Compare commits

..
Author SHA1 Message Date
Garry TanandClaude Fable 5 f7029044a7 fix(auth): rescope-client admin endpoint returns 400 (not 500) for nonexistent write source
The FK-translated 'Source "x" does not exist' error is a client error;
map it to 400 like the sibling validation failures. ('No OAuth client
found' is matched first, so the 404 path is unaffected.)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-23 15:37:22 -07:00
Garry TanandClaude Fable 5 b099db46e2 fix(auth): admin-gated rescope surface for DCR clients stuck on default scope (#1914)
DCR clients self-register with source_id='default' + federated_read=['default']
and the registration comment promised 'rescope via the CLI later' — but no
rescope surface existed. Adds:

- GBrainOAuthProvider.rescopeClient(clientId, { sourceId?, federatedRead? }):
  single-statement COALESCE update, canonical source-id validation
  (assertValidSourceId), FK-backed existence check on the write source,
  friendly errors for pre-v60/v61 schemas and unknown clients. Takes effect
  for already-issued tokens because verifyAccessToken re-reads oauth_clients.
- gbrain auth rescope-client <client_id> [--source S] [--federated-read a,b]
  (trusted local CLI).
- POST /admin/api/rescope-client (requireAdmin), mirroring the existing
  register-client / revoke-client admin endpoints.

Deliberately does NOT let clients self-widen scope (options a/b from the
issue) — fail-closed trust invariant.

Fixes #1914

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-23 15:11:22 -07:00
15 changed files with 381 additions and 283 deletions
+60
View File
@@ -515,6 +515,60 @@ async function registerClient(name: string, args: string[]) {
}
}
/**
* v0.42.x (#1914): rescope an existing OAuth client's write source and/or
* federated read scope. This is the operator surface the DCR registration
* comment promised ("rescope via the CLI later") — DCR clients land with
* source_id='default' / federated_read=['default'] and must not self-widen,
* so widening happens here (trusted local CLI) or via the requireAdmin
* /admin/api/rescope-client endpoint.
*/
async function rescopeClient(clientId: string, args: string[]) {
const usage = 'Usage: auth rescope-client <client_id> [--source SOURCE] [--federated-read SRC1,SRC2,...]';
if (!clientId) {
console.error(usage);
process.exit(1);
}
let sourceId: string | undefined;
let federatedRead: string[] | undefined;
for (let i = 0; i < args.length; i += 2) {
const flag = args[i];
const value = args[i + 1];
if (value === undefined || value.startsWith('--')) {
console.error(`Error: ${flag} requires a value`);
console.error(usage);
process.exit(1);
}
if (flag === '--source') sourceId = value;
else if (flag === '--federated-read') {
federatedRead = value.split(',').map(s => s.trim()).filter(Boolean);
} else {
console.error(`Error: Unknown flag: ${flag}`);
console.error(usage);
process.exit(1);
}
}
if (sourceId === undefined && federatedRead === undefined) {
console.error('Error: pass --source and/or --federated-read');
console.error(usage);
process.exit(1);
}
try {
await withConfiguredSql(async (sql) => {
const { GBrainOAuthProvider } = await import('../core/oauth-provider.ts');
const provider = new GBrainOAuthProvider({ sql });
const result = await provider.rescopeClient(clientId, { sourceId, federatedRead });
console.log(`OAuth client rescoped: "${result.clientName}" (${result.clientId})\n`);
console.log(` Write source: ${result.sourceId}`);
console.log(` Federated reads: ${result.federatedRead.join(', ') || '<none>'}`);
console.log('\nTakes effect on the client\'s next request (existing tokens included).');
});
} catch (e: any) {
console.error('Error:', e.message);
process.exit(1);
}
}
/**
* Entry point for the `gbrain auth` CLI subcommand. Also reused by the
* direct-script path (see bottom of file) so `bun run src/commands/auth.ts`
@@ -556,6 +610,7 @@ export async function runAuth(args: string[]): Promise<void> {
return;
}
case 'register-client': await registerClient(rest[0], rest.slice(1)); return;
case 'rescope-client': await rescopeClient(rest[0], rest.slice(1)); return;
case 'revoke-client': await revokeClient(rest[0]); return;
case 'test': {
const tokenIdx = rest.indexOf('--token');
@@ -593,6 +648,11 @@ Usage:
--bound-slug-prefixes <prefix1,prefix2> Bind submit_agent writes to slug prefixes
--bound-max-concurrent <n> Bound submit_agent concurrency (default: 1)
--budget-usd-per-day <usd> Bound submit_agent daily spend cap
gbrain auth rescope-client <client_id> [options] Change an existing client's source scope (e.g. a DCR
client stuck on the 'default' source). Only the flags
you pass change; the other axis is left as-is.
