Compare commits

..
Author SHA1 Message Date
Garry TanandClaude Fable 5 2247540b4f fix(init,mcp): seed init AI options from env on cold install; whoami reports stdio transport
Two backlog fixes:

- init (#1058): loadConfig() returns null on a cold install (no config.json
  AND no DATABASE_URL), short-circuiting before its env merge — so
  GBRAIN_EMBEDDING_MODEL / GBRAIN_EMBEDDING_DIMENSIONS /
  GBRAIN_EXPANSION_MODEL / GBRAIN_CHAT_MODEL were silently ignored and
  Tier-3 detection auto-picked by API key instead. resolveAIOptions' config
  seed now falls back to those env vars directly when loadConfig() is null
  (new exported helper seedAIOptionsFromConfig, env-injectable for tests).

- whoami (#1061): the stdio MCP dispatch is remote/untrusted by design but
  has no per-token auth (local pipe), so whoami threw unknown_transport on
  the primary stdio surface. The stdio dispatch now marks
  ctx.transport = 'stdio' and whoami returns {transport: 'stdio', scopes: []}
  for it. Trust posture unchanged: remote stays true, the marker is never
  used for trust decisions, and an unmarked auth-less remote context still
  throws (fail-closed preserved).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:24:02 -07:00
9 changed files with 146 additions and 249 deletions
-64
View File
@@ -24,7 +24,6 @@ import type { GBrainConfig } from './core/config.ts';
import type { AIGatewayConfig } from './core/ai/types.ts';
import type { BrainEngine } from './core/engine.ts';
import { operations, OperationError } from './core/operations.ts';
import { resolveSourceIdEngineFree } from './core/source-resolver.ts';
import { formatVolunteeredPage } from './core/context/volunteer.ts';
import type { Operation, OperationContext } from './core/operations.ts';
import { shouldForceExitAfterMain, finishCliTeardown, flushThenExit, currentExitCode, setCliExitVerdict } from './core/cli-force-exit.ts';
@@ -383,15 +382,6 @@ async function main() {
if (op.localOnly) {
refuseThinClient(command, cfgPre!.remote_mcp!.mcp_url);
}
// #2098: the local path resolves --source / GBRAIN_SOURCE / .gbrain-source
// inside makeContext (ctx.sourceId), which this route never reaches — so
// scope must be mapped onto the op's source_id wire param before the call.
try {
applyThinClientSourceScope(op, params);
} catch (e: unknown) {
console.error(e instanceof Error ? e.message : String(e));
process.exit(1);
}
await runThinClientRouted(op, params, cfgPre!, cliOpts);
return;
}
@@ -812,60 +802,6 @@ export function parseOpArgs(op: Operation, args: string[]): Record<string, unkno
return params;
}
/**
* #2098: thin-client source scoping. Locally, --source / GBRAIN_SOURCE /
* .gbrain-source resolve to ctx.sourceId in makeContext; the thin-client
* route short-circuits before that, so `gbrain query --source X` against a
* remote brain silently searched unscoped. This runs the engine-free tiers
* (flag → env → dotfile; the DB-backed tiers can't run without an engine —
* the server's grant scoping covers the rest) and maps the result onto the
* op's `source_id` wire param.
*
* Ops that declare their OWN `source` param (facts add, etc.) are left
* untouched — their --source is an op param, not scope. An explicit --source
* on an op with no source_id wire param throws (loud beats silent drop);
* ambient env/dotfile scope with nowhere to send it is ignored, matching the
* pre-fix behavior for non-scopeable ops. Exported for tests.
