mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-16 18:02:30 +00:00
Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
2247540b4f |
@@ -1651,7 +1651,7 @@ async function extractTimelineFromDB(
|
||||
* make re-extraction idempotent). EVERY processed page is stamped, including
|
||||
* zero-link pages — they WERE processed.
|
||||
*/
|
||||
export async function extractStaleFromDB(
|
||||
async function extractStaleFromDB(
|
||||
engine: BrainEngine,
|
||||
opts: {
|
||||
dryRun: boolean;
|
||||
|
||||
+42
-12
@@ -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 ---------------------------------------------
|
||||
|
||||
+1
-39
@@ -1479,31 +1479,7 @@ export async function registerBuiltinHandlers(
|
||||
embedSkipReason = 'auto_embed_disabled';
|
||||
}
|
||||
|
||||
// #2849: large-sync extract deferral follow-up. performSync skips inline
|
||||
// link/timeline extraction when totalChanges > 100, leaving
|
||||
// links_extracted_at unstamped. A standalone sync job (webhook push,
|
||||
// sync trigger) has no autopilot extract phase behind it, so the pages
|
||||
// would stay extraction-stale until a manual `gbrain extract --stale`.
|
||||
// Queue a source-scoped stale sweep instead. Best-effort + idempotent:
|
||||
// a duplicate sweep finds 0 stale pages and no-ops.
|
||||
let extractJobId: number | null = null;
|
||||
if (result.extractDeferred) {
|
||||
try {
|
||||
const { MinionQueue } = await import('../core/minions/queue.ts');
|
||||
const queue = new MinionQueue(engine);
|
||||
const followUp = await queue.add(
|
||||
'extract',
|
||||
{ stale: true, ...(sourceId ? { sourceId } : {}) },
|
||||
{
|
||||
idempotency_key: `sync-extract-stale:${sourceId ?? 'default'}:${Math.floor(Date.now() / 30_000)}`,
|
||||
maxWaiting: 1,
|
||||
},
|
||||
);
|
||||
extractJobId = followUp.id;
|
||||
} catch { /* best-effort: extract --stale sweeps it later */ }
|
||||
}
|
||||
|
||||
return { ...result, embed_job_id: embedJobId, embed_skip_reason: embedSkipReason, extract_stale_job_id: extractJobId };
|
||||
return { ...result, embed_job_id: embedJobId, embed_skip_reason: embedSkipReason };
|
||||
});
|
||||
|
||||
registerBuiltinJob(worker, engine, 'embed', async (job) => {
|
||||
@@ -1676,20 +1652,6 @@ export async function registerBuiltinHandlers(
|
||||
});
|
||||
|
||||
worker.register('extract', async (job) => {
|
||||
// #2849: stale-sweep mode — the sync handler's large-sync deferral
|
||||
// follow-up. DB-source (reads page content from the DB, so it runs on
|
||||
// checkout-less brains), source-scopable, idempotent. Same core as
|
||||
// `gbrain extract --stale`.
|
||||
if (job.data.stale === true) {
|
||||
const { extractStaleFromDB } = await import('./extract.ts');
|
||||
return await extractStaleFromDB(engine, {
|
||||
dryRun: !!job.data.dryRun,
|
||||
jsonMode: false,
|
||||
includeFrontmatter: false,
|
||||
sourceIdFilter: typeof job.data.sourceId === 'string' ? job.data.sourceId : undefined,
|
||||
catchUp: false,
|
||||
});
|
||||
}
|
||||
const { runExtractCore } = await import('./extract.ts');
|
||||
const mode = (typeof job.data.mode === 'string' && ['links', 'timeline', 'all'].includes(job.data.mode))
|
||||
? (job.data.mode as 'links' | 'timeline' | 'all')
|
||||
|
||||
@@ -2146,13 +2146,8 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
|
||||
// Other event types (ping, pull_request, etc.) return 202 'ignored'
|
||||
// so GitHub doesn't retry.
|
||||
// D15.5: HMAC compare uses the shared safeHexEqual helper.
|
||||
// D18: submits 'sync' job with extraction + auto_embed_backfill enabled and
|
||||
// priority -10 (above autopilot's 0). noExtract:false opts normal
|
||||
// incremental pushes into sync's inline link/timeline extraction (#2849
|
||||
// — the standalone sync handler defaults noExtract to TRUE, which left
|
||||
// webhook-imported pages permanently stale). Large (>100 file) pushes
|
||||
// defer inline extract; the sync handler queues an extract --stale
|
||||
// follow-up job for that branch.
