Compare commits

..
Author SHA1 Message Date
1b45023dba fix(admin): source scoping + redirect URIs in admin OAuth registration
Takeover of #1558 (rebased onto master, admin/dist + admin-embedded
regenerated so asset hashes match; source changes salvaged intact):

- /admin/api/register-client now accepts source_id + federated_read
  (snake and camel case), validated fail-closed against the registered
  source list via the new normalizeAdminClientSourceScope
  (src/core/admin-source-scope.ts) before reaching
  registerClientManual — unknown or malformed ids are a 400, never a
  silently-hardcoded 'default'. Fixes #1490.
- New requireAdmin-gated GET /admin/api/sources feeds the Register
  Agent form; the form now has a Write Source select + Read Sources
  checkboxes, and the agents table/drawer show each client's scope.
- #1036: the Register Agent form now has a Redirect URIs textarea
  (one per line). When present, the POST carries redirectUris plus
  the authorization_code + refresh_token grants, mirroring the CLI's
  --redirect-uri grant-inference convention (src/commands/auth.ts).
  Backend plumbing already existed; this was UI-only.

Tests: test/admin-source-scope.test.ts (normalization matrix),
test/oauth.test.ts (registerClientManual persists source scope into
AuthInfo), test/fix-wave-structural.test.ts (endpoint + form pins for
#1490 and #1036).

Co-authored-by: flamerged <flamerged@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 15:09:32 -07:00
19 changed files with 354 additions and 432 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-CoGEje3-.js"></script>
<script type="module" crossorigin src="/admin/assets/index-CzLjRij_.js"></script>
<link rel="stylesheet" crossorigin href="/admin/assets/index-GxkWX7v3.css">
</head>
<body>
+1
View File
@@ -39,6 +39,7 @@ export const api = {
stats: () => apiFetch('/admin/api/stats'),
health: () => apiFetch('/admin/api/health-indicators'),
agents: () => apiFetch('/admin/api/agents'),
sources: () => apiFetch('/admin/api/sources'),
requests: (page = 1, qs = '') => apiFetch(`/admin/api/requests?page=${page}${qs}`),
apiKeys: () => apiFetch('/admin/api/api-keys'),
createApiKey: (name: string) => apiFetch('/admin/api/api-keys', { method: 'POST', body: JSON.stringify({ name }) }),
+87 -1
View File
@@ -23,9 +23,16 @@ interface Agent {
total_requests: number;
requests_today: number;
token_ttl: number | null;
source_id: string | null;
federated_read: string[] | null;
status: 'active' | 'revoked';
}
interface SourceOption {
id: string;
name: string | null;
}
interface ApiKey {
id: string;
name: string;
@@ -88,6 +95,7 @@ export function AgentsPage() {
<th>Name</th>
<th>Type</th>
<th>Scopes</th>
<th>Source</th>
<th>Status</th>
<th>Requests</th>
<th>Last Used</th>
@@ -108,6 +116,9 @@ export function AgentsPage() {
<span key={s} className={`badge badge-${s}`} style={{ marginRight: 4 }}>{s}</span>
))}
</td>
<td className="mono" style={{ fontSize: 12, color: 'var(--text-secondary)' }}>
{a.auth_type === 'oauth' ? (a.source_id || 'default') : 'all'}
</td>
<td>
<span className={`badge ${a.status === 'active' ? 'badge-success' : 'badge-danger'}`}>{a.status}</span>
</td>
@@ -257,9 +268,29 @@ function RegisterModal({ onClose, onRegistered }: {
Object.fromEntries(ALLOWED_SCOPES_LIST.map(s => [s, s === 'read'])) as Record<Scope, boolean>,
);
const [ttl, setTtl] = useState('86400'); // 24h default
const [redirectUris, setRedirectUris] = useState('');
const [sources, setSources] = useState<SourceOption[]>([{ id: 'default', name: 'default' }]);
const [sourceId, setSourceId] = useState('default');
const [readSources, setReadSources] = useState<Record<string, boolean>>({ default: true });