--source <id> New write source
--federated-read <id1,id2,...> New read-scope source list
gbrain auth revoke-client <client_id> Hard-delete an OAuth 2.1 client (cascades to tokens + codes)
gbrain auth test <url> --token <token> Smoke-test a remote MCP server
`);
+20 -3
View File
@@ -249,6 +249,13 @@ async function resolveAIOptions(opts: ResolveAIOptionsArgs): Promise<ResolvedAIO
// --- Tier 1+2: explicit flags ---------------------------------------------
// #2301: an explicit embedding flag on THIS invocation overrides the
// persisted deferred-setup sentinel above. Without this, a stale
// `embedding_disabled: true` in config.json made every re-init defer
// embedding — including `gbrain init --embedding-model ...`, the exact
// recovery path the deferred-setup message tells users to take.
if (verbose || shorthand) delete out.noEmbedding;
if (verbose) {
out.embedding_model = verbose;
} else if (shorthand) {
@@ -435,7 +442,7 @@ function printNoEmbeddingProviderHint(typos: Array<{ userSet: string; suggested:
console.error(' gbrain init --pglite --embedding-model openai:text-embedding-3-large');
console.error('');
console.error('Or defer setup: gbrain init --pglite --no-embedding');
console.error(' (you can configure later with `gbrain config set embedding_model <id>`)');
console.error(' (you can configure later with `gbrain init --force --embedding-model <provider>:<model>`)');
// D13: surface near-miss env vars (e.g. OPENAPI_API_KEY → OPENAI_API_KEY).
if (typos.length > 0) {
console.error('');
@@ -833,7 +840,7 @@ async function initPGLite(opts: {
let resolvedModel: string | undefined;
if (opts.aiOpts?.noEmbedding) {
// D9 deferred-setup mode: skip preflight, no model/dim resolved.
console.log(` --no-embedding: deferred setup — configure with \`gbrain config set embedding_model <id>\` before import`);
console.log(` --no-embedding: deferred setup — run \`gbrain init --force --embedding-model <provider>:<model>\` before import`);
} else if (opts.aiOpts?.embedding_model) {
const { resolveSchemaEmbeddingDim } = await import('../core/embedding-dim-check.ts');
const pre = resolveSchemaEmbeddingDim({
@@ -972,6 +979,12 @@ async function initPGLite(opts: {
// unless explicitly overridden by --schema-pack on re-init.
...(opts.schemaPack ? { schema_pack: opts.schemaPack } : {}),
};
// #2301: a resolved embedding model supersedes any stale deferred-setup
// sentinel carried over via ...existingFile — otherwise the sentinel
// re-defers embedding on every future init/embed forever.
if (!opts.aiOpts?.noEmbedding && resolvedModel && resolvedDim) {
delete config.embedding_disabled;
}
// PR1: new installs publish their skill catalog over MCP by default
// (existing config wins on re-init, so a prior opt-out is preserved).
config.mcp = { publish_skills: true, ...(config.mcp ?? {}) };
@@ -1056,7 +1069,7 @@ async function initPostgres(opts: {
let resolvedDim: number | undefined;
let resolvedModel: string | undefined;
if (opts.aiOpts?.noEmbedding) {
console.log(` --no-embedding: deferred setup — configure with \`gbrain config set embedding_model <id>\` before import`);
console.log(` --no-embedding: deferred setup — run \`gbrain init --force --embedding-model <provider>:<model>\` before import`);
} else if (opts.aiOpts?.embedding_model) {
const { resolveSchemaEmbeddingDim } = await import('../core/embedding-dim-check.ts');
const pre = resolveSchemaEmbeddingDim({
@@ -1220,6 +1233,10 @@ async function initPostgres(opts: {
// v0.42 (T17): same schema_pack default as PGLite path.
...(opts.schemaPack ? { schema_pack: opts.schemaPack } : {}),
};
// #2301: same stale-sentinel drop as the PGLite path above.
if (!opts.aiOpts?.noEmbedding && resolvedModel && resolvedDim) {
delete config.embedding_disabled;
}
// PR1: new installs publish their skill catalog over MCP by default
// (existing config wins on re-init, so a prior opt-out is preserved).
config.mcp = { publish_skills: true, ...(config.mcp ?? {}) };
+32
View File
@@ -1567,6 +1567,38 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
}
});
// v0.42.x (#1914): rescope an OAuth client's write source / federated read
// scope. Admin-gated on purpose — DCR clients must never self-widen their
// scope (fail-closed trust); only the operator rescopes, here or via
// `gbrain auth rescope-client`. Source ids are validated by the canonical
// validator inside rescopeClient.
app.post('/admin/api/rescope-client', requireAdmin, express.json(), async (req: Request, res: Response) => {
try {
const { clientId, sourceId, federatedRead } = req.body ?? {};
if (!clientId || typeof clientId !== 'string') {
res.status(400).json({ error: 'clientId required' });
return;
}
if (federatedRead !== undefined &&
!(Array.isArray(federatedRead) && federatedRead.every((s: unknown) => typeof s === 'string'))) {
res.status(400).json({ error: 'federatedRead must be an array of source id strings' });
return;
}
if (sourceId !== undefined && typeof sourceId !== 'string') {
res.status(400).json({ error: 'sourceId must be a string' });
return;
}
const result = await oauthProvider.rescopeClient(clientId, { sourceId, federatedRead });
res.json(result);
} catch (e) {
const message = e instanceof Error ? e.message : 'Rescope failed';
const status = /No OAuth client found/.test(message) ? 404
: /Invalid source_id|requires --source|cannot be empty|does not exist/.test(message) ? 400
: 500;
res.status(status).json({ error: message });
}
});
// Revoke OAuth client
app.post('/admin/api/revoke-client', requireAdmin, express.json(), async (req: Request, res: Response) => {
try {
+5 -40
View File
@@ -486,44 +486,9 @@ const DEFAULT_PARALLELISM = 4;
* src/core/errors.ts (the v0.19.0 envelope every new agent-facing
* surface uses) rather than introducing a new BrainstormError class.