|
||||
// D18: submits 'sync' job with auto_embed_backfill=true and priority -10
|
||||
// (above autopilot's 0).
|
||||
// ---------------------------------------------------------------------------
|
||||
const githubWebhookLimiter = rateLimit({
|
||||
windowMs: 60_000,
|
||||
@@ -2272,7 +2267,6 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
|
||||
'sync',
|
||||
{
|
||||
sourceId: source.id,
|
||||
noExtract: false,
|
||||
auto_embed_backfill: true,
|
||||
embed_reason: 'webhook',
|
||||
},
|
||||
|
||||
+1
-19
@@ -222,14 +222,6 @@ export interface SyncResult {
|
||||
* everything," the exact misdiagnosis in the #1794 recurrence report.
|
||||
*/
|
||||
bankedFiles?: number;
|
||||
/**
|
||||
* #2849: true when extraction was REQUESTED (noExtract false) but this sync
|
||||
* skipped inline link/timeline extraction because totalChanges > 100 (the
|
||||
* #1794 large-sync deferral). links_extracted_at stays unstamped for the
|
||||
* imported pages. The standalone `sync` job handler queues a source-scoped
|
||||
* `extract --stale` follow-up when set; CLI runs print the manual hint.
|
||||
*/
|
||||
extractDeferred?: boolean;
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -1387,10 +1379,6 @@ See also:
|
||||
{
|
||||
sourceId: sourceIdArg,
|
||||
repoPath: source.local_path,
|
||||
// #2849: opt in to inline extraction — the standalone sync handler
|
||||
// defaults noExtract to TRUE (dedupe for doctor's [sync, extract]
|
||||
// remediation plan), which would leave triggered syncs extraction-stale.
|
||||
noExtract: false,
|
||||
auto_embed_backfill: true,
|
||||
embed_reason: 'sync_trigger',
|
||||
},
|
||||
@@ -3299,16 +3287,11 @@ async function performSyncInner(engine: BrainEngine, opts: SyncOpts): Promise<Sy
|
||||
// the stale sweep scans the whole source, so banked-across-runs pages are
|
||||
// covered regardless.
|
||||
const extractOpts = opts.sourceId ? { sourceId: opts.sourceId } : undefined;
|
||||
let extractDeferred = false;
|
||||
if (!opts.noExtract && totalChanges > 100 && pagesAffected.length > 0) {
|
||||
// #2849: surface the deferral to callers. A standalone sync job (webhook
|
||||
// push, sync trigger) has no autopilot extract phase behind it, so the
|
||||
// job handler queues an `extract --stale` follow-up off this flag.
|
||||
extractDeferred = true;
|
||||
slog(
|
||||
` Large sync: deferring link/timeline extraction. ` +
|
||||
`Run 'gbrain extract --stale${opts.sourceId ? ` --source-id ${opts.sourceId}` : ''}' ` +
|
||||
`(sync jobs queue this follow-up automatically).`,
|
||||
`(or let the autopilot cycle's extract phase sweep it).`,
|
||||
);
|
||||
}
|
||||
if (!opts.noExtract && totalChanges <= 100 && pagesAffected.length > 0) {
|
||||
@@ -3417,7 +3400,6 @@ async function performSyncInner(engine: BrainEngine, opts: SyncOpts): Promise<Sy
|
||||
chunksCreated,
|
||||
embedded,
|
||||
pagesAffected,
|
||||
extractDeferred,
|
||||
};
|
||||
}
|
||||
|
||||
|
||||
+19
-3
@@ -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',
|
||||
|
||||
@@ -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.
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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();
|
||||
});
|
||||
});
|
||||
|
||||
@@ -16,7 +16,6 @@
|
||||
*/
|
||||
import { describe, test, expect } from 'bun:test';
|
||||
import { createHmac } from 'node:crypto';
|
||||
import { readFileSync } from 'node:fs';
|
||||
import { safeHexEqual } from '../src/core/timing-safe.ts';
|
||||
|
||||
const GITHUB_SECRET = 'super-secret-webhook-key';
|
||||
@@ -124,25 +123,3 @@ describe('Branch ref construction (D5)', () => {
|
||||
expect(pushedRef === `refs/heads/${trackedBranch}`).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
describe('Webhook sync job extraction contract (#2849)', () => {
|
||||
test('opts into extraction before the pushed commit is consumed', () => {
|
||||
const serveSource = readFileSync(
|
||||
new URL('../src/commands/serve-http.ts', import.meta.url),
|
||||
'utf8',
|
||||
);
|
||||
const routeStart = serveSource.indexOf("'/webhooks/github'");
|
||||
const queueStart = serveSource.indexOf('const job = await queue.add(', routeStart);
|
||||
const responseStart = serveSource.indexOf('res.status(202)', queueStart);
|
||||
expect(routeStart).toBeGreaterThanOrEqual(0);
|
||||
expect(queueStart).toBeGreaterThan(routeStart);
|
||||
expect(responseStart).toBeGreaterThan(queueStart);
|
||||
|
||||
const routeSource = serveSource.slice(queueStart, responseStart);
|
||||
const payload = routeSource.match(
|
||||
/queue\.add\(\s*'sync',\s*\{([\s\S]*?)\}\s*,\s*\{/,
|
||||
);
|
||||
expect(payload).not.toBeNull();
|
||||
expect(payload?.[1]).toMatch(/\bnoExtract:\s*false\b/);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -1,130 +0,0 @@
|
||||
/**
|
||||
* #2849 — large-sync extract deferral queues an `extract --stale` follow-up.