*/
// Ops whose `source_id` wire param is NOT read-scope semantics: get_skill's
// source_id flips the lookup from host catalog to brain-resident-pack
// (getResidentSkillDetail). Ambient env/dotfile scope must never leak into
// these; an explicit --source-id still passes through untouched above.
const NON_SCOPE_SOURCE_ID_OPS = new Set(['get_skill']);
export function applyThinClientSourceScope(
op: Operation,
params: Record<string, unknown>,
cwd?: string,
): void {
if ('source' in op.params) return; // the op owns --source; not a scope flag
const explicit = typeof params.source === 'string' && params.source.length > 0
? (params.source as string)
: null;
delete params.source; // never a wire param on these ops — don't leak it
// Explicit per-call scope already on the wire wins over ambient tiers.
if (params.source_id !== undefined || params.all_sources === true) {
if (explicit) {
throw new Error('Pass either --source or --source-id/--all-sources, not both.');
}
return;
}
const resolved = resolveSourceIdEngineFree(explicit, cwd);
if (!resolved) return;
if (!('source_id' in op.params) || NON_SCOPE_SOURCE_ID_OPS.has(op.name)) {
if (explicit) {
const hint = NON_SCOPE_SOURCE_ID_OPS.has(op.name)
? `(its source_id parameter is not a scope filter; pass --source-id explicitly if you mean it)`
: `(the remote op has no source_id parameter; the server scopes it to your grant)`;
throw new Error(
`gbrain ${op.cliHints?.name || op.name} does not accept --source on a thin-client install ${hint}.`,
);
}
return; // ambient env/dotfile scope with nowhere to send it
}
params.source_id = resolved;
}
async function makeContext(engine: BrainEngine, params: Record<string, unknown>): Promise<OperationContext> {
// v0.31.8 (D11): resolve sourceId via the canonical 6-tier chain. Honors
// --source / GBRAIN_SOURCE / .gbrain-source / path-match / brain default /
+42 -12
View File
@@ -161,7 +161,7 @@ interface ResolveAIOptionsArgs {
nonInteractive: boolean; // --non-interactive (forces D3 fail-loud, no picker)
}
interface ResolvedAIOptions {
export interface ResolvedAIOptions {
embedding_model?: string;
embedding_dimensions?: number;
expansion_model?: string;
@@ -170,6 +170,41 @@ interface ResolvedAIOptions {
noEmbedding?: boolean;
}
/**
* Seed init's AI options from persisted config, falling back to the raw env
* vars when loadConfig() returned null (#1058). On a cold install (no
* config.json AND no DATABASE_URL) loadConfig short-circuits BEFORE its env
* merge, so GBRAIN_EMBEDDING_MODEL / GBRAIN_EMBEDDING_DIMENSIONS /
* GBRAIN_EXPANSION_MODEL / GBRAIN_CHAT_MODEL were silently ignored by init
* and Tier-3 detection auto-picked by API key instead. Exported for unit
* tests (env injectable).
*/
export function seedAIOptionsFromConfig(
cfg: GBrainConfig | null,
env: NodeJS.ProcessEnv = process.env,
): ResolvedAIOptions {
const envDims = env.GBRAIN_EMBEDDING_DIMENSIONS
? parseInt(env.GBRAIN_EMBEDDING_DIMENSIONS, 10)
: NaN;
const seed = cfg ?? {
embedding_disabled: undefined,
embedding_model: env.GBRAIN_EMBEDDING_MODEL,
embedding_dimensions: Number.isFinite(envDims) ? envDims : undefined,
expansion_model: env.GBRAIN_EXPANSION_MODEL,
chat_model: env.GBRAIN_CHAT_MODEL,
};
const out: ResolvedAIOptions = {};
if (seed.embedding_disabled) {
out.noEmbedding = true;
} else if (seed.embedding_model) {
out.embedding_model = seed.embedding_model;
if (seed.embedding_dimensions) out.embedding_dimensions = seed.embedding_dimensions;
}
if (seed.expansion_model) out.expansion_model = seed.expansion_model;
if (seed.chat_model) out.chat_model = seed.chat_model;
return out;
}
/**
* Resolve AI provider options for `gbrain init`.