*/
/** File-config slice the orchestrator reads (see loadConfig in core/config.ts). */
export interface BrainstormRunConfig {
embedding_model?: string;
chat_model?: string;
emotional_weight?: { user_holder?: string };
}
/**
* Model used for the cost preview + hard cost ceiling. Mirrors what the
* gateway will actually run: explicit --model override, else the configured
* chat_model (gateway default), else the hardcoded gateway fallback. Before
* this resolved through config, a non-Sonnet chat_model got its preview
* priced against the wrong model. (Takeover of PR #1855 by @starm2010.)
*/
export function resolveBrainstormChatModel(
config: { chat_model?: string },
modelOverride?: string,
): string {
return modelOverride ?? config.chat_model ?? 'anthropic:claude-sonnet-4-6';
}
/**
* Judge-phase model precedence: --judge-model flag, else the
* `models.brainstorm.judge` config key, else undefined (falls back to
* `modelOverride` then the gateway default at the runJudge callsite).
*/
export async function resolveBrainstormJudgeModel(
engine: BrainEngine,
judgeModelFlag?: string,
): Promise<string | undefined> {
if (judgeModelFlag) return judgeModelFlag;
const configured = await engine.getConfig('models.brainstorm.judge');
return configured ?? undefined;
}
export async function runBrainstorm(
engine: BrainEngine,
config: BrainstormRunConfig,
config: { embedding_model?: string; emotional_weight?: { user_holder?: string } },
opts: BrainstormOptions
): Promise<BrainstormResult> {
// v0.39.3.0 (Phase 5, CV11+T4): outer try/catch around the orchestrator
@@ -545,7 +510,7 @@ export async function runBrainstorm(
async function runBrainstormImpl(
engine: BrainEngine,
config: BrainstormRunConfig,
config: { embedding_model?: string; emotional_weight?: { user_holder?: string } },
opts: BrainstormOptions,
): Promise<BrainstormResult> {
// v0.39.0.0 T10: install a gateway-layer BudgetTracker scope around the
@@ -565,7 +530,7 @@ async function runBrainstormImpl(
async function _runBrainstormInner(
engine: BrainEngine,
config: BrainstormRunConfig,
config: { embedding_model?: string; emotional_weight?: { user_holder?: string } },
opts: BrainstormOptions,
): Promise<BrainstormResult> {
const profile = opts.profile ?? BRAINSTORM_PROFILE;
@@ -574,7 +539,7 @@ async function _runBrainstormInner(
const embedFn = opts.embedQueryFn ?? embedQuery;
// ---- Phase 0: cost preview + TTY grace ----
const modelStr = resolveBrainstormChatModel(config, opts.modelOverride);
const modelStr = opts.modelOverride ?? 'anthropic:claude-sonnet-4-6';
const { aborted, estimate } = await previewCostAndWait({
profile,
model: modelStr,
@@ -883,7 +848,7 @@ async function _runBrainstormInner(
far_slug: i.far_slug,
}));
const judgeResult = await runJudge(profile.judge_config, judgeInput, {
modelOverride: (await resolveBrainstormJudgeModel(engine, opts.judgeModel)) ?? opts.modelOverride,
modelOverride: opts.judgeModel ?? opts.modelOverride,
chatFn: opts.chatFn,
activeBiasTags: activeBiasTags ?? undefined,
abortSignal: opts.abortSignal,
-1
View File
@@ -962,7 +962,6 @@ export const KNOWN_CONFIG_KEYS: readonly string[] = [
'models.subagent',
'models.expansion',
'models.chat',
'models.brainstorm.judge',
'models.eval.longmemeval',
'facts.extraction_model',
// #2113: output-token cap for the per-turn facts extractor (default 4000).
+10 -74
View File
@@ -39,11 +39,11 @@
import { randomUUID, createHash } from 'node:crypto';
import { BaseCyclePhase, type ScopedReadOpts, type BasePhaseOpts } from './base-phase.ts';
import { chat as gatewayChat, getChatModel, probeChatModel } from '../ai/gateway.ts';
import { normalizeModelId } from '../model-id.ts';
import { chat as gatewayChat, getChatModel } from '../ai/gateway.ts';
import { writeReceipt } from '../extract/receipt-writer.ts';
import { upsertExtractRollup } from '../extract/rollup-writer.ts';
import { GBrainError } from '../types.ts';
import type { Page, PageFilters } from '../types.ts';
import type { OperationContext } from '../operations.ts';
import type { BrainEngine } from '../engine.ts';
import type { PhaseStatus, CyclePhase } from '../cycle.ts';
@@ -160,48 +160,6 @@ export interface ProposeTakesResult {
warnings: string[];
}
/** Narrow projection of `pages` — the only columns this phase reads. */
interface ProposeTakesPageRow {
slug: string;
source_id: string;
compiled_truth: string | null;
}
/**
* Load proposal candidates with a narrow projection instead of
* `engine.listPages` (`SELECT p.*`). The phase only reads slug, source_id
* and compiled_truth — skipping timeline/frontmatter/title keeps large
* toasted columns out of the hot path. Scope precedence mirrors
* `sourceScopeOpts`: federated array (`sourceIds`) beats scalar
* (`sourceId`); ordering matches `PAGE_SORT_SQL.updated_desc` with an id
* tiebreak for determinism. (Takeover of PR #1979's projection by
* @shawnduggan.)
