const [nameOrId, sourceId] = rest;
if (!nameOrId || !sourceId) {
console.error('Usage: gbrain auth grant-read <client-name-or-id> <source-id> [--dry-run]');
process.exit(1);
}
try {
await withConfiguredSql(async (sql) => {
const outcome = await grantReadCore(sql, nameOrId, sourceId, { dryRun });
printOutcome('grant', sourceId, outcome, dryRun);
});
} catch (e: any) {
console.error('Error:', e.message);
process.exit(1);
}
}
async function revokeRead(args: string[]): Promise<void> {
const { dryRun, rest } = extractDryRun(args);
const [nameOrId, sourceId] = rest;
if (!nameOrId || !sourceId) {
console.error('Usage: gbrain auth revoke-read <client-name-or-id> <source-id> [--dry-run]');
process.exit(1);
}
try {
await withConfiguredSql(async (sql) => {
const outcome = await revokeReadCore(sql, nameOrId, sourceId, { dryRun });
printOutcome('revoke', sourceId, outcome, dryRun);
});
} catch (e: any) {
console.error('Error:', e.message);
process.exit(1);
}
}
async function setFederatedRead(args: string[]): Promise<void> {
const { dryRun, rest } = extractDryRun(args);
const [nameOrId, sourceCsv] = rest;
if (!nameOrId || sourceCsv === undefined) {
console.error(
'Usage: gbrain auth set-federated-read <client-name-or-id> <source-id1,source-id2,...> [--dry-run]',
);
console.error('Pass an empty string ("") to clear all federated reads.');
process.exit(1);
}
try {
await withConfiguredSql(async (sql) => {
const outcome = await setFederatedReadCore(sql, nameOrId, sourceCsv, { dryRun });
printOutcome('set', sourceCsv, outcome, dryRun);
});
} catch (e: any) {
console.error('Error:', e.message);
process.exit(1);
}
}
async function revokeClient(clientId: string) {
if (!clientId) {
console.error('Usage: auth revoke-client <client_id>');
@@ -884,7 +319,7 @@ async function revokeClient(clientId: string) {
console.error(`No client found with id "${clientId}"`);
process.exit(1);
}
console.log(`OAuth client revoked: "${sanitizeForTerminal(String(rows[0].client_name))}" (${clientId})`);
console.log(`OAuth client revoked: "${rows[0].client_name}" (${clientId})`);
console.log('Tokens and authorization codes purged via cascade.');
});
} catch (e: any) {
@@ -1005,15 +440,6 @@ export function parseRegisterClientArgs(args: string[]): RegisterClientArgs {
if (!grantTypesSet && out.redirectUris.length > 0) {
out.grantTypes = ['authorization_code', 'refresh_token'];
}
// Codex re-review (medium): validate source_id shape at the CLI boundary
// so register-client can't seed malformed entries into source_id /
// federated_read that subsequent grant/revoke/set commands can't manage.
assertValidSourceId(out.sourceId);
if (out.federatedRead) {
for (const s of out.federatedRead) {
assertValidSourceId(s);
}
}
return out;
}
@@ -1131,10 +557,6 @@ export async function runAuth(args: string[]): Promise<void> {
}
case 'register-client': await registerClient(rest[0], rest.slice(1)); return;
case 'revoke-client': await revokeClient(rest[0]); return;
case 'list-clients': await listClients(rest); return;
case 'grant-read': await grantRead(rest); return;
case 'revoke-read': await revokeRead(rest); return;
case 'set-federated-read': await setFederatedRead(rest); return;
case 'test': {
const tokenIdx = rest.indexOf('--token');
const url = rest.find(a => !a.startsWith('--') && a !== rest[tokenIdx + 1]);
@@ -1172,13 +594,6 @@ Usage:
--bound-max-concurrent <n> Bound submit_agent concurrency (default: 1)
--budget-usd-per-day <usd> Bound submit_agent daily spend cap
gbrain auth revoke-client <client_id> Hard-delete an OAuth 2.1 client (cascades to tokens + codes)
gbrain auth list-clients [--json] List OAuth 2.1 clients with scope + write source + federated_read.
gbrain auth grant-read <name|client_id> <source-id> [--dry-run]
Add a source to the client's federated_read list (idempotent).
gbrain auth revoke-read <name|client_id> <source-id> [--dry-run]
Remove a source from the client's federated_read list (idempotent).
gbrain auth set-federated-read <name|client_id> "<id1,id2,...>" [--dry-run]
Replace the client's whole federated_read list. Pass "" to clear.
gbrain auth test <url> --token <token> Smoke-test a remote MCP server
`);
}
-141
View File
@@ -365,42 +365,6 @@ export interface AgentClientSpend {
inflight_count: number;
}
/**
* `/admin/api/sources` source list the input rows for buildSyncStatusReport.
*
* Queries the JSONB config column directly (listSources doesn't carry it,
* but buildSyncStatusReport needs syncEnabled / strategy fields).
*
* Deliberately does NOT filter on local_path: in a push-only deployment
* (content arrives via MCP put_page / capture / ingest, not `gbrain sync`
* of a server checkout) every source has a null local_path filtering on
* it would empty both the Sources tab AND the federation source-picker.
* buildSyncStatusReport does no disk I/O, so null-local_path sources
* report fine (pages/chunks from SQL, staleness 'unknown' / never-synced).
*/
export async function queryAdminSources(engine: BrainEngine): Promise<
Array<{ id: string; name: string; local_path: string | null; config: Record<string, unknown> }>
> {
const rows = await engine.executeRaw<{
id: string;
name: string;
local_path: string | null;
config: Record<string, unknown> | string | null;
}>(
`SELECT id, name, local_path, config FROM sources
WHERE archived IS NOT TRUE
ORDER BY id`,
);
return rows.map((r) => ({
id: r.id,
name: r.name,
local_path: r.local_path,
config: typeof r.config === 'string'
? (JSON.parse(r.config) as Record<string, unknown>)
: (r.config ?? {}),
}));
}
export async function queryAgentClientSpend(engine: BrainEngine): Promise<AgentClientSpend[]> {
const sql = sqlQueryForEngine(engine);
const rows = await sql`
@@ -1547,111 +1511,6 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
}
});
// ---------------------------------------------------------------------------
// Sources tab — read-only view of registered sources with sync + embed
// coverage stats. Drives the admin SPA's `Sources` page.
//
// Returns the same shape `gbrain sources status --json` prints, so the
// SPA stays in lockstep with the CLI surface.
// ---------------------------------------------------------------------------
app.get('/admin/api/sources', requireAdmin, async (_req: Request, res: Response) => {
try {
const { buildSyncStatusReport } = await import('./sync.ts');
const report = await buildSyncStatusReport(engine, await queryAdminSources(engine));
res.json(report);
} catch (e) {
const msg = e instanceof Error ? e.message : String(e);
res.status(503).json({ error: 'service_unavailable', detail: msg });
}
});
// ---------------------------------------------------------------------------
// Federated-read management (admin-side counterparts of the CLI commands
// `gbrain auth grant-read / revoke-read / set-federated-read`). All three
// route through the same *Core helpers as the CLI so race-safety,
// soft-delete filter, and source-id shape validation apply uniformly.
//
// The admin SPA's `Agents` page renders "Manage reads" actions per
// client backed by these endpoints.