|
||||
*
|
||||
* performSync's incremental path skips inline link/timeline extraction when
|
||||
* totalChanges > 100 (the #1794 large-sync deferral), leaving
|
||||
* links_extracted_at unstamped. Pre-fix, a standalone sync job (webhook push,
|
||||
* `gbrain sync trigger`) had NOTHING behind it to sweep those pages — the
|
||||
* autopilot cycle's extract phase only walks that cycle's changedSlugs — so a
|
||||
* large webhook push left extraction permanently stale until a manual
|
||||
* `gbrain extract --stale`.
|
||||
*
|
||||
* Pins:
|
||||
* (a) performSync surfaces `extractDeferred: true` on the >100 branch and
|
||||
* leaves the pages unstamped/unlinked.
|
||||
* (b) the `sync` job handler queues an `extract` job with
|
||||
* { stale: true, sourceId? } when extractDeferred is set.
|
||||
* (c) the `extract` handler's stale mode actually sweeps: links created +
|
||||
* watermark stamped (end-to-end recovery, no manual step).
|
||||
*
|
||||
* Marked .serial.test.ts — spawns git subprocesses + shares one PGLite engine.
|
||||
*/
|
||||
|
||||
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
|
||||
import { mkdtempSync, writeFileSync, rmSync, mkdirSync } from 'fs';
|
||||
import { execSync } from 'child_process';
|
||||
import { tmpdir } from 'os';
|
||||
import { join } from 'path';
|
||||
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
|
||||
import { MinionWorker } from '../src/core/minions/worker.ts';
|
||||
import { MinionQueue } from '../src/core/minions/queue.ts';
|
||||
import { registerBuiltinHandlers } from '../src/commands/jobs.ts';
|
||||
|
||||
let engine: PGLiteEngine;
|
||||
let worker: MinionWorker;
|
||||
let repoPath: string;
|
||||
|
||||
function git(cmd: string): void { execSync(cmd, { cwd: repoPath, stdio: 'pipe' }); }
|
||||
|
||||
describe('#2849 — large sync defers extract and queues a stale sweep', () => {
|
||||
beforeAll(async () => {
|
||||
engine = new PGLiteEngine();
|
||||
await engine.connect({});
|
||||
await engine.initSchema();
|
||||
worker = new MinionWorker(engine, { queue: 'test' });
|
||||
await registerBuiltinHandlers(worker, engine, { quiet: true });
|
||||
|
||||
repoPath = mkdtempSync(join(tmpdir(), 'gbrain-large-defer-'));
|
||||
git('git init');
|
||||
git('git config user.email "t@t.com"');
|
||||
git('git config user.name "T"');
|
||||
mkdirSync(join(repoPath, 'people'), { recursive: true });
|
||||
mkdirSync(join(repoPath, 'notes'), { recursive: true });
|
||||
writeFileSync(join(repoPath, 'people/alice.md'), [
|
||||
'---', 'type: person', 'title: Alice', '---', '', 'Alice is a founder.',
|
||||
].join('\n'));
|
||||
git('git add -A && git commit -m "initial"');
|
||||
|
||||
// Seed: full first sync imports the anchor page + sets last_commit.
|
||||
const { performSync } = await import('../src/commands/sync.ts');
|
||||
await performSync(engine, { repoPath, full: true, noPull: true, noEmbed: true });
|
||||
|
||||
// Second commit: 101 new pages → incremental totalChanges > 100.