*/
async function listCandidatePages(
engine: BrainEngine,
scope: ScopedReadOpts,
limit: number,
): Promise<ProposeTakesPageRow[]> {
const where = ['deleted_at IS NULL'];
const params: unknown[] = [];
if (scope.sourceIds && scope.sourceIds.length > 0) {
params.push(scope.sourceIds);
where.push(`source_id = ANY($${params.length}::text[])`);
} else if (scope.sourceId) {
params.push(scope.sourceId);
where.push(`source_id = $${params.length}`);
}
params.push(limit);
return engine.executeRaw<ProposeTakesPageRow>(
`SELECT slug, source_id, compiled_truth
FROM pages
WHERE ${where.join(' AND ')}
ORDER BY updated_at DESC, id DESC
LIMIT $${params.length}`,
params,
);
}
/**
* Compute the content_hash key for the idempotency cache. SHA-256 of the
* page body suffices — page slug + prompt_version are separate columns in
@@ -372,34 +330,6 @@ class ProposeTakesPhase extends BaseCyclePhase {
const phaseStartMs = Date.now();
const proposalRunId = `propose-${new Date().toISOString().slice(0, 19).replace(/[-:T]/g, '')}-${randomUUID().slice(0, 8)}`;
const modelId = opts.model ?? getChatModel();
// With the default (gateway) extractor, skip cheaply when the resolved
// model's provider can't run — same probe semantics as patterns.ts /
// think/index.ts: unknown provider/model or Anthropic-without-key skips;
// other providers' auth surfaces lazily at chat() time. An injected
// extractor bypasses the gateway, so it is never gated. (Takeover of
// PR #1979's intent by @shawnduggan.)
if (!opts.extractor) {
const probe = probeChatModel(normalizeModelId(modelId));
if (!probe.ok) {
return {
summary: `propose_takes skipped: ${probe.detail}`,
details: {
reason: 'no_provider',
model: modelId,
pages_scanned: 0,
cache_hits: 0,
cache_misses: 0,
proposals_inserted: 0,
budget_exhausted: false,
warnings: [],
},
status: 'skipped',
};
}
}
const result: ProposeTakesResult = {
pages_scanned: 0,
cache_hits: 0,
@@ -410,12 +340,19 @@ class ProposeTakesPhase extends BaseCyclePhase {
};
// Load pages eligible for proposal. Source-scoped per BaseCyclePhase.
const pages = await listCandidatePages(engine, scope, pageLimit);
const pageFilters: PageFilters = {
...scope,
limit: pageLimit,
sort: 'updated_desc',
};
const pages: Page[] = await engine.listPages(pageFilters);
if (opts.reporter) {
opts.reporter.start('propose_takes.pages' as never, pages.length);
}
const modelId = opts.model ?? getChatModel();
for (const page of pages) {
// Phase deadline check. Break (not throw) so the phase returns a
// partial result with deadline_hit:true; work already banked stays.
@@ -572,5 +509,4 @@ export const __testing = {
contentHash,
hasCompleteFence,
extractExistingTakesForDedup,
listCandidatePages,
};
+2 -3
View File
@@ -71,9 +71,8 @@ export function assertEmbeddingEnabled(cfg: { embedding_disabled?: boolean } | n
throw new EmbeddingDisabledError(
'This brain was initialized with `--no-embedding` (deferred setup).\n' +
'Configure an embedding provider before running embed / import:\n' +
' gbrain config set embedding_model <provider>:<model>\n' +
' gbrain config set embedding_dimensions <N>\n' +
' gbrain init --force --embedding-model <provider>:<model> # re-init to size schema\n',
' gbrain init --force --embedding-model <provider>:<model> # re-init to size schema\n' +
'(`gbrain config set embedding_model` is refused — schema-sizing fields are set at init.)\n',
);
}
}
+61
View File
@@ -24,6 +24,7 @@ import type { OAuthRegisteredClientsStore } from '@modelcontextprotocol/sdk/serv
import type { AuthInfo as SdkAuthInfo } from '@modelcontextprotocol/sdk/server/auth/types.js';
import { InvalidTokenError, InvalidClientMetadataError } from '@modelcontextprotocol/sdk/server/auth/errors.js';
import { hashToken, generateToken, isUndefinedColumnError } from './utils.ts';
import { assertValidSourceId } from './source-id.ts';
import { hasScope, assertAllowedScopes, parseScopeString, InvalidScopeError } from './scope.ts';
import type { AuthInfo as CoreAuthInfo } from './operations.ts';
import { parseLegacyTokenScope } from './legacy-token-scope.ts';
@@ -1006,6 +1007,66 @@ export class GBrainOAuthProvider implements OAuthServerProvider {
return { clientId, clientSecret };
}
/**
* v0.42.x (#1914): admin-gated rescope for an existing OAuth client.