// ---------------------------------------------------------------------------
app.get('/admin/api/agents/federated-read', requireAdmin, async (_req: Request, res: Response) => {
try {
const rows = await sql`
SELECT client_id, client_name, source_id, federated_read
FROM oauth_clients
WHERE deleted_at IS NULL
ORDER BY client_name
`;
const clients = rows.map((r) => ({
client_id: String(r.client_id),
client_name: String(r.client_name),
source_id: r.source_id == null ? null : String(r.source_id),
federated_read: Array.isArray(r.federated_read)
? (r.federated_read as string[]).map(String)
: [],
}));
res.json({ clients });
} catch (e) {
const msg = e instanceof Error ? e.message : String(e);
res.status(503).json({ error: 'service_unavailable', detail: msg });
}
});
app.post('/admin/api/agents/:clientId/grant-read', requireAdmin, express.json(), async (req: Request, res: Response) => {
const clientId = String(req.params.clientId ?? '');
const sourceId = String(req.body?.source_id ?? '').trim();
if (!clientId || !sourceId) {
res.status(400).json({ error: 'invalid_request', detail: 'clientId path param + source_id body required' });
return;
}
try {
const { grantReadCore } = await import('./auth.ts');
const outcome = await grantReadCore(sql, clientId, sourceId);
res.json({ outcome });
} catch (e) {
const msg = e instanceof Error ? e.message : String(e);
res.status(400).json({ error: 'mutation_failed', detail: msg });
}
});
app.post('/admin/api/agents/:clientId/revoke-read', requireAdmin, express.json(), async (req: Request, res: Response) => {
const clientId = String(req.params.clientId ?? '');
const sourceId = String(req.body?.source_id ?? '').trim();
if (!clientId || !sourceId) {
res.status(400).json({ error: 'invalid_request', detail: 'clientId path param + source_id body required' });
return;
}
try {
const { revokeReadCore } = await import('./auth.ts');
const outcome = await revokeReadCore(sql, clientId, sourceId);
res.json({ outcome });
} catch (e) {
const msg = e instanceof Error ? e.message : String(e);
res.status(400).json({ error: 'mutation_failed', detail: msg });
}
});
app.post('/admin/api/agents/:clientId/set-federated-read', requireAdmin, express.json(), async (req: Request, res: Response) => {
const clientId = String(req.params.clientId ?? '');
const rawIds = req.body?.source_ids;
if (!clientId || !Array.isArray(rawIds)) {
res.status(400).json({ error: 'invalid_request', detail: 'clientId path param + source_ids[] body required' });
return;
}
// Encode the array as CSV so the same setFederatedReadCore signature
// (string CSV input) the CLI uses applies here. Empty array → empty
// string → clears the list.
const csv = rawIds.map((s) => String(s).trim()).filter(Boolean).join(',');
try {
const { setFederatedReadCore } = await import('./auth.ts');
const outcome = await setFederatedReadCore(sql, clientId, csv);
res.json({ outcome });
} catch (e) {
const msg = e instanceof Error ? e.message : String(e);
res.status(400).json({ error: 'mutation_failed', detail: msg });
}
});
// ---------------------------------------------------------------------------
// SSE live activity feed
// ---------------------------------------------------------------------------
+101 -20
View File
@@ -428,8 +428,13 @@ export async function runPhaseSynthesize(
const queue = new MinionQueue(engine);
const childIds: number[] = [];
/** Map child job_id → chunk metadata for D6 orchestrator-side slug rewrite. */
const chunkInfo = new Map<number, { idx: number; hash6: string }>();
/**
* Map child job_id transcript metadata. Drives D6 orchestrator-side
* slug rewrite for chunked transcripts AND the deterministic frontmatter
* stampDreamProvenance merges into each written page. Populated for
* every child (single-chunk children carry chunkTotal=1).
*/
const childMeta = new Map<number, ChildMeta>();
/** Skip reasons for the cycle report (D5 cap hits, D8 legacy-key skips). */
const skipReports: Array<{ filePath: string; reason: string }> = [];
@@ -513,9 +518,14 @@ export async function runPhaseSynthesize(
{ allowProtectedSubmit: true },
);
childIds.push(child.id);
if (isChunked) {
chunkInfo.set(child.id, { idx: i, hash6 });
}
childMeta.set(child.id, {
idx: i,
hash6,
chunkTotal: chunks.length,
transcriptSource: t.transcriptSource,
transcriptId: stripContentVersionSuffix(t.basename),
inferredDate: t.inferredDate,
});
}
}
@@ -544,14 +554,14 @@ export async function runPhaseSynthesize(
// Collect slugs from put_page tool executions across the children
// (codex finding #2: deterministic provenance, NOT pages.updated_at).
// D6 orchestrator slug rewrite: chunkInfo drives post-hoc rewrite of
// D6 orchestrator slug rewrite: childMeta drives post-hoc rewrite of
// bare-hash slugs to `<hash6>-c<idx>` so chunked siblings can't collide
// even if Sonnet drops the chunk suffix.
// v0.32.8: refs carry source_id so reverseWriteRefs picks the correct
// (source, slug) row. #1586: refs are stamped with the cycle's resolved
// source (children write there via SubagentHandlerData.source_id).
const cycleSourceId = opts.sourceId ?? 'default';
const writtenRefs = await collectChildPutPageSlugs(engine, childIds, chunkInfo, cycleSourceId);
const writtenRefs = await collectChildPutPageSlugs(engine, childIds, childMeta, cycleSourceId);
const summaryDate = opts.date ?? today();
@@ -559,7 +569,12 @@ export async function runPhaseSynthesize(
// of every child-written page BEFORE reverse-rendering, so generated pages
// are queryable (`frontmatter->>'dream_generated'`) and a later put_page
// write-through (which re-renders from the DB row) can't erase the stamp.
await stampDreamProvenance(engine, writtenRefs, summaryDate);
// #2285: the stamp also carries the orchestrator-owned deterministic
// frontmatter (transcript_id, transcript_source, transcript_hash, date,
// chunk) derived from childMeta — subagent drift on those fields can't
// leak, and reverseWriteRefs below re-reads the row so the same fields
// land in the on-disk markdown.
await stampDreamProvenance(engine, writtenRefs, summaryDate, childMeta);
// Dual-write: reverse-render each DB row → markdown file.
const reverseWriteCount = await reverseWriteRefs(engine, opts.brainDir, writtenRefs, cycleSourceId);
@@ -1095,15 +1110,17 @@ function sanitizeForSlug(s: string): string {
* fake"): we no longer need detection because the rewrite enforces
* uniqueness at slug-write time.
*
* `chunkInfo` maps child job_id { chunk_index, hash6 }. Single-chunk
* children are absent from the map and pass through unchanged.
* `childMeta` maps child job_id per-child transcript metadata. Chunked
* children (chunkTotal > 1) get the slug rewrite; single-chunk children
* pass through unchanged. Each returned ref carries the job_id that wrote
* it so stampDreamProvenance can pair the slug back to its childMeta entry.
*/
async function collectChildPutPageSlugs(
engine: BrainEngine,
childIds: number[],
chunkInfo: Map<number, { idx: number; hash6: string }>,
childMeta: Map<number, ChildMeta>,
sourceId = 'default',
): Promise<Array<{ slug: string; source_id: string }>> {
): Promise<Array<{ slug: string; source_id: string; jobId: number }>> {
if (childIds.length === 0) return [];
// Raw fetch — NO SELECT DISTINCT. Preserves per-child slug duplicates so
// the orchestrator sees what each child wrote. COALESCE handles both
@@ -1122,16 +1139,73 @@ async function collectChildPutPageSlugs(
FROM subagent_tool_executions
WHERE job_id = ANY($1::int[])
AND tool_name = 'brain_put_page'
AND status = 'complete'`,
AND status = 'complete'
ORDER BY id`,
[childIds],
);
const rewritten = new Set<string>();
const rewritten = new Map<string, number>();
for (const r of rows) {
if (typeof r.slug !== 'string' || r.slug.length === 0) continue;
const ci = chunkInfo.get(r.job_id);
rewritten.add(ci ? rewriteChunkedSlug(r.slug, ci.hash6, ci.idx) : r.slug);
const meta = childMeta.get(r.job_id);
const finalSlug = meta && meta.chunkTotal > 1
? rewriteChunkedSlug(r.slug, meta.hash6, meta.idx)
: r.slug;
// Last writer wins, in execution-row order (ORDER BY id): if two children
// collide on a final slug, the pages row holds the LAST put_page write, so
// the stamp must attribute that child's transcript — not an arbitrary one.
rewritten.set(finalSlug, r.job_id);
}
return Array.from(rewritten).sort().map(slug => ({ slug, source_id: sourceId }));
return [...rewritten.entries()]
.sort(([a], [b]) => a.localeCompare(b))
.map(([slug, jobId]) => ({ slug, source_id: sourceId, jobId }));
}
/**
* Per-child orchestrator state. Drives D6 chunked-slug rewrite (idx + hash6)
* AND the deterministic frontmatter stampDreamProvenance merges into each
* written page. Populated for every child, not just chunked ones.