|
||||
for (let i = 0; i < 101; i++) {
|
||||
writeFileSync(join(repoPath, `notes/n${i}.md`), [
|
||||
'---', 'type: note', `title: Note ${i}`, '---', '',
|
||||
`[Alice](people/alice) appears in note ${i}.`,
|
||||
].join('\n'));
|
||||
}
|
||||
git('git add -A && git commit -m "add 101 pages"');
|
||||
}, 120_000);
|
||||
|
||||
afterAll(async () => {
|
||||
if (repoPath) rmSync(repoPath, { recursive: true, force: true });
|
||||
if (engine) await engine.disconnect();
|
||||
}, 60_000);
|
||||
|
||||
test('sync handler defers inline extract and queues extract{stale} follow-up; stale sweep recovers', async () => {
|
||||
const syncHandler = (worker as unknown as { handlers: Map<string, (job: unknown) => Promise<unknown>> })
|
||||
.handlers.get('sync');
|
||||
expect(syncHandler).toBeDefined();
|
||||
|
||||
// Same payload shape the webhook submits (minus embed backfill noise).
|
||||
const result = await syncHandler!({
|
||||
data: { repoPath, noExtract: false, noPull: true, auto_embed_backfill: false },
|
||||
signal: { aborted: false },
|
||||
updateProgress: async () => {},
|
||||
}) as { status: string; extractDeferred?: boolean; extract_stale_job_id?: number | null };
|
||||
|
||||
expect(result.status).toBe('synced');
|
||||
// (a) inline extract was deferred, pages left stale.
|
||||
expect(result.extractDeferred).toBe(true);
|
||||
const staleBefore = await engine.countStalePagesForExtraction();
|
||||
expect(staleBefore).toBeGreaterThan(100);
|
||||
expect(await engine.getLinks('notes/n0')).toHaveLength(0);
|
||||
|
||||
// (b) a follow-up extract job with stale:true was queued.
|
||||
expect(result.extract_stale_job_id).toBeGreaterThan(0);
|
||||
const queue = new MinionQueue(engine);
|
||||
const extractJobs = await queue.getJobs({ name: 'extract', limit: 5 });
|
||||
expect(extractJobs.length).toBe(1);
|
||||
expect((extractJobs[0].data as { stale: boolean }).stale).toBe(true);
|
||||
|
||||
// (c) running the extract handler's stale mode recovers: links + stamps.
|
||||
const extractHandler = (worker as unknown as { handlers: Map<string, (job: unknown) => Promise<unknown>> })
|
||||
.handlers.get('extract');
|
||||
await extractHandler!({
|
||||
data: extractJobs[0].data,
|
||||
signal: { aborted: false },
|
||||
updateProgress: async () => {},
|
||||
});
|
||||
const links = await engine.getLinks('notes/n0');
|
||||
expect(links.some(l => l.to_slug === 'people/alice')).toBe(true);
|
||||
const rows = await engine.executeRaw<{ links_extracted_at: string | null }>(
|
||||
`SELECT links_extracted_at FROM pages WHERE slug = 'notes/n0'`,
|
||||
);
|
||||
expect(rows[0]?.links_extracted_at).not.toBeNull();
|
||||
}, 180_000);
|
||||
|
||||
test('sub-threshold sync does NOT set extractDeferred (no spurious follow-up)', async () => {
|
||||
// One more small commit → inline extract path, no deferral.
|
||||
writeFileSync(join(repoPath, 'notes/small.md'), [
|
||||
'---', 'type: note', 'title: Small', '---', '', 'No big deal.',
|
||||
].join('\n'));
|
||||
git('git add -A && git commit -m "one small page"');
|
||||
const { performSync } = await import('../src/commands/sync.ts');
|
||||
const result = await performSync(engine, { repoPath, noPull: true, noEmbed: true });
|
||||
expect(result.status).toBe('synced');
|
||||
expect(result.extractDeferred).toBeFalsy();
|
||||
}, 60_000);
|
||||
});
|
||||
@@ -100,10 +100,6 @@ describe('runSyncTrigger', () => {
|
||||
const job = jobs[0];
|
||||
expect(job.priority).toBe(-10);
|
||||
expect((job.data as { sourceId: string }).sourceId).toBe('default');
|
||||
// #2849: opt in to inline extraction — the standalone sync handler
|
||||
// defaults noExtract to TRUE, which would leave triggered syncs
|
||||
// extraction-stale.
|
||||
expect((job.data as { noExtract: boolean }).noExtract).toBe(false);
|
||||
expect((job.data as { auto_embed_backfill: boolean }).auto_embed_backfill).toBe(true);
|
||||
});
|
||||
|
||||
|
||||
@@ -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.
|
||||
|
||||
Reference in New Issue
Block a user