*
* DCR clients self-register with source_id='default' +
* federated_read=['default'] and MUST NOT be able to widen their own
* scope (fail-closed trust). This is the trusted-operator surface that
* changes it afterward: `gbrain auth rescope-client` (local CLI) and
* POST /admin/api/rescope-client (requireAdmin) both route here.
*
* Omitted fields are left untouched (COALESCE). Takes effect on the
* client's NEXT request even for already-issued tokens, because
* verifyAccessToken re-reads oauth_clients on every verification.
*/
async rescopeClient(
clientId: string,
opts: { sourceId?: string; federatedRead?: string[] },
): Promise<{ clientId: string; clientName: string; sourceId: string; federatedRead: string[] }> {
const { sourceId, federatedRead } = opts;
if (sourceId === undefined && federatedRead === undefined) {
throw new Error('rescope-client requires --source and/or --federated-read');
}
if (sourceId !== undefined) assertValidSourceId(sourceId);
if (federatedRead !== undefined) {
if (federatedRead.length === 0) {
throw new Error('--federated-read cannot be empty (pass at least one source id)');
}
for (const s of federatedRead) assertValidSourceId(s);
}
let rows: Record<string, unknown>[];
try {
rows = await this.sql`
UPDATE oauth_clients
SET source_id = COALESCE(${sourceId ?? null}::text, source_id),
federated_read = COALESCE(${federatedRead ? pgArray(federatedRead) : null}::text[], federated_read)
WHERE client_id = ${clientId}
RETURNING client_id, client_name, source_id, federated_read
`;
} catch (err) {
if (isUndefinedColumnError(err, 'source_id') || isUndefinedColumnError(err, 'federated_read')) {
throw new Error('rescope-client requires an up-to-date OAuth schema; run `gbrain apply-migrations --yes` and retry.');
}
// FK oauth_clients.source_id → sources(id): translate the raw 23503
// into an actionable message.
if ((err as { code?: string })?.code === '23503') {
throw new Error(`Source "${sourceId}" does not exist. Create it first: gbrain sources add ${sourceId} ...`);
}
throw err;
}
if (rows.length === 0) {
throw new Error(`No OAuth client found with id "${clientId}"`);
}
const row = rows[0];
return {
clientId: row.client_id as string,
clientName: (row.client_name as string | null) ?? '',
sourceId: (row.source_id as string | null) ?? 'default',
federatedRead: Array.isArray(row.federated_read) ? (row.federated_read as string[]) : [],
};
}
// -------------------------------------------------------------------------
// Internal: Issue access + optional refresh tokens
// -------------------------------------------------------------------------
+2 -2
View File
@@ -4835,11 +4835,11 @@ export class PGLiteEngine implements BrainEngine {
const { rows } = await this.db.query(
`SELECT t.id AS take_id, t.page_id, p.slug AS page_slug, t.row_num,
t.claim, t.kind, t.holder, t.weight,
word_similarity($1, t.claim)::real AS score
similarity(t.claim, $1)::real AS score
FROM takes t
JOIN pages p ON p.id = t.page_id
WHERE t.active
AND $1 <% t.claim
AND t.claim % $1
AND ($2::text[] IS NULL OR t.holder = ANY($2::text[]))
AND ($4::text[] IS NULL OR p.source_id = ANY($4::text[]))
AND ($5::text IS NULL OR p.source_id = $5::text)
+2 -2
View File
@@ -4962,11 +4962,11 @@ export class PostgresEngine implements BrainEngine {
const rows = await sql`
SELECT t.id AS take_id, t.page_id, p.slug AS page_slug, t.row_num,
t.claim, t.kind, t.holder, t.weight,
word_similarity(${query}, t.claim)::real AS score
similarity(t.claim, ${query})::real AS score
FROM takes t
JOIN pages p ON p.id = t.page_id
WHERE t.active
AND ${query} <% t.claim
AND t.claim % ${query}
AND (
${opts.takesHoldersAllowList ?? null}::text[] IS NULL
OR t.holder = ANY(${opts.takesHoldersAllowList ?? null}::text[])
-65
View File
@@ -1,65 +0,0 @@
/**
* Brainstorm model configurability (takeover of PR #1855 by @starm2010).
*
* - The cost preview + hard cost ceiling price the model that will actually
* run: --model override → configured chat_model → gateway fallback. Before
* this, the preview always priced anthropic:claude-sonnet-4-6 even when
* the configured chat_model was something else.
* - The judge phase honors the `models.brainstorm.judge` config key when no
* --judge-model flag is passed.