const [loading, setLoading] = useState(false);
const [error, setError] = useState('');
useEffect(() => {
api.sources()
.then((rows: SourceOption[]) => {
const nextSources = rows.length > 0 ? rows : [{ id: 'default', name: 'default' }];
const nextSourceId = nextSources.some(s => s.id === sourceId) ? sourceId : nextSources[0].id;
setSources(nextSources);
setSourceId(nextSourceId);
setReadSources(prev => {
const next = Object.fromEntries(nextSources.map(s => [s.id, Boolean(prev[s.id])])) as Record<string, boolean>;
next[nextSourceId] = true;
return next;
});
})
.catch(() => {});
}, []);
const ttlOptions = [
{ label: '1 hour', value: '3600' },
{ label: '24 hours', value: '86400' },
@@ -277,11 +308,24 @@ function RegisterModal({ onClose, onRegistered }: {
try {
// Use the CLI registration endpoint (POST to admin API)
const selectedScopes = Object.entries(scopes).filter(([, v]) => v).map(([k]) => k).join(' ');
const federatedRead = sources.map(s => s.id).filter(id => readSources[id]);
if (federatedRead.length === 0) { setError('Select at least one read source'); setLoading(false); return; }
// #1036: redirect URIs, one per line. Mirrors the CLI convention
// (src/commands/auth.ts): presence of redirect URIs implies
// authorization_code + refresh_token grants unless the user had none.
const uris = redirectUris.split('\n').map(u => u.trim()).filter(Boolean);
const res = await fetch('/admin/api/register-client', {
method: 'POST',
credentials: 'same-origin',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ name: name.trim(), scopes: selectedScopes, tokenTtl: ttl === '0' ? 315360000 : Number(ttl) }),
body: JSON.stringify({
name: name.trim(),
scopes: selectedScopes,
tokenTtl: ttl === '0' ? 315360000 : Number(ttl),
source_id: sourceId,
federated_read: federatedRead,
...(uris.length > 0 ? { redirectUris: uris, grantTypes: ['authorization_code', 'refresh_token'] } : {}),
}),
});
if (!res.ok) throw new Error('Registration failed');
const data = await res.json();
@@ -312,6 +356,42 @@ function RegisterModal({ onClose, onRegistered }: {
))}
</div>
</div>
<div style={{ marginBottom: 16 }}>
<label>Write Source</label>
<select value={sourceId} onChange={e => {
const id = e.target.value;
setSourceId(id);
setReadSources(p => ({ ...p, [id]: true }));
}}
style={{ width: '100%', background: 'var(--bg-secondary)', color: 'var(--text-primary)', border: '1px solid var(--border)', borderRadius: 6, padding: '6px 10px', fontSize: 14 }}>
{sources.map(s => <option key={s.id} value={s.id}>{s.name && s.name !== s.id ? `${s.id} (${s.name})` : s.id}</option>)}
</select>
</div>
<div style={{ marginBottom: 16 }}>
<label>Read Sources</label>
<div className="checkbox-group">
{sources.map(s => (
<label key={s.id} className="checkbox-label">
<input
type="checkbox"
checked={Boolean(readSources[s.id])}
onChange={e => setReadSources(p => ({ ...p, [s.id]: e.target.checked }))}
/>
{s.name && s.name !== s.id ? `${s.id} (${s.name})` : s.id}
</label>
))}
</div>
</div>
<div style={{ marginBottom: 16 }}>
<label>Redirect URIs <span style={{ color: 'var(--text-secondary)', fontWeight: 400 }}>(optional, one per line enables authorization_code flow)</span></label>
<textarea
placeholder={'https://example.com/callback'}
value={redirectUris}
onChange={e => setRedirectUris(e.target.value)}
rows={2}
style={{ width: '100%', background: 'var(--bg-secondary)', color: 'var(--text-primary)', border: '1px solid var(--border)', borderRadius: 6, padding: '6px 10px', fontSize: 13, fontFamily: 'inherit', resize: 'vertical' }}
/>
</div>
<div style={{ marginBottom: 20 }}>
<label>Token Lifetime</label>
<select value={ttl} onChange={e => setTtl(e.target.value)}