*/
interface ChildMeta {
idx: number;
hash6: string;
chunkTotal: number;
transcriptSource: string | null;
transcriptId: string;
inferredDate: string | null;
}
/**
* Strip the content-version suffix that claude-code-archive appends when a
* conversation is edited (`<uuid>--<contentHash>.md`). The session UUID is
* the stable transcript identifier; the suffix changes with content. Used to
* populate `transcript_id` so edits of the same session collapse to one id.
*/
function stripContentVersionSuffix(basename: string): string {
return basename.replace(/--[a-f0-9]+$/i, '');
}
/**
* Deterministic frontmatter for one synthesized page (#2285). Every field
* here is owned by the orchestrator the subagent's value for any of these
* is overwritten. The subagent retains authority over type / title / tags /
* body. `date` feeds the effective-date precedence chain
* (src/core/effective-date.ts) so re-imports keep the conversation date even
* when sync tools re-stamp file mtimes.
*/
function buildDeterministicFrontmatter(
meta: ChildMeta,
cycleDate: string,
): Record<string, unknown> {
const overrides: Record<string, unknown> = {
dream_generated: true,
dream_cycle_date: cycleDate,
transcript_id: meta.transcriptId,
transcript_hash: meta.hash6,
};
if (meta.transcriptSource) overrides.transcript_source = meta.transcriptSource;
if (meta.chunkTotal > 1) overrides.chunk = `${meta.idx + 1}/${meta.chunkTotal}`;
if (meta.inferredDate) overrides.date = meta.inferredDate;
return overrides;
}
/**
@@ -1177,12 +1251,19 @@ async function hasLegacySingleChunkCompletion(
*/
async function stampDreamProvenance(
engine: BrainEngine,
refs: Array<{ slug: string; source_id: string }>,
refs: Array<{ slug: string; source_id: string; jobId?: number }>,
cycleDate: string,
childMeta?: Map<number, ChildMeta>,
): Promise<void> {
if (refs.length === 0) return;
const { executeRawJsonb } = await import('../sql-query.ts');
for (const { slug, source_id } of refs) {
for (const { slug, source_id, jobId } of refs) {
// #2285: when the ref pairs back to a child, the stamp also carries the
// orchestrator-owned deterministic frontmatter for that transcript.
const meta = jobId !== undefined ? childMeta?.get(jobId) : undefined;
const stamp = meta
? buildDeterministicFrontmatter(meta, cycleDate)
: { dream_generated: true, dream_cycle_date: cycleDate };
try {
await executeRawJsonb(
engine,
@@ -1190,7 +1271,7 @@ async function stampDreamProvenance(
SET frontmatter = COALESCE(frontmatter, '{}'::jsonb) || $3::jsonb
WHERE slug = $1 AND source_id = $2`,
[slug, source_id],
[{ dream_generated: true, dream_cycle_date: cycleDate }],
[stamp],
);
} catch (e) {
const msg = e instanceof Error ? e.message : String(e);
+58 -5
View File
@@ -10,7 +10,7 @@
*/
import { readFileSync, readdirSync, statSync } from 'node:fs';
import { join, basename } from 'node:path';
import { join, basename, dirname } from 'node:path';
import { createHash } from 'node:crypto';
import { pruneDir } from '../sync.ts';
@@ -23,8 +23,22 @@ export interface DiscoveredTranscript {
content: string;
/** Filename basename without extension; used as a topic-slug seed. */
basename: string;
/** Inferred date if the basename matches `YYYY-MM-DD...` (or null). */
/**
* Inferred conversation date (YYYY-MM-DD) or null. Precedence: the
* `| First message | <ISO> |` row in the transcript's `## Metadata`
* table (stable across mtime-restamping re-syncs) wins; a leading
* `YYYY-MM-DD` in the basename is the fallback.
*/
inferredDate: string | null;
/**
* Transcript source archive name, derived from the path's grandparent
* directory (the immediate parent of the date directory). For the
* canonical layout `<corpus>/<source>/<date>/<id>.md` this yields the
* source-name segment e.g. `claude-code` for the claude-code-archive
* output, `meetings` for meeting recordings. Null when the file does
* not live under a `<source>/<date>/` pair (ad-hoc inputs).
*/
transcriptSource: string | null;
}
export interface DiscoverOpts {
@@ -161,6 +175,36 @@ function matchesAnyExclude(text: string, patterns: RegExp[]): boolean {
return false;
}
/**
* Content-based conversation date: the `| First message | <ISO timestamp> |`
* row claude-code-archive writes into the transcript's `## Metadata` table.
* Stable across rsync/Dropbox/Syncthing/B2 re-syncs that re-stamp mtime,
* unlike anything derived from file metadata. Returns YYYY-MM-DD or null.
*/
const FIRST_MESSAGE_RE = /^\|\s*First message\s*\|\s*(\d{4}-\d{2}-\d{2})/im;
export function inferContentDate(content: string): string | null {
const m = FIRST_MESSAGE_RE.exec(content);
return m ? m[1] : null;
}
/**
* Derive the archive source name from a transcript path. Returns the basename
* of the directory two levels above the file when the immediate parent is a
* date directory and the grandparent looks like a source-name slug (lowercase
* alphanumeric segments separated by hyphens); otherwise null. This pins the
* canonical claude-code-archive layout `<corpus>/<source>/<date>/<id>.md`
* without claiming a source for ad-hoc inputs that don't match.
*/
export function deriveTranscriptSource(filePath: string): string | null {
const parentName = basename(dirname(filePath));
if (!/^\d{4}-\d{2}-\d{2}/.test(parentName)) return null;
const grandparentName = basename(dirname(dirname(filePath)));
if (!grandparentName) return null;
if (!/^[a-z0-9]+(-[a-z0-9]+)*$/.test(grandparentName)) return null;
return grandparentName;
}
function listTextFiles(dir: string): string[] {
// Recursive walk with descent-time pruning (closes codex C12/C13 spec gap).
// Accepts BOTH .txt and .md per transcript-discovery's domain rules — does
@@ -225,8 +269,11 @@ export function discoverTranscripts(opts: DiscoverOpts): DiscoveredTranscript[]
const ext = filePath.endsWith('.md') ? '.md' : '.txt';
const baseName = basename(filePath, ext);
const dateMatch = DATE_RE.exec(baseName);
const inferredDate = dateMatch ? dateMatch[1] : null;
if (!isInDateRange(inferredDate, opts)) continue;
const filenameDate = dateMatch ? dateMatch[1] : null;
// Fast path: date-named files outside the window skip before the read.