*
@@ -203,18 +238,13 @@ async function resolveAIOptions(opts: ResolveAIOptionsArgs): Promise<ResolvedAIO
// user already opted into deferred mode.
try {
const { loadConfig } = await import('../core/config.ts');
const cfg = loadConfig();
if (cfg?.embedding_disabled) {
out.noEmbedding = true;
} else if (cfg?.embedding_model) {
out.embedding_model = cfg.embedding_model;
if (cfg.embedding_dimensions) out.embedding_dimensions = cfg.embedding_dimensions;
}
if (cfg?.expansion_model) out.expansion_model = cfg.expansion_model;
if (cfg?.chat_model) out.chat_model = cfg.chat_model;
// #1058: loadConfig() returns null on a cold install (no config.json AND
// no DATABASE_URL) — before it ever reaches its env merge. The seed helper
// falls back to the same GBRAIN_* env vars directly in that case.
Object.assign(out, seedAIOptionsFromConfig(loadConfig()));
} catch {
// loadConfig throws when no brain configured — first-time install, fall
// through to env detection.
// loadConfig threw — treat as first-time install, fall through to env
// detection.
}
// --- Tier 1+2: explicit flags ---------------------------------------------
+19 -3
View File
@@ -332,6 +332,15 @@ export interface OperationContext {
* remote/untrusted (defense in depth in case the type is bypassed via cast).
*/
remote: boolean;
/**
* Transport marker for auth-less remote surfaces (#1061). The stdio MCP
* dispatch sets 'stdio' — it is deliberately `remote: true` (agent-facing,
* untrusted) but has no per-token auth (local pipe), so identity ops like
* whoami need a way to distinguish "known auth-less transport" from "a
* transport bug forgot to thread ctx.auth". Trust decisions MUST NOT key
* off this field — only `ctx.remote === false` grants trust.
*/
transport?: 'stdio';
/**
* Subagent runtime context (v0.16+). Set by the subagent tool dispatcher when
* dispatching an op as a tool call from an LLM loop. Used to enforce per-op
@@ -3713,9 +3722,10 @@ const whoami: Operation = {
'Introspect the calling identity. Returns one of three transport shapes: ' +
'{transport: "oauth", client_id, client_name, scopes, expires_at}, ' +
'{transport: "legacy", token_name, scopes, expires_at: null}, or ' +
'{transport: "local", scopes: []}. Throws unknown_transport when the ' +
'context is ambiguous (remote=true without auth) — fail-closed posture ' +
'mirroring the v0.26.9 trust-boundary contract.',
'{transport: "local", scopes: []}, or {transport: "stdio", scopes: []} ' +
'for the auth-less stdio MCP pipe. Throws unknown_transport when the ' +
'context is ambiguous (remote=true without auth and no transport marker) ' +
'— fail-closed posture mirroring the v0.26.9 trust-boundary contract.',
params: {},
scope: 'read',
handler: async (ctx) => {
@@ -3727,6 +3737,12 @@ const whoami: Operation = {
if (ctx.remote === false) {
return { transport: 'local', scopes: [] };
}
// #1061: stdio MCP is remote/untrusted by design but has no per-token
// auth (local pipe) — a known transport, not a bug. Report it instead of
// throwing. Empty scopes: nothing here may be used to gate anything.
if (!ctx.auth && ctx.transport === 'stdio') {
return { transport: 'stdio', scopes: [] };
}
if (!ctx.auth) {
throw new OperationError(
'unknown_transport',
-27
View File
@@ -160,33 +160,6 @@ export async function resolveSourceId(
return 'default';
}
/**
* Engine-free tiers (1-3) of the resolution chain: explicit flag →
* GBRAIN_SOURCE env → .gbrain-source dotfile walk. Used by the thin-client
* CLI path (#2098), which has no local engine to run tiers 4-6 or
* assertSourceExists against — the remote server enforces existence + grant.
* Returns null when no engine-free tier fires.