@@ -528,6 +608,8 @@ function AgentDrawer({ agent, onClose, onRevoked }: { agent: Agent; onClose: ()
client_name: agentName,
auth_type: agent.auth_type,
scope: agent.scope,
source_id: agent.source_id,
federated_read: agent.federated_read,
}, null, 2),
};
@@ -547,6 +629,10 @@ function AgentDrawer({ agent, onClose, onRevoked }: { agent: Agent; onClose: ()
<span>{(agent.scope || '').split(' ').filter(Boolean).map(s => (
<span key={s} className={`badge badge-${s}`} style={{ marginRight: 4 }}>{s}</span>
))}</span>
<span style={{ color: 'var(--text-secondary)' }}>Write Source</span>
<span className="mono">{agent.source_id || (isOAuth ? 'default' : 'all')}</span>
<span style={{ color: 'var(--text-secondary)' }}>Read Sources</span>
<span className="mono">{isOAuth ? (agent.federated_read && agent.federated_read.length > 0 ? agent.federated_read.join(', ') : (agent.source_id || 'default')) : 'all'}</span>
<span style={{ color: 'var(--text-secondary)' }}>Registered</span>
<span>{new Date(agent.created_at).toLocaleDateString()}</span>
<span style={{ color: 'var(--text-secondary)' }}>Token TTL</span>
+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 2026-05-27.
// Source: admin/dist/ at 2026-07-21.
//
// Bun resolves the file: imports to a path that works at runtime even
// inside a compiled binary (`bun build --compile`). The manifest maps
// the request path the express handler sees to (resolved-path, mime).
// @ts-ignore — type: 'file' is Bun ESM, not in lib.d.ts
import A_0_assets_index_CoGEje3__js from '../admin/dist/assets/index-CoGEje3-.js' with { type: 'file' };
import A_0_assets_index_CzLjRij__js from '../admin/dist/assets/index-CzLjRij_.js' with { type: 'file' };
// @ts-ignore — type: 'file' is Bun ESM, not in lib.d.ts
import A_1_assets_index_GxkWX7v3_css from '../admin/dist/assets/index-GxkWX7v3.css' with { type: 'file' };
// @ts-ignore — type: 'file' is Bun ESM, not in lib.d.ts
@@ -19,7 +19,7 @@ export interface AdminAsset {
}
export const ADMIN_ASSETS: Record<string, AdminAsset> = {
"/admin/assets/index-CoGEje3-.js": { path: A_0_assets_index_CoGEje3__js as unknown as string, mime: "application/javascript; charset=utf-8" },
"/admin/assets/index-CzLjRij_.js": { path: A_0_assets_index_CzLjRij__js as unknown as string, mime: "application/javascript; charset=utf-8" },
"/admin/assets/index-GxkWX7v3.css": { path: A_1_assets_index_GxkWX7v3_css as unknown as string, mime: "text/css; charset=utf-8" },
"/admin/index.html": { path: A_2_index_html as unknown as string, mime: "text/html; charset=utf-8" },
};
+32 -1
View File
@@ -39,6 +39,7 @@ import * as db from '../core/db.ts';
import { sqlQueryForEngine, executeRawJsonb } from '../core/sql-query.ts';
import { MinionQueue } from '../core/minions/queue.ts';
import { isRetryableError } from '../core/retry-matcher.ts';
import { normalizeAdminClientSourceScope } from '../core/admin-source-scope.ts';
import {
computeContentHash,
validateIngestionEvent,
@@ -1086,6 +1087,7 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
const oauthClients = await sql`
SELECT c.client_id as id, c.client_name as name, 'oauth' as auth_type,
c.grant_types, c.scope, c.created_at, c.token_ttl,
c.source_id, c.federated_read,
CASE WHEN c.deleted_at IS NOT NULL THEN 'revoked' ELSE 'active' END as status,
(SELECT max(created_at) FROM mcp_request_log WHERE token_name = c.client_id) as last_used_at,
(SELECT count(*)::int FROM mcp_request_log WHERE token_name = c.client_id) as total_requests,
@@ -1095,6 +1097,7 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
const legacyKeys = await sql`
SELECT a.id, a.name, 'api_key' as auth_type,
'{"bearer"}' as grant_types, 'read write admin' as scope, a.created_at, null as token_ttl,