// ponytail: a date-named file whose content date differs is filtered on
// its filename date — acceptable; archive layouts use UUID basenames.
if (filenameDate && !isInDateRange(filenameDate, opts)) continue;
let content: string;
try {
@@ -241,12 +288,17 @@ export function discoverTranscripts(opts: DiscoverOpts): DiscoveredTranscript[]
}
if (matchesAnyExclude(content, excludeRes)) continue;
// Content-metadata date wins (survives mtime restamps); filename next.
const inferredDate = inferContentDate(content) ?? filenameDate;
if (!isInDateRange(inferredDate, opts)) continue;
results.push({
filePath,
contentHash: hashContent(content),
content,
basename: baseName,
inferredDate,
transcriptSource: deriveTranscriptSource(filePath),
});
}
}
@@ -290,6 +342,7 @@ export function readSingleTranscript(
contentHash: hashContent(content),
content,
basename: baseName,
inferredDate: dateMatch ? dateMatch[1] : null,
inferredDate: inferContentDate(content) ?? (dateMatch ? dateMatch[1] : null),
transcriptSource: deriveTranscriptSource(filePath),
};
}
+1 -1
View File
@@ -55,7 +55,7 @@ export interface AgentClientBindings {
* `redirect_uri` containing `,`) would be parsed by Postgres as MULTIPLE
* array elements, smuggling values past validation. See CSO finding #5.
*/
export function pgArray(arr: string[]): string {
function pgArray(arr: string[]): string {
if (!arr || arr.length === 0) return '{}';
const escaped = arr.map(s => `"${s.replace(/\\/g, '\\\\').replace(/"/g, '\\"')}"`);
return `{${escaped.join(',')}}`;
-82
View File
@@ -1,82 +0,0 @@
import { describe, it, expect, beforeAll, afterAll, beforeEach } from 'bun:test';
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
import { resetPgliteState } from './helpers/reset-pglite.ts';
import { queryAdminSources } from '../src/commands/serve-http.ts';
import { buildSyncStatusReport } from '../src/commands/sync.ts';
/**
* v0.41.29 Sources tab `/admin/api/sources` endpoint SQL.
*
* The endpoint is a thin Express handler over `queryAdminSources` +
* `buildSyncStatusReport`; the source-selection SQL is the load-bearing
* surface (same pattern as test/admin-agents-spend.test.ts).
*
* Pinned behaviors:
* - Excludes archived sources
* - INCLUDES sources with null local_path (push-only brains: filtering
* on local_path emptied the Sources tab + federation source-picker)
* - JSONB config surfaces as an object, defaulting to {}
* - Deterministic ORDER BY id
* - buildSyncStatusReport accepts the rows (no disk I/O on null paths)
*/
let engine: PGLiteEngine;
beforeAll(async () => {
engine = new PGLiteEngine();
await engine.connect({});
await engine.initSchema();
});
afterAll(async () => {
await engine.disconnect();
});
beforeEach(async () => {
await resetPgliteState(engine);
});
describe('queryAdminSources (/admin/api/sources SQL)', () => {
it('includes push-only sources with null local_path', async () => {
await engine.executeRaw(
`INSERT INTO sources (id, name, local_path, config)
VALUES ('push-only', 'push-only', NULL, '{}'::jsonb)`,
);
const sources = await queryAdminSources(engine);
const ids = sources.map((s) => s.id);
expect(ids).toContain('push-only');
expect(sources.find((s) => s.id === 'push-only')!.local_path).toBe(null);
});
it('excludes archived sources', async () => {
await engine.executeRaw(
`INSERT INTO sources (id, name, archived) VALUES ('gone', 'gone', true)`,
);
const sources = await queryAdminSources(engine);
expect(sources.map((s) => s.id)).not.toContain('gone');
});
it('surfaces JSONB config as an object and orders by id', async () => {
await engine.executeRaw(
`INSERT INTO sources (id, name, config)
VALUES ('bbb', 'bbb', '{"syncEnabled": true}'::jsonb),
('aaa', 'aaa', '{}'::jsonb)`,
);
const sources = await queryAdminSources(engine);
const ids = sources.map((s) => s.id);
expect(ids.indexOf('aaa')).toBeLessThan(ids.indexOf('bbb'));
expect(sources.find((s) => s.id === 'bbb')!.config).toEqual({ syncEnabled: true });
expect(sources.find((s) => s.id === 'aaa')!.config).toEqual({});
});
it('buildSyncStatusReport accepts the rows (null local_path does not throw)', async () => {
await engine.executeRaw(
`INSERT INTO sources (id, name, local_path, config)
VALUES ('push-only', 'push-only', NULL, '{}'::jsonb)`,
);
const report = await buildSyncStatusReport(engine, await queryAdminSources(engine));
expect(report.schema_version).toBe(1);
const row = report.sources.find((s) => s.source_id === 'push-only');
expect(row).toBeDefined();
});
});
-568
View File
@@ -1,568 +0,0 @@
/**
* Tests for `gbrain auth grant-read|revoke-read|set-federated-read`.
*
* Pure helper: parseSourceCsv (no DB).
* DB-coupled: resolveClient, assertSourceExists, *Core fns exercised
* against a real PGLite via the canonical block.
*/
import { describe, expect, test, beforeAll, afterAll, beforeEach } from 'bun:test';
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
import { resetPgliteState } from './helpers/reset-pglite.ts';
import { sqlQueryForEngine } from '../src/core/sql-query.ts';
import { pgArray } from '../src/core/oauth-provider.ts';
import {
parseSourceCsv,
resolveClient,
assertSourceExists,
grantReadCore,
revokeReadCore,
setFederatedReadCore,
extractDryRun,
sanitizeForTerminal,
} from '../src/commands/auth.ts';
let engine: PGLiteEngine;
beforeAll(async () => {
engine = new PGLiteEngine();
await engine.connect({});
await engine.initSchema();
});
afterAll(async () => {
await engine.disconnect();
});
beforeEach(async () => {
await resetPgliteState(engine);
});
// ---------------------------------------------------------------------------
// pure helpers
// ---------------------------------------------------------------------------
describe('parseSourceCsv', () => {
test('splits and trims', () => {
expect(parseSourceCsv('a,b,c')).toEqual(['a', 'b', 'c']);
expect(parseSourceCsv(' a , b ')).toEqual(['a', 'b']);
});
test('drops empty segments', () => {
expect(parseSourceCsv('a,,b,')).toEqual(['a', 'b']);
expect(parseSourceCsv(',,')).toEqual([]);
expect(parseSourceCsv('')).toEqual([]);
});
test('dedupes while preserving first-seen order', () => {
expect(parseSourceCsv('a,b,a,c,b')).toEqual(['a', 'b', 'c']);
});
});
describe('extractDryRun', () => {
test('absent flag → false', () => {
expect(extractDryRun(['alice', 'proj-x'])).toEqual({
dryRun: false,
rest: ['alice', 'proj-x'],
});
});
test('flag at end', () => {
expect(extractDryRun(['alice', 'proj-x', '--dry-run'])).toEqual({
dryRun: true,
rest: ['alice', 'proj-x'],
});
});
test('flag at start', () => {
expect(extractDryRun(['--dry-run', 'alice', 'proj-x'])).toEqual({
dryRun: true,
rest: ['alice', 'proj-x'],
});
});
test('flag in middle', () => {
expect(extractDryRun(['alice', '--dry-run', 'proj-x'])).toEqual({
dryRun: true,
rest: ['alice', 'proj-x'],
});
});
test('no args', () => {
expect(extractDryRun([])).toEqual({ dryRun: false, rest: [] });
});
});
// ---------------------------------------------------------------------------
// DB-coupled
// ---------------------------------------------------------------------------
async function seedSource(id: string): Promise<void> {
const sql = sqlQueryForEngine(engine);
await sql`INSERT INTO sources (id, name) VALUES (${id}, ${id}) ON CONFLICT (id) DO NOTHING`;
}
async function seedClient(name: string, federated: string[] = []): Promise<string> {
// Ensure write source FK is satisfied — every seeded client points at 'default'.