*/
import { describe, test, expect } from 'bun:test';
import {
resolveBrainstormChatModel,
resolveBrainstormJudgeModel,
} from '../../src/core/brainstorm/orchestrator.ts';
import type { BrainEngine } from '../../src/core/engine.ts';
function mockEngine(configValues: Record<string, string>): { engine: BrainEngine; reads: string[] } {
const reads: string[] = [];
const engine = {
async getConfig(key: string): Promise<string | null> {
reads.push(key);
return configValues[key] ?? null;
},
} as unknown as BrainEngine;
return { engine, reads };
}
describe('resolveBrainstormChatModel', () => {
test('--model override wins over config', () => {
expect(resolveBrainstormChatModel({ chat_model: 'openai:gpt-5' }, 'anthropic:claude-opus-4-6'))
.toBe('anthropic:claude-opus-4-6');
});
test('configured chat_model wins over the hardcoded fallback', () => {
expect(resolveBrainstormChatModel({ chat_model: 'openai:gpt-5' }))
.toBe('openai:gpt-5');
});
test('falls back to the gateway default model when nothing is configured', () => {
expect(resolveBrainstormChatModel({})).toBe('anthropic:claude-sonnet-4-6');
});
});
describe('resolveBrainstormJudgeModel', () => {
test('--judge-model flag wins without touching config', async () => {
const { engine, reads } = mockEngine({ 'models.brainstorm.judge': 'openai:gpt-5' });
const out = await resolveBrainstormJudgeModel(engine, 'anthropic:claude-opus-4-6');
expect(out).toBe('anthropic:claude-opus-4-6');
expect(reads).toHaveLength(0);
});
test('models.brainstorm.judge config key is honored when no flag is passed', async () => {
const { engine, reads } = mockEngine({ 'models.brainstorm.judge': 'openai:gpt-5' });
const out = await resolveBrainstormJudgeModel(engine);
expect(out).toBe('openai:gpt-5');
expect(reads).toEqual(['models.brainstorm.judge']);
});
test('returns undefined (defer to modelOverride / gateway default) when unset', async () => {
const { engine } = mockEngine({});
expect(await resolveBrainstormJudgeModel(engine)).toBeUndefined();
});
});
+111
View File
@@ -0,0 +1,111 @@
/**
* #2301 — re-init with an explicit --embedding-model must recover a brain
* that was initialized with --no-embedding (deferred setup).
*
* Pre-fix: resolveAIOptions honored the persisted `embedding_disabled: true`
* sentinel BEFORE the explicit flag and never cleared noEmbedding, and the
* persistence merge carried the sentinel forward via ...existingFile. Result:
* every re-init (including the recovery command the deferred-setup error
* itself recommends) silently re-deferred embedding, forever.
*
* Hermetic: in-process runInit, GBRAIN_HOME pinned to a tmpdir (same pattern
* as test/e2e/fresh-install-pglite.test.ts).
*/
import { afterEach, beforeEach, describe, expect, test } from 'bun:test';
import { mkdtempSync, rmSync, readFileSync } from 'fs';
import { tmpdir } from 'os';
import { join } from 'path';
import { configureGateway, resetGateway } from '../../src/core/ai/gateway.ts';
describe('E2E: re-init with --embedding-model after --no-embedding init (#2301)', () => {
let tmpHome: string;
let origHome: string | undefined;
let origZeKey: string | undefined;
let origOpenaiKey: string | undefined;
let origVoyageKey: string | undefined;
beforeEach(() => {
tmpHome = mkdtempSync(join(tmpdir(), 'gbrain-e2e-reinit-'));
origHome = process.env.GBRAIN_HOME;
origZeKey = process.env.ZEROENTROPY_API_KEY;
origOpenaiKey = process.env.OPENAI_API_KEY;
origVoyageKey = process.env.VOYAGE_API_KEY;
delete process.env.OPENAI_API_KEY;
delete process.env.VOYAGE_API_KEY;
process.env.GBRAIN_HOME = tmpHome;
process.env.ZEROENTROPY_API_KEY = 'sk-test-ze';
resetGateway();
});
afterEach(() => {
rmSync(tmpHome, { recursive: true, force: true });
if (origHome === undefined) delete process.env.GBRAIN_HOME;
else process.env.GBRAIN_HOME = origHome;
if (origZeKey === undefined) delete process.env.ZEROENTROPY_API_KEY;
else process.env.ZEROENTROPY_API_KEY = origZeKey;
if (origOpenaiKey !== undefined) process.env.OPENAI_API_KEY = origOpenaiKey;
if (origVoyageKey !== undefined) process.env.VOYAGE_API_KEY = origVoyageKey;
// Restore legacy-preload gateway state (mirrors fresh-install-pglite.test.ts).
configureGateway({
embedding_model: 'openai:text-embedding-3-large',
embedding_dimensions: 1536,
env: { ...process.env },
});
});
async function runInitCapturing(args: string[]): Promise<string> {
const { runInit } = await import('../../src/commands/init.ts');
const origLog = console.log;
const origWarn = console.warn;
const stdoutBuf: string[] = [];
console.log = (...a: unknown[]) => {
stdoutBuf.push(a.map(x => (typeof x === 'string' ? x : JSON.stringify(x))).join(' '));
};
console.warn = () => {};
try {
await runInit(args);
} finally {
console.log = origLog;
console.warn = origWarn;
}
return stdoutBuf.join('\n');
}
const cfgPath = () => join(tmpHome, '.gbrain', 'config.json');
const readCfg = () => JSON.parse(readFileSync(cfgPath(), 'utf-8'));
test('explicit --embedding-model clears the persisted embedding_disabled sentinel', async () => {
// Step 1: deferred-setup init writes the sentinel.
const out1 = await runInitCapturing(['--pglite', '--non-interactive', '--no-embedding']);
expect(out1).toContain('deferred setup');
const cfg1 = readCfg();
expect(cfg1.embedding_disabled).toBe(true);
expect(cfg1.embedding_model).toBeUndefined();
// Step 2: re-init with an explicit embedding model — the recovery path.