null as source_id, null as federated_read,
CASE WHEN a.revoked_at IS NOT NULL THEN 'revoked' ELSE 'active' END as status,
a.last_used_at,
(SELECT count(*)::int FROM mcp_request_log WHERE token_name = a.name) as total_requests,
@@ -1107,6 +1110,17 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
}
});
app.get('/admin/api/sources', requireAdmin, async (_req: Request, res: Response) => {
try {
const sources = await engine.listAllSources({ includeArchived: false });
const options = sources.map(s => ({ id: s.id, name: s.name }));
if (!options.some(s => s.id === 'default')) options.unshift({ id: 'default', name: 'default' });
res.json(options);
} catch (e) {
res.status(503).json({ error: 'service_unavailable' });
}
});
// v0.38 Slice 4 — per-OAuth-client agent spend viewer. Pre-computes today's
// spend (committed + pending reservations) per client so the Agents tab
// can render a "$X / $Y today" cell. Read-side endpoint only — no mutation.
@@ -1440,6 +1454,8 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
// missing, empty) and rejects the rest with a structured 400.
const { name, tokenTtl, grantTypes, redirectUris, tokenEndpointAuthMethod } = req.body;
const rawScopes = (req.body as Record<string, unknown>).scopes ?? (req.body as Record<string, unknown>).scope;
const rawSourceId = (req.body as Record<string, unknown>).source_id ?? (req.body as Record<string, unknown>).sourceId;
const rawFederatedRead = (req.body as Record<string, unknown>).federated_read ?? (req.body as Record<string, unknown>).federatedRead;
if (!name) { res.status(400).json({ error: 'Name required' }); return; }
let scopeString: string;
try {
@@ -1470,8 +1486,23 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
});
return;
}
let sourceScope: ReturnType<typeof normalizeAdminClientSourceScope>;
try {
const sources = await engine.listAllSources({ includeArchived: false });
sourceScope = normalizeAdminClientSourceScope(
rawSourceId,
rawFederatedRead,
sources.map(s => s.id),
);
} catch (e) {
res.status(400).json({
error: 'invalid_source_scope',
message: e instanceof Error ? e.message : String(e),
});
return;
}
const result = await oauthProvider.registerClientManual(
name, grants, scopeString, uris, 'default', undefined, validatedAuthMethod,
name, grants, scopeString, uris, sourceScope.sourceId, sourceScope.federatedRead, validatedAuthMethod,
);
// Set per-client TTL if specified
if (tokenTtl && Number(tokenTtl) > 0) {
+51
View File
@@ -0,0 +1,51 @@
import { isValidSourceId } from './source-id.ts';
export interface AdminClientSourceScope {
sourceId: string;
federatedRead: string[];
}
function parseFederatedReadInput(raw: unknown, sourceId: string): string[] {
if (raw === undefined || raw === null) return [sourceId];
if (typeof raw === 'string') {
const values = raw.split(',').map(s => s.trim()).filter(Boolean);
return values.length > 0 ? values : [sourceId];
}
if (Array.isArray(raw)) {
if (!raw.every(v => typeof v === 'string')) {
throw new Error('federated_read must be an array of source ids');
}
const values = raw.map(v => v.trim()).filter(Boolean);
return values.length > 0 ? values : [sourceId];
}
throw new Error('federated_read must be a string or array');
}
export function normalizeAdminClientSourceScope(
rawSourceId: unknown,
rawFederatedRead: unknown,
availableSourceIds: string[],
): AdminClientSourceScope {
const knownSources = new Set(availableSourceIds);
const fallbackSourceId = knownSources.has('default') ? 'default' : (availableSourceIds[0] ?? 'default');
const sourceId = rawSourceId === undefined || rawSourceId === null || rawSourceId === ''
? fallbackSourceId
: rawSourceId;
if (!isValidSourceId(sourceId)) {
throw new Error(`Invalid source_id: ${JSON.stringify(sourceId)}`);