await seedSource('default');
const sql = sqlQueryForEngine(engine);
const clientId = `gbrain_cl_test_${name}_${Date.now()}_${Math.random().toString(16).slice(2, 8)}`;
const fedLit = pgArray(federated);
await sql`
INSERT INTO oauth_clients (client_id, client_name, client_secret_hash,
redirect_uris, grant_types, scope,
client_id_issued_at, source_id, federated_read)
VALUES (${clientId}, ${name}, ${'dummy-hash'},
${pgArray([])}, ${pgArray(['client_credentials'])}, ${'read'},
${Date.now()}, ${'default'}, ${fedLit})
`;
return clientId;
}
async function readFederated(clientId: string): Promise<string[]> {
const sql = sqlQueryForEngine(engine);
const rows = await sql`SELECT federated_read FROM oauth_clients WHERE client_id = ${clientId}`;
const fed = rows[0]?.federated_read;
return Array.isArray(fed) ? (fed as string[]).map(String) : [];
}
describe('resolveClient', () => {
test('matches by client_id', async () => {
await seedSource('default');
const id = await seedClient('alice', ['default']);
const sql = sqlQueryForEngine(engine);
const c = await resolveClient(sql, id);
expect(c.client_name).toBe('alice');
expect(c.federated_read).toEqual(['default']);
});
test('matches by client_name', async () => {
await seedSource('default');
await seedClient('alice', ['default']);
const sql = sqlQueryForEngine(engine);
const c = await resolveClient(sql, 'alice');
expect(c.client_name).toBe('alice');
});
test('errors loudly on no-match', async () => {
const sql = sqlQueryForEngine(engine);
await expect(resolveClient(sql, 'nobody')).rejects.toThrow(/No active OAuth client found/);
});
test('errors loudly on ambiguous client_name', async () => {
await seedSource('default');
await seedClient('bob', ['default']);
await seedClient('bob', ['default']);
const sql = sqlQueryForEngine(engine);
await expect(resolveClient(sql, 'bob')).rejects.toThrow(/Multiple active OAuth clients named/);
});
test('null source_id is preserved as null (legacy row tolerance)', async () => {
const sql = sqlQueryForEngine(engine);
const clientId = `gbrain_cl_test_null_${Date.now()}`;
await sql`
INSERT INTO oauth_clients (client_id, client_name, client_secret_hash,
redirect_uris, grant_types, scope,
client_id_issued_at, source_id, federated_read)
VALUES (${clientId}, ${'legacy'}, ${'dummy'},
${pgArray([])}, ${pgArray(['client_credentials'])}, ${'read'},
${Date.now()}, ${null}, ${pgArray([])})
`;
const c = await resolveClient(sql, clientId);
expect(c.source_id).toBeNull();
expect(c.federated_read).toEqual([]);
});
});
describe('assertSourceExists', () => {
test('passes when present', async () => {
await seedSource('proj-x');
const sql = sqlQueryForEngine(engine);
await expect(assertSourceExists(sql, 'proj-x')).resolves.toBeUndefined();
});
test('throws with paste-ready hint when missing', async () => {
const sql = sqlQueryForEngine(engine);
await expect(assertSourceExists(sql, 'ghost')).rejects.toThrow(
/Source "ghost" does not exist.*gbrain sources add ghost/s,
);
});
});
describe('grantReadCore', () => {
test('appends when not present and persists', async () => {
await seedSource('default');
await seedSource('proj-x');
const id = await seedClient('alice', ['default']);
const sql = sqlQueryForEngine(engine);
const outcome = await grantReadCore(sql, 'alice', 'proj-x');
expect(outcome.kind).toBe('updated');
if (outcome.kind === 'updated') {
expect(outcome.before).toEqual(['default']);
expect(outcome.after).toEqual(['default', 'proj-x']);
}
expect(await readFederated(id)).toEqual(['default', 'proj-x']);
});
test('is idempotent — second call is a noop, list unchanged', async () => {
await seedSource('default');
await seedSource('proj-x');
const id = await seedClient('alice', ['default']);
const sql = sqlQueryForEngine(engine);
await grantReadCore(sql, 'alice', 'proj-x');
const outcome = await grantReadCore(sql, 'alice', 'proj-x');
expect(outcome.kind).toBe('noop');
if (outcome.kind === 'noop') {
expect(outcome.reason).toBe('already-granted');
}
expect(await readFederated(id)).toEqual(['default', 'proj-x']);
});
test('refuses unknown source (fails BEFORE mutating)', async () => {
await seedSource('default');
const id = await seedClient('alice', ['default']);
const sql = sqlQueryForEngine(engine);
await expect(grantReadCore(sql, 'alice', 'ghost')).rejects.toThrow(/does not exist/);
expect(await readFederated(id)).toEqual(['default']);
});
test('refuses unknown client', async () => {
const sql = sqlQueryForEngine(engine);
await expect(grantReadCore(sql, 'nobody', 'whatever')).rejects.toThrow(/No active OAuth client found/);
});
test('accepts client_id resolution too', async () => {
await seedSource('default');
await seedSource('proj-x');
const id = await seedClient('alice', ['default']);
const sql = sqlQueryForEngine(engine);
await grantReadCore(sql, id, 'proj-x');
expect(await readFederated(id)).toEqual(['default', 'proj-x']);
});
test('rejects malformed source_id BEFORE existence check (Codex finding #3)', async () => {
await seedSource('default');
const id = await seedClient('alice', ['default']);
const sql = sqlQueryForEngine(engine);
// Even with a row in `sources` having a weird id, the validator at the
// boundary refuses. Closes the "manual SQL plants a row, CLI lets it
// become unmanageable in federated_read" vector.
await sql`INSERT INTO sources (id, name) VALUES (${'has,"weird"-bits'}, ${'weird'})`;
await expect(grantReadCore(sql, 'alice', 'has,"weird"-bits')).rejects.toThrow(/Invalid source_id/);
// DB unchanged.
expect(await readFederated(id)).toEqual(['default']);
});
});
describe('revokeReadCore', () => {
test('removes when present', async () => {
await seedSource('default');
await seedSource('proj-x');
const id = await seedClient('alice', ['default', 'proj-x']);
const sql = sqlQueryForEngine(engine);
const outcome = await revokeReadCore(sql, 'alice', 'proj-x');
expect(outcome.kind).toBe('updated');
expect(await readFederated(id)).toEqual(['default']);
});
test('is idempotent — second call is a noop, list unchanged', async () => {
await seedSource('default');
const id = await seedClient('alice', ['default']);
const sql = sqlQueryForEngine(engine);
const outcome = await revokeReadCore(sql, 'alice', 'ghost-source');
expect(outcome.kind).toBe('noop');
if (outcome.kind === 'noop') {
expect(outcome.reason).toBe('not-present');
}
expect(await readFederated(id)).toEqual(['default']);
});
test('allows clearing the list down to empty (no implicit guard)', async () => {
await seedSource('default');
const id = await seedClient('alice', ['default']);
const sql = sqlQueryForEngine(engine);
await revokeReadCore(sql, 'alice', 'default');
expect(await readFederated(id)).toEqual([]);
});
test('does NOT validate the source exists — operator may revoke stale references', async () => {
await seedSource('default');
// federated_read carries 'proj-x' but the source row was deleted.