*/
export function resolveSourceIdEngineFree(
explicit: string | null | undefined,
cwd: string = process.cwd(),
): string | null {
if (explicit) {
if (!SOURCE_ID_RE.test(explicit)) {
throw new Error(`Invalid --source value "${explicit}". Must match [a-z0-9-]{1,32}.`);
}
return explicit;
}
const env = process.env.GBRAIN_SOURCE;
if (env && env.length > 0) {
if (!SOURCE_ID_RE.test(env)) {
throw new Error(`Invalid GBRAIN_SOURCE value "${env}". Must match [a-z0-9-]{1,32}.`);
}
return env;
}
return readDotfileWalk(cwd);
}
/**
* Returns the id of the SINGLE registered non-default source with a
* local_path, when exactly one such row exists. Returns null when:
+7
View File
@@ -32,6 +32,12 @@ export interface DispatchOpts {
remote?: boolean;
/** Override the default stderr logger (e.g. CLI uses console.* directly). */
logger?: OperationContext['logger'];
/**
* #1061: transport marker for auth-less remote surfaces. The stdio MCP
* server passes 'stdio' so identity ops (whoami) can report the transport
* instead of throwing unknown_transport. Never used for trust decisions.
*/
transport?: OperationContext['transport'];
/**
* v0.28: per-token allow-list for the takes.holder field. Threaded by
* the HTTP/stdio transport from `access_tokens.permissions.takes_holders`.
@@ -203,6 +209,7 @@ export function buildOperationContext(
logger: opts.logger || stderrLogger,
dryRun: !!params.dry_run,
remote: opts.remote ?? true,
transport: opts.transport,
takesHoldersAllowList: opts.takesHoldersAllowList,
// v0.34 D4: sourceId is REQUIRED at the type level. Auto-fill 'default'
// for single-source brains and any caller who didn't resolve a sourceId.
+4
View File
@@ -42,6 +42,10 @@ export async function startMcpServer(engine: BrainEngine) {
// `gbrain call <op>` (sets remote=false in src/cli.ts).
return dispatchToolCall(engine, name, params, {
remote: true,
// #1061: mark the transport so whoami can report {transport: 'stdio'}
// instead of throwing unknown_transport. Trust posture unchanged —
// stdio stays remote/untrusted.
transport: 'stdio',
takesHoldersAllowList: ['world'],
// v0.31: source defaults to 'default' for stdio (no per-token scope).
// Operators who want a different source on stdio MCP should set
+45 -1
View File
@@ -12,7 +12,7 @@
*/
import { describe, test, expect } from 'bun:test';
import { groupReadyByProvider, findEnvKeyTypos } from '../src/commands/init.ts';
import { groupReadyByProvider, findEnvKeyTypos, seedAIOptionsFromConfig } from '../src/commands/init.ts';
describe('groupReadyByProvider — embedding touchpoint', () => {
test('OPENAI_API_KEY alone → openai is ready', async () => {
@@ -149,3 +149,47 @@ describe('findEnvKeyTypos', () => {
expect(got.find(t => t.userSet === 'COMPLETELY_UNRELATED_KEY')).toBeUndefined();
});
});
describe('seedAIOptionsFromConfig — #1058 cold-install env fallback', () => {
test('null config (no config.json, no DATABASE_URL) falls back to GBRAIN_* env vars', () => {
const got = seedAIOptionsFromConfig(null, {
GBRAIN_EMBEDDING_MODEL: 'voyage:voyage-3-large',
GBRAIN_EMBEDDING_DIMENSIONS: '1024',
GBRAIN_EXPANSION_MODEL: 'openai:gpt-5-mini',
GBRAIN_CHAT_MODEL: 'anthropic:claude-sonnet-4-6',
});
expect(got.embedding_model).toBe('voyage:voyage-3-large');
expect(got.embedding_dimensions).toBe(1024);
expect(got.expansion_model).toBe('openai:gpt-5-mini');
expect(got.chat_model).toBe('anthropic:claude-sonnet-4-6');
});
test('null config + no env vars → empty seed (Tier-3 detection takes over)', () => {
const got = seedAIOptionsFromConfig(null, {});
expect(got).toEqual({});
});
test('persisted config wins (loadConfig already merged env when non-null)', () => {
const got = seedAIOptionsFromConfig(
{ engine: 'pglite', embedding_model: 'openai:text-embedding-3-small', embedding_dimensions: 1536 } as any,
{ GBRAIN_EMBEDDING_MODEL: 'voyage:voyage-3-large' },
);
expect(got.embedding_model).toBe('openai:text-embedding-3-small');
expect(got.embedding_dimensions).toBe(1536);
});
test('embedding_disabled sentinel honored on re-init', () => {
const got = seedAIOptionsFromConfig({ engine: 'pglite', embedding_disabled: true } as any, {});
expect(got.noEmbedding).toBe(true);
expect(got.embedding_model).toBeUndefined();
});
test('non-numeric GBRAIN_EMBEDDING_DIMENSIONS ignored, model still seeds', () => {
const got = seedAIOptionsFromConfig(null, {
GBRAIN_EMBEDDING_MODEL: 'voyage:voyage-3-large',
GBRAIN_EMBEDDING_DIMENSIONS: 'not-a-number',
});
expect(got.embedding_model).toBe('voyage:voyage-3-large');
expect(got.embedding_dimensions).toBeUndefined();
});
});
-142
View File
@@ -1,142 +0,0 @@
/**
* #2098: thin-client routing dropped --source / GBRAIN_SOURCE / .gbrain-source.