}
if (knownSources.size > 0 && !knownSources.has(sourceId)) {
throw new Error(`Unknown source_id: ${sourceId}`);
}
const federatedRead = Array.from(new Set(parseFederatedReadInput(rawFederatedRead, sourceId)));
for (const id of federatedRead) {
if (!isValidSourceId(id)) {
throw new Error(`Invalid federated_read source_id: ${JSON.stringify(id)}`);
}
if (knownSources.size > 0 && !knownSources.has(id)) {
throw new Error(`Unknown federated_read source_id: ${id}`);
}
}
return { sourceId, federatedRead };
}
+20 -101
View File
@@ -428,13 +428,8 @@ export async function runPhaseSynthesize(
const queue = new MinionQueue(engine);
const childIds: number[] = [];
/**
* 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>();
/** Map child job_id → chunk metadata for D6 orchestrator-side slug rewrite. */
const chunkInfo = new Map<number, { idx: number; hash6: string }>();
/** Skip reasons for the cycle report (D5 cap hits, D8 legacy-key skips). */
const skipReports: Array<{ filePath: string; reason: string }> = [];
@@ -518,14 +513,9 @@ export async function runPhaseSynthesize(
{ allowProtectedSubmit: true },
);
childIds.push(child.id);
childMeta.set(child.id, {
idx: i,
hash6,
chunkTotal: chunks.length,
transcriptSource: t.transcriptSource,
transcriptId: stripContentVersionSuffix(t.basename),
inferredDate: t.inferredDate,
});
if (isChunked) {
chunkInfo.set(child.id, { idx: i, hash6 });
}
}
}
@@ -554,14 +544,14 @@ 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: childMeta drives post-hoc rewrite of
// D6 orchestrator slug rewrite: chunkInfo 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, childMeta, cycleSourceId);
const writtenRefs = await collectChildPutPageSlugs(engine, childIds, chunkInfo, cycleSourceId);
const summaryDate = opts.date ?? today();
@@ -569,12 +559,7 @@ 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.
// #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);
await stampDreamProvenance(engine, writtenRefs, summaryDate);
// Dual-write: reverse-render each DB row → markdown file.
const reverseWriteCount = await reverseWriteRefs(engine, opts.brainDir, writtenRefs, cycleSourceId);
@@ -1110,17 +1095,15 @@ function sanitizeForSlug(s: string): string {
* fake"): we no longer need detection because the rewrite enforces
* uniqueness at slug-write time.
*
* `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.
* `chunkInfo` maps child job_id { chunk_index, hash6 }. Single-chunk
* children are absent from the map and pass through unchanged.
*/
async function collectChildPutPageSlugs(
engine: BrainEngine,
childIds: number[],
childMeta: Map<number, ChildMeta>,
chunkInfo: Map<number, { idx: number; hash6: string }>,
sourceId = 'default',
): Promise<Array<{ slug: string; source_id: string; jobId: number }>> {
): Promise<Array<{ slug: string; source_id: string }>> {
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
@@ -1139,73 +1122,16 @@ async function collectChildPutPageSlugs(
FROM subagent_tool_executions
WHERE job_id = ANY($1::int[])
AND tool_name = 'brain_put_page'
AND status = 'complete'
ORDER BY id`,
AND status = 'complete'`,
[childIds],
);
const rewritten = new Map<string, number>();
const rewritten = new Set<string>();
for (const r of rows) {
if (typeof r.slug !== 'string' || r.slug.length === 0) continue;
const meta = childMeta.get(r.job_id);
const finalSlug = meta && meta.chunkTotal > 1
? rewriteChunkedSlug(r.slug, meta.hash6, meta.idx)
: r.slug;
// Last writer wins, in execution-row order (ORDER BY id): if two children
// collide on a final slug, the pages row holds the LAST put_page write, so
// the stamp must attribute that child's transcript — not an arbitrary one.