const id = await seedClient('alice', ['default', 'proj-x']);
const sql = sqlQueryForEngine(engine);
const outcome = await revokeReadCore(sql, 'alice', 'proj-x');
expect(outcome.kind).toBe('updated');
expect(await readFederated(id)).toEqual(['default']);
});
});
describe('setFederatedReadCore', () => {
test('replaces list wholesale', async () => {
await seedSource('a');
await seedSource('b');
await seedSource('c');
const id = await seedClient('alice', ['a']);
const sql = sqlQueryForEngine(engine);
const outcome = await setFederatedReadCore(sql, 'alice', 'b,c');
expect(outcome.kind).toBe('updated');
expect(await readFederated(id)).toEqual(['b', 'c']);
});
test('dedupes CSV input', async () => {
await seedSource('a');
await seedSource('b');
const id = await seedClient('alice', []);
const sql = sqlQueryForEngine(engine);
await setFederatedReadCore(sql, 'alice', 'a,b,a,b,a');
expect(await readFederated(id)).toEqual(['a', 'b']);
});
test('empty string clears the list', async () => {
await seedSource('a');
const id = await seedClient('alice', ['a']);
const sql = sqlQueryForEngine(engine);
await setFederatedReadCore(sql, 'alice', '');
expect(await readFederated(id)).toEqual([]);
});
test('noop when result equals current list', async () => {
await seedSource('a');
await seedSource('b');
const id = await seedClient('alice', ['a', 'b']);
const sql = sqlQueryForEngine(engine);
const outcome = await setFederatedReadCore(sql, 'alice', 'a,b');
expect(outcome.kind).toBe('noop');
if (outcome.kind === 'noop') {
expect(outcome.reason).toBe('same-list');
}
expect(await readFederated(id)).toEqual(['a', 'b']);
});
test('refuses unknown source (fails BEFORE mutating)', async () => {
await seedSource('a');
const id = await seedClient('alice', ['a']);
const sql = sqlQueryForEngine(engine);
await expect(setFederatedReadCore(sql, 'alice', 'a,ghost')).rejects.toThrow(/does not exist/);
// Original list preserved.
expect(await readFederated(id)).toEqual(['a']);
});
test('order in CSV is the order persisted', async () => {
await seedSource('a');
await seedSource('b');
await seedSource('c');
const id = await seedClient('alice', ['a']);
const sql = sqlQueryForEngine(engine);
await setFederatedReadCore(sql, 'alice', 'c,a,b');
expect(await readFederated(id)).toEqual(['c', 'a', 'b']);
});
});
// ---------------------------------------------------------------------------
// --dry-run semantics
// ---------------------------------------------------------------------------
// ---------------------------------------------------------------------------
// Codex fixes: soft-delete filter, atomic-SQL race-safety, sanitizer
// ---------------------------------------------------------------------------
describe('sanitizeForTerminal', () => {
test('preserves printable ASCII unchanged', () => {
expect(sanitizeForTerminal('alice')).toBe('alice');
expect(sanitizeForTerminal('a b-c_d.e/f@g')).toBe('a b-c_d.e/f@g');
});
test('escapes ANSI escape sequences', () => {
expect(sanitizeForTerminal('\x1b[2J')).toBe('\\x1b[2J');
expect(sanitizeForTerminal('\x1b]0;TITLE\x07')).toBe('\\x1b]0;TITLE\\x07');
});
test('escapes ALL C0 controls including tab and newline', () => {
// Codex re-review: preserving \n lets a DCR-registered name spoof
// additional rows in list-clients output. Tab spoofs field separators.
// Both are now escaped.
expect(sanitizeForTerminal('\x00\x07\x08')).toBe('\\x00\\x07\\x08');
expect(sanitizeForTerminal('line1\nline2')).toBe('line1\\x0aline2');
expect(sanitizeForTerminal('col1\tcol2')).toBe('col1\\x09col2');
});
test('escapes DEL and C1 controls', () => {
expect(sanitizeForTerminal('\x7f')).toBe('\\x7f');
expect(sanitizeForTerminal('\x9b[31m')).toBe('\\x9b[31m');
});
test('passes through unicode', () => {
expect(sanitizeForTerminal('café')).toBe('café');
expect(sanitizeForTerminal('日本語')).toBe('日本語');
});
});
describe('soft-delete filter (Codex finding #2)', () => {
async function softDeleteClient(clientId: string): Promise<void> {
const sql = sqlQueryForEngine(engine);
await sql`UPDATE oauth_clients SET deleted_at = now() WHERE client_id = ${clientId}`;
}
test('resolveClient hides soft-deleted clients by default', async () => {
await seedSource('default');
const id = await seedClient('alice', ['default']);
await softDeleteClient(id);
const sql = sqlQueryForEngine(engine);
await expect(resolveClient(sql, 'alice')).rejects.toThrow(/No active OAuth client found/);
await expect(resolveClient(sql, id)).rejects.toThrow(/No active OAuth client found/);
});
test('resolveClient with includeDeleted finds soft-deleted clients', async () => {
await seedSource('default');
const id = await seedClient('alice', ['default']);
await softDeleteClient(id);
const sql = sqlQueryForEngine(engine);
const c = await resolveClient(sql, id, { includeDeleted: true });
expect(c.client_name).toBe('alice');
expect(c.deleted_at).not.toBeNull();
});
test('grantReadCore refuses to mutate soft-deleted clients', async () => {
await seedSource('default');
await seedSource('proj-x');
const id = await seedClient('alice', ['default']);
await softDeleteClient(id);
const sql = sqlQueryForEngine(engine);
await expect(grantReadCore(sql, 'alice', 'proj-x')).rejects.toThrow(/No active OAuth client found/);
expect(await readFederated(id)).toEqual(['default']);
});
test('revokeReadCore refuses to mutate soft-deleted clients', async () => {
await seedSource('default');
const id = await seedClient('alice', ['default']);
await softDeleteClient(id);
const sql = sqlQueryForEngine(engine);
await expect(revokeReadCore(sql, 'alice', 'default')).rejects.toThrow(/No active OAuth client found/);
expect(await readFederated(id)).toEqual(['default']);
});
test('two clients with same name but only one active resolves to the active one', async () => {
await seedSource('default');
// Seed two clients with the same name; soft-delete the older one.
const sql = sqlQueryForEngine(engine);
const oldId = await seedClient('alice', ['default']);
await softDeleteClient(oldId);
const newId = await seedClient('alice', ['default']); // same name, new row
const c = await resolveClient(sql, 'alice');
expect(c.client_id).toBe(newId); // active row wins; ambiguity error suppressed
});
});
describe('atomic SQL race-safety (Codex finding #1, HIGH)', () => {
test('grant+revoke serialize at row-lock — sensitive stays revoked', async () => {
await seedSource('default');
await seedSource('sensitive');
await seedSource('harmless');
const id = await seedClient('alice', ['default', 'sensitive']);
const sql = sqlQueryForEngine(engine);
// Simulate concurrent revoke(sensitive) + grant(harmless). Real concurrency
// would race at the JS event loop boundary; here we await sequentially but
// each call goes through the ATOMIC SQL path. The contract: regardless of
// ordering, the final state has sensitive REMOVED and harmless ADDED.
await revokeReadCore(sql, 'alice', 'sensitive');
await grantReadCore(sql, 'alice', 'harmless');
const final1 = await readFederated(id);
expect(final1.sort()).toEqual(['default', 'harmless']);
// Reverse order, same final state. The pre-fix read-modify-write shape
// would have produced ['default', 'sensitive', 'harmless'] here (the
// resurrection bug Codex caught).
const id2 = await seedClient('bob', ['default', 'sensitive']);
await grantReadCore(sql, 'bob', 'harmless');
await revokeReadCore(sql, 'bob', 'sensitive');
const final2 = await readFederated(id2);
expect(final2.sort()).toEqual(['default', 'harmless']);
});
test('grant uses RETURNING to surface the post-write state', async () => {
await seedSource('default');
await seedSource('proj-x');
await seedClient('alice', ['default']);
const sql = sqlQueryForEngine(engine);
const outcome = await grantReadCore(sql, 'alice', 'proj-x');
expect(outcome.kind).toBe('updated');
if (outcome.kind === 'updated') {
// The `after` came from RETURNING, not from computing prev+sourceId
// in JS — proves the atomic path returned authoritative state.