*
* The local CLI path resolves source scope in makeContext (ctx.sourceId); the
* thin-client route short-circuits before that and sent params verbatim, so
* `gbrain query --source X` against a remote brain silently searched unscoped
* (the server op ignores the unknown `source` key).
*
* applyThinClientSourceScope runs the engine-free tiers (flag → env → dotfile)
* and maps the result onto the op's `source_id` wire param. These tests fail
* without the fix (params.source_id stays undefined / params.source leaks).
*/
import { describe, test, expect } from 'bun:test';
import { mkdtempSync, rmSync, writeFileSync } from 'fs';
import { join } from 'path';
import { tmpdir } from 'os';
import { applyThinClientSourceScope, parseOpArgs } from '../src/cli.ts';
import { operationsByName } from '../src/core/operations.ts';
import { withEnv } from './helpers/with-env.ts';
const queryOp = operationsByName.query;
describe('applyThinClientSourceScope (#2098)', () => {
test('--source maps onto the query op wire param source_id', async () => {
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
const params = parseOpArgs(queryOp, ['find things', '--source', 'wiki']);
expect(params.source).toBe('wiki'); // pre-fix state: wrong key
applyThinClientSourceScope(queryOp, params, '/');
expect(params.source_id).toBe('wiki');
expect('source' in params).toBe(false); // never leaks the unknown key
});
});
test('GBRAIN_SOURCE env tier fires when no flag is passed', async () => {
await withEnv({ GBRAIN_SOURCE: 'gstack' }, () => {
const params = parseOpArgs(queryOp, ['find things']);
applyThinClientSourceScope(queryOp, params, '/');
expect(params.source_id).toBe('gstack');
});
});
test('.gbrain-source dotfile tier fires when flag and env are absent', async () => {
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
const tmp = mkdtempSync(join(tmpdir(), 'gbrain-thin-scope-'));
try {
writeFileSync(join(tmp, '.gbrain-source'), 'essays\n');
const params = parseOpArgs(queryOp, ['find things']);
applyThinClientSourceScope(queryOp, params, tmp);
expect(params.source_id).toBe('essays');
} finally {
rmSync(tmp, { recursive: true, force: true });
}
});
});
test('explicit --source-id on the wire wins over ambient env scope', async () => {
await withEnv({ GBRAIN_SOURCE: 'gstack' }, () => {
const params = parseOpArgs(queryOp, ['find things', '--source-id', 'wiki']);
applyThinClientSourceScope(queryOp, params, '/');
expect(params.source_id).toBe('wiki');
});
});
test('--source together with --source-id is rejected loudly', async () => {
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
const params = parseOpArgs(queryOp, ['q', '--source', 'a', '--source-id', 'b']);
expect(() => applyThinClientSourceScope(queryOp, params, '/')).toThrow(/not both/);
});
});
test('invalid --source value is rejected loudly', async () => {
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
const params = parseOpArgs(queryOp, ['q', '--source', 'Bad_Value!']);
expect(() => applyThinClientSourceScope(queryOp, params, '/')).toThrow(/Invalid --source/);
});
});
test('--source on an op with no source_id wire param errors instead of silently dropping', async () => {
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
const op = operationsByName.add_tag;
expect('source_id' in op.params).toBe(false);
const params = { slug: 'x', tag: 'y', source: 'wiki' };
expect(() => applyThinClientSourceScope(op, params, '/')).toThrow(/--source/);