rewritten.set(finalSlug, r.job_id);
const ci = chunkInfo.get(r.job_id);
rewritten.add(ci ? rewriteChunkedSlug(r.slug, ci.hash6, ci.idx) : r.slug);
}
return [...rewritten.entries()]
.sort(([a], [b]) => a.localeCompare(b))
.map(([slug, jobId]) => ({ slug, source_id: sourceId, jobId }));
}
/**
* Per-child orchestrator state. Drives D6 chunked-slug rewrite (idx + hash6)
* AND the deterministic frontmatter stampDreamProvenance merges into each
* written page. Populated for every child, not just chunked ones.
*/
interface ChildMeta {
idx: number;
hash6: string;
chunkTotal: number;
transcriptSource: string | null;
transcriptId: string;
inferredDate: string | null;
}
/**
* Strip the content-version suffix that claude-code-archive appends when a
* conversation is edited (`<uuid>--<contentHash>.md`). The session UUID is
* the stable transcript identifier; the suffix changes with content. Used to
* populate `transcript_id` so edits of the same session collapse to one id.
*/
function stripContentVersionSuffix(basename: string): string {
return basename.replace(/--[a-f0-9]+$/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;
return Array.from(rewritten).sort().map(slug => ({ slug, source_id: sourceId }));
}
/**
@@ -1251,19 +1177,12 @@ async function hasLegacySingleChunkCompletion(
*/
async function stampDreamProvenance(
engine: BrainEngine,
refs: Array<{ slug: string; source_id: string; jobId?: number }>,
refs: Array<{ slug: string; source_id: string }>,
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, 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 };
for (const { slug, source_id } of refs) {
try {
await executeRawJsonb(
engine,
@@ -1271,7 +1190,7 @@ async function stampDreamProvenance(
SET frontmatter = COALESCE(frontmatter, '{}'::jsonb) || $3::jsonb
WHERE slug = $1 AND source_id = $2`,
[slug, source_id],
[stamp],
[{ dream_generated: true, dream_cycle_date: cycleDate }],
);
} catch (e) {
const msg = e instanceof Error ? e.message : String(e);
+5 -58
View File
@@ -10,7 +10,7 @@
*/
import { readFileSync, readdirSync, statSync } from 'node:fs';
import { join, basename, dirname } from 'node:path';
import { join, basename } from 'node:path';
import { createHash } from 'node:crypto';
import { pruneDir } from '../sync.ts';
@@ -23,22 +23,8 @@ export interface DiscoveredTranscript {
content: string;
/** Filename basename without extension; used as a topic-slug seed. */
basename: string;
/**
* 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.