expect(outcome.after).toEqual(['default', 'proj-x']);
}
});
test('grant noop path still survives without writing', async () => {
await seedSource('default');
const id = await seedClient('alice', ['default']);
const sql = sqlQueryForEngine(engine);
const outcome = await grantReadCore(sql, 'alice', 'default');
expect(outcome.kind).toBe('noop');
if (outcome.kind === 'noop') expect(outcome.reason).toBe('already-granted');
expect(await readFederated(id)).toEqual(['default']);
});
});
describe('dryRun mode', () => {
test('grantReadCore returns "updated" outcome but skips the write', async () => {
await seedSource('default');
await seedSource('proj-x');
const id = await seedClient('alice', ['default']);
const sql = sqlQueryForEngine(engine);
const outcome = await grantReadCore(sql, 'alice', 'proj-x', { dryRun: true });
expect(outcome.kind).toBe('updated');
if (outcome.kind === 'updated') {
expect(outcome.before).toEqual(['default']);
expect(outcome.after).toEqual(['default', 'proj-x']);
}
// Crucially: the DB row is UNCHANGED.
expect(await readFederated(id)).toEqual(['default']);
});
test('revokeReadCore returns "updated" outcome but skips the write', async () => {
await seedSource('default');
await seedSource('proj-x');
const id = await seedClient('alice', ['default', 'proj-x']);
const sql = sqlQueryForEngine(engine);
const outcome = await revokeReadCore(sql, 'alice', 'proj-x', { dryRun: true });
expect(outcome.kind).toBe('updated');
expect(await readFederated(id)).toEqual(['default', 'proj-x']);
});
test('setFederatedReadCore returns "updated" outcome but skips the write', async () => {
await seedSource('a');
await seedSource('b');
await seedSource('c');
const id = await seedClient('alice', ['a']);
const sql = sqlQueryForEngine(engine);
const outcome = await setFederatedReadCore(sql, 'alice', 'b,c', { dryRun: true });
expect(outcome.kind).toBe('updated');
expect(await readFederated(id)).toEqual(['a']);
});
test('noop outcomes are surfaced identically with or without dryRun', async () => {
await seedSource('default');
await seedSource('proj-x');
await seedClient('alice', ['default', 'proj-x']);
const sql = sqlQueryForEngine(engine);
const live = await grantReadCore(sql, 'alice', 'proj-x', { dryRun: false });
const dry = await grantReadCore(sql, 'alice', 'proj-x', { dryRun: true });
expect(live.kind).toBe('noop');
expect(dry.kind).toBe('noop');
});
test('errors still fire in dryRun (operator sees the problem before commit)', async () => {
await seedSource('default');
const id = await seedClient('alice', ['default']);
const sql = sqlQueryForEngine(engine);
await expect(
grantReadCore(sql, 'alice', 'ghost', { dryRun: true }),
).rejects.toThrow(/does not exist/);
await expect(
grantReadCore(sql, 'nobody', 'default', { dryRun: true }),
).rejects.toThrow(/No active OAuth client found/);
// DB unchanged.
expect(await readFederated(id)).toEqual(['default']);
});
});
-23
View File
@@ -174,29 +174,6 @@ describe('parseRegisterClientArgs', () => {
});
describe('error cases', () => {
test('--source with malformed id throws (validates source_id shape — codex re-review)', () => {
// Defense for the "register-client seeds an unmanageable
// federated_read entry" vector. assertValidSourceId fires before the
// function returns so DB never sees a row with bad source scope.
expect(() => parseRegisterClientArgs(['--source', 'has,weird,bits'])).toThrow(/Invalid source_id/);
expect(() => parseRegisterClientArgs(['--source', 'UPPER'])).toThrow(/Invalid source_id/);
expect(() => parseRegisterClientArgs(['--source', ''])).toThrow(/Invalid source_id|requires a value/);
});
test('--federated-read with any malformed id throws', () => {
// Single-item bad.
expect(() => parseRegisterClientArgs(['--federated-read', 'bad,source!'])).toThrow(/Invalid source_id/);
// Mixed valid + invalid — fails on the first bad one.
expect(() => parseRegisterClientArgs(['--federated-read', 'good,bad source'])).toThrow(/Invalid source_id/);
});
test('--source default + --federated-read default,team passes (regression — common case)', () => {
// Sanity: the canonical real-world invocation still parses cleanly.
const out = parseRegisterClientArgs(['--source', 'default', '--federated-read', 'default,team']);
expect(out.sourceId).toBe('default');
expect(out.federatedRead).toEqual(['default', 'team']);
});
test('--redirect-uri without value → throws', () => {
expect(() => parseRegisterClientArgs(['--redirect-uri'])).toThrow(/requires a value/);
});
+1
View File
@@ -26,6 +26,7 @@ const transcript: DiscoveredTranscript = {
content: 'User: hello world',
contentHash: 'abcdef0123456789',
inferredDate: '2026-07-17',
transcriptSource: null,
} as DiscoveredTranscript;
describe('#2415: buildSynthesisPrompt output root', () => {
@@ -152,3 +152,94 @@ describe('#2569: stampDreamProvenance persists the marker into DB frontmatter',
await stampDreamProvenance(engine as any, refs, '2026-07-17'); // idempotent
});
});
describe('#2285: orchestrator-owned deterministic transcript frontmatter', () => {
const meta = {
idx: 1,
hash6: 'abc123',
chunkTotal: 3,
transcriptSource: 'claude-code',
transcriptId: 'session-uuid',
inferredDate: '2026-05-15',
};
test('collectChildPutPageSlugs pairs each ref back to the writing job', async () => {
const refs = await collectChildPutPageSlugs(
engine as any, [1001], new Map([[1001, { ...meta, chunkTotal: 1 }]]), 'mybrain',
);
expect(refs.length).toBeGreaterThan(0);
for (const r of refs) {
expect(r.jobId).toBe(1001);
expect(r.source_id).toBe('mybrain'); // #1586: cycle source, never hardcoded 'default'
}
});
test('slug collision across children attributes the LAST writer (matches surviving putPage)', async () => {
const db = (engine as any).db;
// Jobs 1001 then 1002 write the same slug; the pages row would hold
// 1002's content (last put_page wins), so the ref must carry jobId 1002.