// Pre-fix this printed the deferred-setup line again and re-persisted
// embedding_disabled: true.
const out2 = await runInitCapturing([
'--pglite', '--non-interactive', '--skip-embed-check',
'--embedding-model', 'zeroentropyai:zembed-1',
'--embedding-dimensions', '1280',
]);
expect(out2).not.toContain('deferred setup');
expect(out2).toContain('zeroentropyai:zembed-1');
const cfg2 = readCfg();
expect(cfg2.embedding_model).toBe('zeroentropyai:zembed-1');
expect(cfg2.embedding_dimensions).toBe(1280);
expect(cfg2.embedding_disabled).toBeUndefined();
}, 60000);
test('re-init WITHOUT flags still honors the deferred-setup sentinel (no regression)', async () => {
await runInitCapturing(['--pglite', '--non-interactive', '--no-embedding']);
const out = await runInitCapturing(['--pglite', '--non-interactive']);
expect(out).toContain('deferred setup');
const cfg = readCfg();
expect(cfg.embedding_disabled).toBe(true);
expect(cfg.embedding_model).toBeUndefined();
}, 60000);
});
+76
View File
@@ -166,6 +166,82 @@ describe('client registration', () => {
});
});
// ---------------------------------------------------------------------------
// rescopeClient (#1914) — admin-gated rescope of a DCR-defaulted client
// ---------------------------------------------------------------------------
describe('rescopeClient', () => {
beforeAll(async () => {
// oauth_clients.source_id has FK → sources(id); create the targets.
for (const id of ['wiki', 'essays', 'alpha', 'gamma']) {
await sql`INSERT INTO sources (id, name) VALUES (${id}, ${id}) ON CONFLICT (id) DO NOTHING`;
}
});
test('DCR client stuck on default gets rescoped; existing tokens pick it up', async () => {
// Simulate the DCR path: self-registered client lands with
// source_id='default', federated_read=['default']. client_credentials
// over DCR needs the explicit --enable-dcr-insecure opt-in, so build a
// provider with that flag just for this registration.
const dcrProvider = new GBrainOAuthProvider({ sql, tokenTtl: 60, allowClientCredentialsDcr: true });
const dcr = await dcrProvider.clientsStore.registerClient!({
client_name: 'dcr-stuck-client',
redirect_uris: [],
grant_types: ['client_credentials'],
scope: 'read',
token_endpoint_auth_method: 'client_secret_post',
} as any);
const clientId = dcr.client_id;
const [before] = await sql`SELECT source_id, federated_read FROM oauth_clients WHERE client_id = ${clientId}`;
expect(before.source_id).toBe('default');
expect(before.federated_read).toEqual(['default']);
// Issue a token BEFORE the rescope — it must see the new scope after.
const tokens = await provider.exchangeClientCredentials(clientId, dcr.client_secret!, 'read');
const result = await provider.rescopeClient(clientId, {
sourceId: 'wiki',
federatedRead: ['wiki', 'essays'],
});
expect(result.sourceId).toBe('wiki');
expect(result.federatedRead).toEqual(['wiki', 'essays']);
const authInfo = await provider.verifyAccessToken(tokens.access_token) as unknown as CoreAuthInfo;
expect(authInfo.sourceId).toBe('wiki');
expect(authInfo.allowedSources).toEqual(['wiki', 'essays']);
});
test('partial rescope leaves the other axis untouched', async () => {
const { clientId } = await provider.registerClientManual(
'partial-rescope', ['client_credentials'], 'read', [], 'alpha', ['alpha', 'beta'],
);
const result = await provider.rescopeClient(clientId, { federatedRead: ['beta'] });
expect(result.sourceId).toBe('alpha'); // untouched
expect(result.federatedRead).toEqual(['beta']);
const result2 = await provider.rescopeClient(clientId, { sourceId: 'gamma' });
expect(result2.sourceId).toBe('gamma');
expect(result2.federatedRead).toEqual(['beta']); // untouched
});
test('rejects invalid source ids, empty federated list, no-op calls, unknown client', async () => {
const { clientId } = await provider.registerClientManual(
'rescope-validation', ['client_credentials'], 'read',
);
await expect(provider.rescopeClient(clientId, { sourceId: '../etc' })).rejects.toThrow('Invalid source_id');
await expect(provider.rescopeClient(clientId, { federatedRead: ['ok', 'Not Valid!'] })).rejects.toThrow('Invalid source_id');
await expect(provider.rescopeClient(clientId, { federatedRead: [] })).rejects.toThrow('cannot be empty');
await expect(provider.rescopeClient(clientId, {})).rejects.toThrow('requires --source and/or --federated-read');
await expect(provider.rescopeClient('gbrain_cl_nonexistent', { sourceId: 'wiki' })).rejects.toThrow('No OAuth client found');
// FK: write source must exist in sources(id).
await expect(provider.rescopeClient(clientId, { sourceId: 'no-such-source' })).rejects.toThrow('does not exist');
// Validation failures must not have mutated the row.