*/
/** Inferred date if the basename matches `YYYY-MM-DD...` (or null). */
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 {
@@ -175,36 +161,6 @@ 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
@@ -269,11 +225,8 @@ 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 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;
const inferredDate = dateMatch ? dateMatch[1] : null;
if (!isInDateRange(inferredDate, opts)) continue;
let content: string;
try {
@@ -288,17 +241,12 @@ 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),
});
}
}
@@ -342,7 +290,6 @@ export function readSingleTranscript(
contentHash: hashContent(content),
content,
basename: baseName,
inferredDate: inferContentDate(content) ?? (dateMatch ? dateMatch[1] : null),
transcriptSource: deriveTranscriptSource(filePath),
inferredDate: dateMatch ? dateMatch[1] : null,
};
}
+44
View File
@@ -0,0 +1,44 @@
import { describe, expect, test } from 'bun:test';
import { normalizeAdminClientSourceScope } from '../src/core/admin-source-scope.ts';
describe('admin register-client source scope normalization', () => {
const sources = ['default', 'team-a', 'team-b'];
test('defaults write and read scope to default source', () => {
expect(normalizeAdminClientSourceScope(undefined, undefined, sources)).toEqual({
sourceId: 'default',
federatedRead: ['default'],
});
});
test('accepts snake-case body fields with multiple read sources', () => {
expect(normalizeAdminClientSourceScope('team-a', ['team-a', 'team-b'], sources)).toEqual({
sourceId: 'team-a',
federatedRead: ['team-a', 'team-b'],
});
});
test('accepts comma-separated federated_read for API callers', () => {
expect(normalizeAdminClientSourceScope('team-a', 'team-b, default,team-b', sources)).toEqual({
sourceId: 'team-a',
federatedRead: ['team-b', 'default'],
});
});
test('falls back to selected write source when federated_read is empty', () => {
expect(normalizeAdminClientSourceScope('team-b', [], sources)).toEqual({
sourceId: 'team-b',
federatedRead: ['team-b'],
});
});
test('rejects malformed source ids before registration', () => {
expect(() => normalizeAdminClientSourceScope('../secret', undefined, sources)).toThrow(/Invalid source_id/);
expect(() => normalizeAdminClientSourceScope('team-a', ['snake_case'], sources)).toThrow(/Invalid federated_read/);
});
test('rejects valid-looking but unregistered source ids', () => {
expect(() => normalizeAdminClientSourceScope('ghost', undefined, sources)).toThrow(/Unknown source_id/);
expect(() => normalizeAdminClientSourceScope('team-a', ['ghost'], sources)).toThrow(/Unknown federated_read/);
});
});
-1
View File
@@ -26,7 +26,6 @@ const transcript: DiscoveredTranscript = {
content: 'User: hello world',
contentHash: 'abcdef0123456789',
inferredDate: '2026-07-17',
transcriptSource: null,
} as DiscoveredTranscript;
describe('#2415: buildSynthesisPrompt output root', () => {
@@ -152,94 +152,3 @@ 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
@@ -302,7 +302,6 @@ describe('judgeSignificance', () => {
content: 'A short conversation about something interesting.',
basename: 'x',
inferredDate: null,
transcriptSource: null,
};
}
@@ -416,7 +415,6 @@ describe('judgeSignificance — UTF-16 safety (v0.41.13)', () => {
content,
basename: 'long',
inferredDate: null,
transcriptSource: null,
};
}
@@ -45,7 +45,6 @@ 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', () => {
@@ -1,109 +0,0 @@
/**
* #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');
});
});
+26
View File
@@ -78,6 +78,8 @@ describe('v0.36.1.x #1077 — admin register-client supports PKCE public clients
// (under either name) from req.body. Pin the fallback pattern so the
// PKCE-fix regression contract stays load-bearing.
expect(src).toMatch(/req\.body[^;]*scopes\s*\?\?\s*[^;]*scope\b/);
expect(src).toMatch(/req\.body[^;]*source_id\s*\?\?\s*[^;]*sourceId\b/);
expect(src).toMatch(/req\.body[^;]*federated_read\s*\?\?\s*[^;]*federatedRead\b/);
// v0.41.3 (T4 atomicity fix, codex F4): admin endpoint now validates
// tokenEndpointAuthMethod via the shared validator and passes it to
// registerClientManual as a positional arg. Pre-v0.41.3 the route did
@@ -87,6 +89,7 @@ describe('v0.36.1.x #1077 — admin register-client supports PKCE public clients
// UPDATE block (the regex deliberately asserts the post-insert UPDATE
// is GONE).