await db.query(
`INSERT INTO subagent_tool_executions (job_id, message_idx, tool_use_id, tool_name, status, input)
VALUES (1001, 9, 'tool_dup_a', 'brain_put_page', 'complete', $1::jsonb)`,
[JSON.stringify({ slug: 'wiki/agents/test/collision', body: 'first' })],
);
await db.query(
`INSERT INTO subagent_tool_executions (job_id, message_idx, tool_use_id, tool_name, status, input)
VALUES (1002, 9, 'tool_dup_b', 'brain_put_page', 'complete', $1::jsonb)`,
[JSON.stringify({ slug: 'wiki/agents/test/collision', body: 'second' })],
);
const refs = await collectChildPutPageSlugs(engine as any, [1001, 1002], new Map());
const hit = refs.find((r: { slug: string }) => r.slug === 'wiki/agents/test/collision');
expect(hit?.jobId).toBe(1002);
});
test('stampDreamProvenance merges the transcript metadata into DB frontmatter', async () => {
const slug = 'wiki/originals/ideas/2026-07-17-transcript-meta-abc123';
await engine.putPage(slug, {
type: 'note',
title: 'Meta stamp',
compiled_truth: 'body',
timeline: '',
frontmatter: { keep_me: 'yes', transcript_id: 'subagent-drift' },
});
await stampDreamProvenance(
engine as any,
[{ slug, source_id: 'default', jobId: 42 }],
'2026-07-17',
new Map([[42, meta]]),
);
const rows = await engine.executeRaw<{ fm: Record<string, unknown> }>(
`SELECT frontmatter AS fm FROM pages WHERE slug = $1`, [slug],
);
const fm = rows[0].fm as Record<string, unknown>;
expect(fm.dream_generated).toBe(true);
expect(fm.dream_cycle_date).toBe('2026-07-17');
expect(fm.transcript_id).toBe('session-uuid'); // orchestrator wins over subagent drift
expect(fm.transcript_hash).toBe('abc123');
expect(fm.transcript_source).toBe('claude-code');
expect(fm.chunk).toBe('2/3');
expect(fm.date).toBe('2026-05-15');
expect(fm.keep_me).toBe('yes'); // subagent-owned keys survive
});
test('single-chunk children with no inferredDate stamp only the applicable fields', async () => {
const slug = 'wiki/originals/ideas/2026-07-17-minimal-meta-abc123';
await engine.putPage(slug, {
type: 'note', title: 'Minimal', compiled_truth: 'b', timeline: '', frontmatter: {},
});
await stampDreamProvenance(
engine as any,
[{ slug, source_id: 'default', jobId: 43 }],
'2026-07-17',
new Map([[43, { ...meta, chunkTotal: 1, transcriptSource: null, inferredDate: null }]]),
);
const rows = await engine.executeRaw<{ fm: Record<string, unknown> }>(
`SELECT frontmatter AS fm FROM pages WHERE slug = $1`, [slug],
);
const fm = rows[0].fm as Record<string, unknown>;
expect(fm.transcript_id).toBe('session-uuid');
expect(fm.chunk).toBeUndefined();
expect(fm.transcript_source).toBeUndefined();
expect(fm.date).toBeUndefined();
});
});
+2
View File
@@ -302,6 +302,7 @@ describe('judgeSignificance', () => {
content: 'A short conversation about something interesting.',
basename: 'x',
inferredDate: null,
transcriptSource: null,
};
}
@@ -415,6 +416,7 @@ describe('judgeSignificance — UTF-16 safety (v0.41.13)', () => {
content,
basename: 'long',
inferredDate: null,
transcriptSource: null,
};
}
@@ -45,6 +45,7 @@ const FIXTURE_TRANSCRIPT: DiscoveredTranscript = {
content: 'Synthetic transcript content for gateway-adapter parity tests.',
contentHash: 'sha-fixture-1',
inferredDate: '2026-05-24',
transcriptSource: null,
};
describe('makeJudgeClient — construction-time provider probe', () => {
@@ -0,0 +1,109 @@
/**
* #2285 transcript metadata discovery.
*
* Pins the two discovery-side additions:
* 1. `transcriptSource` derived from the `<source>/<date>/<file>` path
* layout; null for ad-hoc inputs that don't match.
* 2. Content-based date inference the `| First message | <ISO> |` row in
* the transcript's `## Metadata` table wins over the filename-regex
* date (stable across mtime-restamping re-syncs); filename is the
* fallback.
*
* Pure filesystem; no engine, no LLM.
*/
import { describe, test, expect, beforeEach, afterEach } from 'bun:test';
import { mkdtempSync, rmSync, writeFileSync, mkdirSync } from 'node:fs';
import { tmpdir } from 'node:os';
import { join, dirname } from 'node:path';
import {
discoverTranscripts,
readSingleTranscript,
deriveTranscriptSource,
inferContentDate,
} from '../../src/core/cycle/transcript-discovery.ts';
let tmpDir: string;
beforeEach(() => {
tmpDir = mkdtempSync(join(tmpdir(), 'gbrain-transcript-meta-'));
});
afterEach(() => {
rmSync(tmpDir, { recursive: true, force: true });
});
function write(relPath: string, body: string): string {
const full = join(tmpDir, relPath);
mkdirSync(dirname(full), { recursive: true });
writeFileSync(full, body);
return full;
}
const FILLER = 'User: hello world. '.repeat(200);
const METADATA_BLOCK =
'## Metadata\n\n| Key | Value |\n| --- | --- |\n| First message | 2026-05-15T03:51:11.584Z |\n\n';
describe('deriveTranscriptSource', () => {
test('extracts the source slug from <source>/<date>/<file> layout', () => {
expect(deriveTranscriptSource('/corpus/claude-code/2026-06-12/abc.md')).toBe('claude-code');
expect(deriveTranscriptSource('/corpus/voice-notes/2026-06-12/xyz.md')).toBe('voice-notes');
});
test('null when the parent dir is not a date dir or grandparent is not a slug', () => {
expect(deriveTranscriptSource('/corpus/flat-file.md')).toBeNull();
expect(deriveTranscriptSource('/corpus/claude-code/not-a-date/abc.md')).toBeNull();
expect(deriveTranscriptSource('/corpus/Not A Slug/2026-06-12/abc.md')).toBeNull();
});
});
describe('inferContentDate', () => {
test('parses the | First message | row', () => {
expect(inferContentDate(METADATA_BLOCK)).toBe('2026-05-15');
});
test('null when absent', () => {
expect(inferContentDate(FILLER)).toBeNull();
});
});
describe('discoverTranscripts — transcriptSource + date cascade', () => {
test('populates transcriptSource per file; null for flat files', () => {
write('claude-code/2026-06-12/aaaa.md', FILLER);
write('2026-06-12-flat.md', FILLER);
const out = discoverTranscripts({ corpusDir: tmpDir, minChars: 100 });
const byBase = new Map(out.map(t => [t.basename, t.transcriptSource]));
expect(byBase.get('aaaa')).toBe('claude-code');
expect(byBase.get('2026-06-12-flat')).toBeNull();
});
test('content First-message date wins over the filename date', () => {
write('2026-01-01-named.md', METADATA_BLOCK + FILLER);
const out = discoverTranscripts({ corpusDir: tmpDir, minChars: 100 });
expect(out).toHaveLength(1);
expect(out[0].inferredDate).toBe('2026-05-15');
});
test('filename date remains the fallback when content has no metadata row', () => {
write('2026-01-01-named.md', FILLER);
const out = discoverTranscripts({ corpusDir: tmpDir, minChars: 100 });
expect(out[0].inferredDate).toBe('2026-01-01');
});
test('date filter matches on the content date for UUID-named transcripts', () => {
write('claude-code/2026-05-15/uuid-basename.md', METADATA_BLOCK + FILLER);
const hit = discoverTranscripts({ corpusDir: tmpDir, minChars: 100, date: '2026-05-15' });
expect(hit).toHaveLength(1);
const miss = discoverTranscripts({ corpusDir: tmpDir, minChars: 100, date: '2026-05-16' });
expect(miss).toHaveLength(0);
});
});
describe('readSingleTranscript — same metadata surface', () => {
test('carries transcriptSource and prefers the content date', () => {
const p = write('claude-code/2026-05-15/2026-01-01-single.md', METADATA_BLOCK + FILLER);
const t = readSingleTranscript(p, { minChars: 100 });
expect(t).not.toBeNull();
expect(t!.transcriptSource).toBe('claude-code');
expect(t!.inferredDate).toBe('2026-05-15');
});
});
+7 -3
View File
@@ -216,17 +216,21 @@ describe('progress reporter', () => {
});
test('only one process-level signal handler installed across many reporters', () => {
// Baseline: one handler already installed by prior tests in this file.
// Baseline: one handler already installed by prior tests in this file, and
// possibly live reporters from OTHER test files sharing this bun process
// (shard composition is not this test's invariant — assert the delta, not
// an absolute zero, or shard reshuffles make this fail spuriously).
const installedBefore = __signalHandlerInstalledForTest();
const liveBefore = __liveReporterCountForTest();
const { stream } = sink(false);
for (let i = 0; i < 50; i++) {
const p = createProgress({ mode: 'json', stream, minIntervalMs: 0, minItems: 1 });
p.start(`phase_${i}`, 1);
p.finish();
}
// After 50 reporter lifecycles, still exactly one handler and zero leaked live entries.
// After 50 reporter lifecycles, still exactly one handler and zero NET leaked live entries.
expect(__signalHandlerInstalledForTest()).toBe(installedBefore || true);
expect(__liveReporterCountForTest()).toBe(0);
expect(__liveReporterCountForTest()).toBe(liveBefore);
});
test('startHeartbeat() fires heartbeats and stop() clears', async () => {