const [row] = await sql`SELECT source_id FROM oauth_clients WHERE client_id = ${clientId}`;
expect(row.source_id).toBe('default');
});
});
// ---------------------------------------------------------------------------
// Client Credentials Exchange
// ---------------------------------------------------------------------------
-77
View File
@@ -15,7 +15,6 @@
*/
import { describe, test, expect } from 'bun:test';
import { withEnv, emptyHome } from './helpers/with-env.ts';
import {
runPhaseProposeTakes,
parseExtractorOutput,
@@ -53,14 +52,6 @@ function buildMockEngine(opts: {
},
async executeRaw<T>(sql: string, params?: unknown[]): Promise<T[]> {
captured.push({ sql, params: params ?? [] });
// Narrow candidate-page projection (replaces listPages in the phase).
if (sql.includes('SELECT slug, source_id, compiled_truth')) {
return opts.pages.map((p) => ({
slug: p.slug,
source_id: p.source_id,
compiled_truth: p.compiled_truth,
})) as T[];
}
// SELECT idempotency check
if (sql.includes('SELECT id FROM take_proposals')) {
const [sourceId, slug, ch, pv] = params ?? [];
@@ -485,72 +476,4 @@ New prose appended here.`;
resetGateway();
}
});
test('default extractor skips cleanly when the Anthropic chat model has no key', async () => {
// Empty GBRAIN_HOME so hasAnthropicKey's config-file fallback can't find
// the operator's real key.
await withEnv({ GBRAIN_HOME: emptyHome(), ANTHROPIC_API_KEY: undefined }, async () => {
configureGateway({ chat_model: 'anthropic:claude-sonnet-4-6', env: {} });
try {
const { engine, captured } = buildMockEngine({
pages: [buildPage({ slug: 'wiki/a', body: 'claim-ish prose' })],
});
const result = await runPhaseProposeTakes(buildCtx(engine));
expect(result.status).toBe('skipped');
expect((result.details as Record<string, unknown>).reason).toBe('no_provider');
// Skips BEFORE touching the engine — no page scan, no cache probes.
expect(captured).toHaveLength(0);
} finally {
resetGateway();
}
});
});
test('an injected extractor is never gated on provider availability', async () => {
await withEnv({ GBRAIN_HOME: emptyHome(), ANTHROPIC_API_KEY: undefined }, async () => {
configureGateway({ chat_model: 'anthropic:claude-sonnet-4-6', env: {} });
try {
const { engine } = buildMockEngine({
pages: [buildPage({ slug: 'wiki/b', body: 'still processed' })],
});
const extractor: ProposeTakesExtractor = async () => [];
const result = await runPhaseProposeTakes(buildCtx(engine), { extractor });
expect(result.status).toBe('ok');
expect((result.details as Record<string, unknown>).pages_scanned).toBe(1);
} finally {
resetGateway();
}
});
});
test('loads proposal candidates with a narrow page projection', async () => {
const pages = [buildPage({ slug: 'wiki/narrow', body: 'A narrow projection avoids unrelated page columns.' })];
const { engine, captured } = buildMockEngine({ pages });
const extractor: ProposeTakesExtractor = async () => [];
await runPhaseProposeTakes(buildCtx(engine), { extractor });
const pageSelect = captured.find(c => c.sql.includes('FROM pages'));
expect(pageSelect).toBeDefined();
expect(pageSelect!.sql).toContain('SELECT slug, source_id, compiled_truth');
expect(pageSelect!.sql).not.toContain('*');
// Scalar sourceId scope from ctx binds as a plain equality param.
expect(pageSelect!.params[0]).toBe('default');
});
test('narrow projection: federated sourceIds beat scalar sourceId', async () => {
const { engine, captured } = buildMockEngine({ pages: [] });
const extractor: ProposeTakesExtractor = async () => [];
const ctx = {
...buildCtx(engine),
auth: { allowedSources: ['team-a', 'team-b'] },
} as OperationContext;
await runPhaseProposeTakes(ctx, { extractor });
const pageSelect = captured.find(c => c.sql.includes('FROM pages'));
expect(pageSelect).toBeDefined();
expect(pageSelect!.sql).toContain('source_id = ANY(');
expect(pageSelect!.params[0]).toEqual(['team-a', 'team-b']);
});
});
-16
View File
@@ -100,22 +100,6 @@ describe('searchTakes', () => {
const worldHits = await engine.searchTakes('founder', { takesHoldersAllowList: ['world'] });
expect(worldHits.every(h => h.holder === 'world')).toBe(true);
});
// #3267: whole-string trigram % structurally can't match a short keyword
// against a long claim (similarity between the full strings stays under the
// 0.3 threshold). word_similarity (<%) matches the keyword against the
// best-matching word span instead.
test('single-word keyword matches a long claim containing it (#3267)', async () => {
await engine.addTakesBatch([
{
page_id: acmePageId, row_num: 50,
claim: 'Acme will consolidate the mid-market vertical SaaS landscape through disciplined acquisitions and a shared billing platform over the next five years',
kind: 'bet', holder: 'garry', weight: 0.6,
},
]);
const hits = await engine.searchTakes('consolidate');
expect(hits.some(h => h.claim.includes('consolidate the mid-market'))).toBe(true);
});
});
describe('updateTake', () => {