expect(src).toMatch(/validateTokenEndpointAuthMethod\(tokenEndpointAuthMethod\)/);
expect(src).toMatch(/normalizeAdminClientSourceScope\(/);
expect(src).toMatch(/registerClientManual\([^)]*validatedAuthMethod[^)]*\)/);
// Regression guard: post-insert UPDATE flipping client_secret_hash to
// NULL based on a runtime check is exactly the non-atomic pattern T4
@@ -267,3 +270,26 @@ describe('v0.42.43.0 #2095 — volunteer-events sink + cycle purge wiring (struc
expect(src).toMatch(/purged_volunteer_events_count/);
});
});
describe('#1490 + #1036 — admin Register Agent form exposes source scope + redirect URIs', () => {
test('Agents.tsx RegisterModal sends source_id + federated_read in the POST body (#1490)', () => {
const src = readFileSync('admin/src/pages/Agents.tsx', 'utf8');
expect(src).toMatch(/source_id:\s*sourceId/);
expect(src).toMatch(/federated_read:\s*federatedRead/);
// The source list comes from the requireAdmin-gated endpoint, not a hardcoded 'default'.
expect(src).toMatch(/api\.sources\(\)/);
});
test('serve-http.ts serves /admin/api/sources behind requireAdmin (#1490)', () => {
const src = readFileSync('src/commands/serve-http.ts', 'utf8');
expect(src).toMatch(/app\.get\('\/admin\/api\/sources',\s*requireAdmin/);
});
test('Agents.tsx RegisterModal sends redirectUris + authorization_code grants when URIs are entered (#1036)', () => {
const src = readFileSync('admin/src/pages/Agents.tsx', 'utf8');
// One-per-line textarea split into an array...
expect(src).toMatch(/redirectUris\.split\('\\n'\)/);
// ...included in the body with the CLI's grant-type inference convention.
expect(src).toMatch(/redirectUris:\s*uris,\s*grantTypes:\s*\['authorization_code',\s*'refresh_token'\]/);
});
});
+24
View File
@@ -125,6 +125,30 @@ describe('client registration', () => {
expect(client!.client_name).toBe('test-agent');
});
test('registerClientManual persists source_id and federated_read into AuthInfo', async () => {
await sql`
INSERT INTO sources (id, name) VALUES (${'team-a'}, ${'Team A'}), (${'team-b'}, ${'Team B'})
ON CONFLICT DO NOTHING
`;
const { clientId, clientSecret } = await provider.registerClientManual(
'source-scoped-test',
['client_credentials'],
'read write',
[],
'team-a',
['team-a', 'team-b'],
);
const tokens = await provider.exchangeClientCredentials(clientId, clientSecret!, 'read');
const authInfo = await provider.verifyAccessToken(tokens.access_token) as {
sourceId?: string;
allowedSources?: string[];
};
expect(authInfo.sourceId).toBe('team-a');
expect(authInfo.allowedSources).toEqual(['team-a', 'team-b']);
});
test('getClient returns undefined for unknown client', async () => {
const client = await provider.clientsStore.getClient('nonexistent');
expect(client).toBeUndefined();
+3 -7
View File
@@ -216,21 +216,17 @@ describe('progress reporter', () => {
});
test('only one process-level signal handler installed across many reporters', () => {
// Baseline: one handler already installed by prior tests in this file, and
// possibly live reporters from OTHER test files sharing this bun process
// (shard composition is not this test's invariant — assert the delta, not
// an absolute zero, or shard reshuffles make this fail spuriously).
// Baseline: one handler already installed by prior tests in this file.
const installedBefore = __signalHandlerInstalledForTest();
const liveBefore = __liveReporterCountForTest();
const { stream } = sink(false);
for (let i = 0; i < 50; i++) {
const p = createProgress({ mode: 'json', stream, minIntervalMs: 0, minItems: 1 });
p.start(`phase_${i}`, 1);
p.finish();
}
// After 50 reporter lifecycles, still exactly one handler and zero NET leaked live entries.
// After 50 reporter lifecycles, still exactly one handler and zero leaked live entries.
expect(__signalHandlerInstalledForTest()).toBe(installedBefore || true);
expect(__liveReporterCountForTest()).toBe(liveBefore);
expect(__liveReporterCountForTest()).toBe(0);
});
test('startHeartbeat() fires heartbeats and stop() clears', async () => {