});
});
test('ambient env scope on an op with no source_id wire param is ignored (no throw)', async () => {
await withEnv({ GBRAIN_SOURCE: 'wiki' }, () => {
const op = operationsByName.add_tag;
const params: Record<string, unknown> = { slug: 'x', tag: 'y' };
applyThinClientSourceScope(op, params, '/');
expect(params.source_id).toBeUndefined();
});
});
test('ops that declare their OWN source param are left untouched', async () => {
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
const op = operationsByName.put_raw_data;
expect('source' in op.params).toBe(true);
const params: Record<string, unknown> = { slug: 'x', source: 'crustdata', data: {} };
applyThinClientSourceScope(op, params, '/');
expect(params.source).toBe('crustdata');
expect(params.source_id).toBeUndefined();
});
});
test('get_skill: ambient scope never leaks into its non-scope source_id param', async () => {
await withEnv({ GBRAIN_SOURCE: 'wiki' }, () => {
const op = operationsByName.get_skill;
expect('source_id' in op.params).toBe(true); // has the param, but it is a mode switch
const params: Record<string, unknown> = { name: 'ingest' };
applyThinClientSourceScope(op, params, '/');
expect(params.source_id).toBeUndefined(); // would flip host catalog → brain-pack lookup
});
});
test('get_skill: explicit --source errors instead of masquerading as --source-id', async () => {
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
const op = operationsByName.get_skill;
const params: Record<string, unknown> = { name: 'ingest', source: 'wiki' };
expect(() => applyThinClientSourceScope(op, params, '/')).toThrow(/--source-id/);
});
});
test('get_skill: explicit --source-id passes through untouched', async () => {
await withEnv({ GBRAIN_SOURCE: 'gstack' }, () => {
const op = operationsByName.get_skill;
const params: Record<string, unknown> = { name: 'ingest', source_id: 'wiki' };
applyThinClientSourceScope(op, params, '/');
expect(params.source_id).toBe('wiki');
});
});
test('no scope from any tier leaves params unchanged', async () => {
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
const params = parseOpArgs(queryOp, ['find things']);
applyThinClientSourceScope(queryOp, params, '/');
expect(params.source_id).toBeUndefined();
});
});
});
+29
View File
@@ -94,6 +94,35 @@ describe('whoami op contract', () => {
expect(result.expires_at).toBeNull();
});
// #1061: stdio MCP is remote/untrusted by design but has no per-token auth
// (local pipe). The stdio dispatch marks ctx.transport='stdio'; whoami
// reports it instead of throwing unknown_transport.
test('stdio transport (remote=true, no auth, transport marker) reports stdio', async () => {
const result = (await whoami.handler(
ctxWith({ remote: true, auth: undefined, transport: 'stdio' }),
{},
)) as any;
expect(result.transport).toBe('stdio');
expect(result.scopes).toEqual([]);
});
test('stdio marker does not mask real auth (auth still wins)', async () => {
const result = (await whoami.handler(
ctxWith({
remote: true,
transport: 'stdio',
auth: {
token: 'gbrain_at_xxx',
clientId: 'gbrain_cl_abc',
scopes: ['read'],
expiresAt: 1,
} as AuthInfo,
}),
{},
)) as any;
expect(result.transport).toBe('oauth');
});
// Q3: ambiguous transport — fail-closed. The footgun this guards against
// is a future transport that lands without threading auth, where a buggy
// caller might trust whoami's output to gate sensitive ops.